diff --git a/.github/workflows/tests-core.yaml b/.github/workflows/tests-core.yaml index aab3713..917cfbb 100644 --- a/.github/workflows/tests-core.yaml +++ b/.github/workflows/tests-core.yaml @@ -16,7 +16,8 @@ jobs: fail-fast: false matrix: python-version: ["3.10", "3.11", "3.12"] - os: [ubuntu-22.04, ubuntu-latest] + os: [ubuntu-22.04] + #TODO: re-enable ubuntu-latest, this is disabled as oscrypto cannot be pinned to github commit and pushed to pypi defaults: run: working-directory: ./ diff --git a/.gitignore b/.gitignore index 7c6bf08..701de43 100644 --- a/.gitignore +++ b/.gitignore @@ -32,3 +32,4 @@ archived/ dist* docs/_build/ docs/source/autoapi/ +docs/source/modules/autogen/ diff --git a/.readthedocs.yaml b/.readthedocs.yaml index 9f67835..434f805 100644 --- a/.readthedocs.yaml +++ b/.readthedocs.yaml @@ -15,7 +15,7 @@ build: # https://python-poetry.org/docs/managing-dependencies/#dependency-groups # VIRTUAL_ENV needs to be set manually for now. # See https://github.com/readthedocs/readthedocs.org/pull/11152/ - - VIRTUAL_ENV=$READTHEDOCS_VIRTUALENV_PATH poetry install --only docs + - VIRTUAL_ENV=$READTHEDOCS_VIRTUALENV_PATH poetry install --with docs sphinx: diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md new file mode 100644 index 0000000..7e71f82 --- /dev/null +++ b/CONTRIBUTING.md @@ -0,0 +1,49 @@ +# Contributing to Auto Archiver + +Thank you for your interest in contributing to Auto Archiver! Your contributions help improve the project and make it more useful for everyone. Please follow the guidelines below to ensure a smooth collaboration. + +### 1. Reporting a Bug + +If you encounter a bug, please create an issue on GitHub with the following details: + +* Describe the bug: Provide a clear and concise description of the issue. +* Steps to reproduce: Include the steps needed to reproduce the bug. +* Expected behavior: Describe what you expected to happen. +* Actual behavior: Explain what actually happened. +* Screenshots/logs: If applicable, attach screenshots or logs to help diagnose the problem. +* Environment: Mention the OS, Ruby version, and any other relevant details. + +### 2. Writing a Patch/Fix and Submitting Pull Requests + +If you’d like to fix a bug or improve existing code: + +1. Open a pull request on GitHub and link it to the relevant issue. +2. Make sure to document your pull request with a clear description of what changes were made and why. +3. Wait for review and make any requested changes. + +### 3. Creating New Modules + +If you want to add a new module to Auto Archiver: + +1. Ensure your module follows the existing [coding style and project structure](https://auto-archiver.readthedocs.io/en/latest/development/creating_modules.html). +2. Write clear documentation explaining what your module does and how to use it. +3. Ideally, include unit tests for your module! +4. Follow the steps in Section 2 to submit a pull request. + +### 4. Do You Have Questions About the Source Code? + +If you have any questions about how the source code works or need help using Auto Archiver + +📝 Check the [Auto Archiver](https://auto-archiver.readthedocs.io/en/latest/) documentation. + +👉 Ask your questions in the [Bellingcat Discord](https://www.bellingcat.com/follow-bellingcat-on-social-media/). + +### 5. Do You Want to Contribute to the Documentation? + +We welcome contributions to the documentation! + +📖 Please read [Contributing to the Auto Archiver Documentation](https://auto-archiver.readthedocs.io/en/latest/development/docs.html) to learn how you can help improve the project's documentation. + +------------------ + +Thank you for contributing to Auto Archiver! 🚀 \ No newline at end of file diff --git a/README.md b/README.md index c52c464..368a904 100644 --- a/README.md +++ b/README.md @@ -9,327 +9,31 @@ + +Auto Archiver is a Python tool to automatically archive content on the web in a secure and verifiable way. It takes URLs from different sources (e.g. a CSV file, Google Sheets, command line etc.) and archives the content of each one. It can archive social media posts, videos, images and webpages. Content can enriched, then saved either locally or remotely (S3 bucket, Google Drive). The status of the archiving process can be appended to a CSV report, or if using Google Sheets – back to the original sheet. + +
+ +**[See the Auto Archiver documentation for more information.](https://auto-archiver.readthedocs.io/en/latest/)** + +
+ Read the [article about Auto Archiver on bellingcat.com](https://www.bellingcat.com/resources/2022/09/22/preserve-vital-online-content-with-bellingcats-auto-archiver-tool/). -Python tool to automatically archive social media posts, videos, and images from a Google Sheets, the console, and more. Uses different archivers depending on the platform, and can save content to local storage, S3 bucket (Digital Ocean Spaces, AWS, ...), and Google Drive. If using Google Sheets as the source for links, it will be updated with information about the archived content. It can be run manually or on an automated basis. +## Installation -There are 3 ways to use the auto-archiver: -1. (easiest installation) via docker -2. (local python install) `pip install auto-archiver` -3. (legacy/development) clone and manually install from repo (see legacy [tutorial video](https://youtu.be/VfAhcuV2tLQ)) +View the [Installation Guide](installation/installation.md) for full instructions -But **you always need a configuration/orchestration file**, which is where you'll configure where/what/how to archive. Make sure you read [orchestration](#orchestration). +To get started quickly using Docker: +`docker pull bellingcat/auto-archiver && docker run` -## How to install and run the auto-archiver +Or pip: -### Option 1 - docker +`pip install auto-archiver && auto-archiver --help` -[![dockeri.co](https://dockerico.blankenship.io/image/bellingcat/auto-archiver)](https://hub.docker.com/r/bellingcat/auto-archiver) +## Contributing -Docker works like a virtual machine running inside your computer, it isolates everything and makes installation simple. Since it is an isolated environment when you need to pass it your orchestration file or get downloaded media out of docker you will need to connect folders on your machine with folders inside docker with the `-v` volume flag. +We welcome contributions to the Auto Archiver project! See the [Contributing Guide](https://auto-archiver.readthedocs.io/en/latest/contributing.html) for how to get involved! - -1. install [docker](https://docs.docker.com/get-docker/) -2. pull the auto-archiver docker [image](https://hub.docker.com/r/bellingcat/auto-archiver) with `docker pull bellingcat/auto-archiver` -3. run the docker image locally in a container: `docker run --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive bellingcat/auto-archiver --config secrets/orchestration.yaml` breaking this command down: - 1. `docker run` tells docker to start a new container (an instance of the image) - 2. `--rm` makes sure this container is removed after execution (less garbage locally) - 3. `-v $PWD/secrets:/app/secrets` - your secrets folder - 1. `-v` is a volume flag which means a folder that you have on your computer will be connected to a folder inside the docker container - 2. `$PWD/secrets` points to a `secrets/` folder in your current working directory (where your console points to), we use this folder as a best practice to hold all the secrets/tokens/passwords/... you use - 3. `/app/secrets` points to the path the docker container where this image can be found - 4. `-v $PWD/local_archive:/app/local_archive` - (optional) if you use local_storage - 1. `-v` same as above, this is a volume instruction - 2. `$PWD/local_archive` is a folder `local_archive/` in case you want to archive locally and have the files accessible outside docker - 3. `/app/local_archive` is a folder inside docker that you can reference in your orchestration.yml file - -### Option 2 - python package - -
Python package instructions - -1. make sure you have python 3.10 or higher installed -2. install the package with your preferred package manager: `pip/pipenv/conda install auto-archiver` or `poetry add auto-archiver` -3. test it's installed with `auto-archiver --help` -4. run it with your orchestration file and pass any flags you want in the command line `auto-archiver --config secrets/orchestration.yaml` if your orchestration file is inside a `secrets/`, which we advise - -You will also need [ffmpeg](https://www.ffmpeg.org/), [firefox](https://www.mozilla.org/en-US/firefox/new/) and [geckodriver](https://github.com/mozilla/geckodriver/releases), and optionally [fonts-noto](https://fonts.google.com/noto). Similar to the local installation. - -
- - -### Option 3 - local installation -This can also be used for development. - -
Legacy instructions, only use if docker/package is not an option - - -Install the following locally: -1. [ffmpeg](https://www.ffmpeg.org/) must also be installed locally for this tool to work. -2. [firefox](https://www.mozilla.org/en-US/firefox/new/) and [geckodriver](https://github.com/mozilla/geckodriver/releases) on a path folder like `/usr/local/bin`. -3. [Poetry](https://python-poetry.org/docs/#installation) for dependency management and packaging. -4. (optional) [fonts-noto](https://fonts.google.com/noto) to deal with multiple unicode characters during selenium/geckodriver's screenshots: `sudo apt install fonts-noto -y`. - -Clone and run: -1. `git clone https://github.com/bellingcat/auto-archiver` -2. `poetry install` -3. `poetry run python -m src.auto_archiver --config secrets/orchestration.yaml` - -Note: Add the plugin [poetry-shell-plugin](https://github.com/python-poetry/poetry-plugin-shell) and run `poetry shell` to activate the virtual environment. -This allows you to run the auto-archiver without the `poetry run` prefix. - -

- -# Orchestration -The archiver work is orchestrated by the following workflow (we call each a **step**): -1. **Feeder** gets the links (from a spreadsheet, from the console, ...) -2. **Archiver** tries to archive the link (twitter, youtube, ...) -3. **Enricher** adds more info to the content (hashes, thumbnails, ...) -4. **Formatter** creates a report from all the archived content (HTML, PDF, ...) -5. **Database** knows what's been archived and also stores the archive result (spreadsheet, CSV, or just the console) - -To setup an auto-archiver instance create an `orchestration.yaml` which contains the workflow you would like. We advise you put this file into a `secrets/` folder and do not share it with others because it will contain passwords and other secrets. - -The structure of orchestration file is split into 2 parts: `steps` (what **steps** to use) and `configurations` (how those steps should behave), here's a simplification: -```yaml -# orchestration.yaml content -steps: - feeder: gsheet_feeder - archivers: # order matters - - youtubedl_archiver - enrichers: - - thumbnail_enricher - formatter: html_formatter - storages: - - local_storage - databases: - - gsheet_db - -configurations: - gsheet_feeder: - sheet: "your google sheet name" - header: 2 # row with header for your sheet - # ... configurations for the other steps here ... -``` - -To see all available `steps` (which archivers, storages, databases, ...) exist check the [example.orchestration.yaml](example.orchestration.yaml). - -All the `configurations` in the `orchestration.yaml` file (you can name it differently but need to pass it in the `--config FILENAME` argument) can be seen in the console by using the `--help` flag. They can also be overwritten, for example if you are using the `cli_feeder` to archive from the command line and want to provide the URLs you should do: - -```bash -auto-archiver --config secrets/orchestration.yaml --cli_feeder.urls="url1,url2,url3" -``` - -Here's the complete workflow that the auto-archiver goes through: -```{mermaid} -graph TD - s((start)) --> F(fa:fa-table Feeder) - F -->|get and clean URL| D1{fa:fa-database Database} - D1 -->|is already archived| e((end)) - D1 -->|not yet archived| a(fa:fa-download Archivers) - a -->|got media| E(fa:fa-chart-line Enrichers) - E --> S[fa:fa-box-archive Storages] - E --> Fo(fa:fa-code Formatter) - Fo --> S - Fo -->|update database| D2(fa:fa-database Database) - D2 --> e -``` - -## Orchestration checklist -Use this to make sure you help making sure you did all the required steps: -* [ ] you have a `/secrets` folder with all your configuration files including - * [ ] a orchestration file eg: `orchestration.yaml` pointing to the correct location of other files - * [ ] (optional if you use GoogleSheets) you have a `service_account.json` (see [how-to](https://gspread.readthedocs.io/en/latest/oauth2.html#for-bots-using-service-account)) - * [ ] (optional for telegram) a `anon.session` which appears after the 1st run where you login to telegram - * if you use private channels you need to add `channel_invites` and set `join_channels=true` at least once - * [ ] (optional for VK) a `vk_config.v2.json` - * [ ] (optional for using GoogleDrive storage) `gd-token.json` (see [help script](scripts/create_update_gdrive_oauth_token.py)) - * [ ] (optional for instagram) `instaloader.session` file which appears after the 1st run and login in instagram - * [ ] (optional for browsertrix) `profile.tar.gz` file - -#### Example invocations -The recommended way to run the auto-archiver is through Docker. The invocations below will run the auto-archiver Docker image using a configuration file that you have specified - -```bash -# all the configurations come from ./secrets/orchestration.yaml -docker run --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive bellingcat/auto-archiver --config secrets/orchestration.yaml -# uses the same configurations but for another google docs sheet -# with a header on row 2 and with some different column names -# notice that columns is a dictionary so you need to pass it as JSON and it will override only the values provided -docker run --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive bellingcat/auto-archiver --config secrets/orchestration.yaml --gsheet_feeder.sheet="use it on another sheets doc" --gsheet_feeder.header=2 --gsheet_feeder.columns='{"url": "link"}' -# all the configurations come from orchestration.yaml and specifies that s3 files should be private -docker run --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive bellingcat/auto-archiver --config secrets/orchestration.yaml --s3_storage.private=1 -``` - -The auto-archiver can also be run locally, if pre-requisites are correctly configured. Equivalent invocations are below. - -```bash -# all the configurations come from ./secrets/orchestration.yaml -auto-archiver --config secrets/orchestration.yaml -# uses the same configurations but for another google docs sheet -# with a header on row 2 and with some different column names -# notice that columns is a dictionary so you need to pass it as JSON and it will override only the values provided -auto-archiver --config secrets/orchestration.yaml --gsheet_feeder.sheet="use it on another sheets doc" --gsheet_feeder.header=2 --gsheet_feeder.columns='{"url": "link"}' -# all the configurations come from orchestration.yaml and specifies that s3 files should be private -auto-archiver --config secrets/orchestration.yaml --s3_storage.private=1 -``` - -### Extra notes on configuration -#### Google Drive -To use Google Drive storage you need the id of the shared folder in the `config.yaml` file which must be shared with the service account eg `autoarchiverservice@auto-archiver-111111.iam.gserviceaccount.com` and then you can use `--storage=gd` - -#### Telethon + Instagram with telegram bot -The first time you run, you will be prompted to do a authentication with the phone number associated, alternatively you can put your `anon.session` in the root. - -#### Atlos -When integrating with [Atlos](https://atlos.org), you will need to provide an API token in your configuration. You can learn more about Atlos and how to get an API token [here](https://docs.atlos.org/technical/api). You will have to provide this token to the `atlos_feeder`, `atlos_storage`, and `atlos_db` steps in your orchestration file. If you use a custom or self-hosted Atlos instance, you can also specify the `atlos_url` option to point to your custom instance's URL. For example: - -```yaml -# orchestration.yaml content -steps: - feeder: atlos_feeder - archivers: # order matters - - youtubedl_archiver - enrichers: - - thumbnail_enricher - - hash_enricher - formatter: html_formatter - storages: - - atlos_storage - databases: - - console_db - - atlos_db - -configurations: - atlos_feeder: - atlos_url: "https://platform.atlos.org" # optional - api_token: "...your API token..." - atlos_db: - atlos_url: "https://platform.atlos.org" # optional - api_token: "...your API token..." - atlos_storage: - atlos_url: "https://platform.atlos.org" # optional - api_token: "...your API token..." - hash_enricher: - algorithm: "SHA-256" -``` - -## Running on Google Sheets Feeder (gsheet_feeder) -The `--gsheet_feeder.sheet` property is the name of the Google Sheet to check for URLs. -This sheet must have been shared with the Google Service account used by `gspread`. -This sheet must also have specific columns (case-insensitive) in the `header` as specified in [gsheet_feeder.__manifest__.py](src/auto_archiver/modules/gsheet_feeder/__manifest__.py). The default names of these columns and their purpose is: - -Inputs: - -* **Link** *(required)*: the URL of the post to archive -* **Destination folder**: custom folder for archived file (regardless of storage) - -Outputs: -* **Archive status** *(required)*: Status of archive operation -* **Archive location**: URL of archived post -* **Archive date**: Date archived -* **Thumbnail**: Embeds a thumbnail for the post in the spreadsheet -* **Timestamp**: Timestamp of original post -* **Title**: Post title -* **Text**: Post text -* **Screenshot**: Link to screenshot of post -* **Hash**: Hash of archived HTML file (which contains hashes of post media) - for checksums/verification -* **Perceptual Hash**: Perceptual hashes of found images - these can be used for de-duplication of content -* **WACZ**: Link to a WACZ web archive of post -* **ReplayWebpage**: Link to a ReplayWebpage viewer of the WACZ archive - -For example, this is a spreadsheet configured with all of the columns for the auto archiver and a few URLs to archive. (Note that the column names are not case sensitive.) - -![A screenshot of a Google Spreadsheet with column headers defined as above, and several Youtube and Twitter URLs in the "Link" column](docs/demo-before.png) - -Now the auto archiver can be invoked, with this command in this example: `docker run --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive bellingcat/auto-archiver:dockerize --config secrets/orchestration-global.yaml --gsheet_feeder.sheet "Auto archive test 2023-2"`. Note that the sheet name has been overridden/specified in the command line invocation. - -When the auto archiver starts running, it updates the "Archive status" column. - -![A screenshot of a Google Spreadsheet with column headers defined as above, and several Youtube and Twitter URLs in the "Link" column. The auto archiver has added "archive in progress" to one of the status columns.](docs/demo-progress.png) - -The links are downloaded and archived, and the spreadsheet is updated to the following: - -![A screenshot of a Google Spreadsheet with videos archived and metadata added per the description of the columns above.](docs/demo-after.png) - -Note that the first row is skipped, as it is assumed to be a header row (`--gsheet_feeder.header=1` and you can change it if you use more rows above). Rows with an empty URL column, or a non-empty archive column are also skipped. All sheets in the document will be checked. - -The "archive location" link contains the path of the archived file, in local storage, S3, or in Google Drive. - -![The archive result for a link in the demo sheet.](docs/demo-archive.png) - ---- -## Development -Use `python -m src.auto_archiver --config secrets/orchestration.yaml` to run from the local development environment. - -### Testing - -Tests are split using `pytest.mark` into 'core' and 'download' tests. Download tests will hit the network and make API calls (e.g. Twitter, Bluesky etc.) and should be run regularly to make sure that APIs have not changed. - -Tests can be run as follows: -``` -# run core tests -pytest -ra -v -m "not download" # or poetry run pytest -ra -v -m "not download" -# run download tests -pytest -ra -v -m "download" # or poetry run pytest -ra -v -m "download" -# run all tests -pytest -ra -v # or poetry run pytest -ra -v -``` - -#### Docker development -working with docker locally: - * `docker compose up` to build the first time and run a local image with the settings in `secrets/orchestration.yaml` - * To modify/pass additional command line args, use `docker compose run auto-archiver --config secrets/orchestration.yaml [OTHER ARGUMENTS]` - * To rebuild after code changes, just pass the `--build` flag, e.g. `docker compose up --build` - - -manual release to docker hub - * `docker image tag auto-archiver bellingcat/auto-archiver:latest` - * `docker push bellingcat/auto-archiver` - - -### Building the Docs - -The documentation is built using [Sphinx](https://www.sphinx-doc.org/en/master/) and [AutoAPI](https://sphinx-autoapi.readthedocs.io/en/latest/) and hosted on ReadTheDocs. -To build the documentation locally, run the following commands: - -**Install required dependencies:** -- Install the docs group of dependencies: -```shell -# only the docs dependencies -poetry install --only docs - -# or for all dependencies -poetry install -``` -- Either use [poetry-plugin-shell](https://github.com/python-poetry/poetry-plugin-shell) to activate the virtual environment: `poetry shell` -- Or prepend the following commands with `poetry run` - -**Create the documentation:** -- Build the documentation: -``` -# Using makefile (Linux/macOS): -make -C docs html - -# or using sphinx directly (Windows/Linux/macOS): -sphinx-build -b html docs/source docs/_build/html -``` -- If you make significant changes and want a fresh build run: `make -C docs clean` to remove the old build files. - -**Viewing the documentation:** -```shell -# to open the documentation in your browser. -open docs/_build/html/index.html - -# or run autobuild to automatically update the documentation when you make changes -sphinx-autobuild docs/source docs/_build/html -``` - - - -#### RELEASE -* update version in [version.py](src/auto_archiver/version.py) -* go to github releases > new release > use `vx.y.z` for matching version notation - * package is automatically updated in pypi - * docker image is automatically pushed to dockerhup diff --git a/docs/_static/custom.css b/docs/_static/custom.css new file mode 100644 index 0000000..d77ab9d --- /dev/null +++ b/docs/_static/custom.css @@ -0,0 +1,4 @@ +.hidden_rtd { + display:none; +} + diff --git a/docs/_templates/autoapi/index.rst b/docs/_templates/autoapi/index.rst new file mode 100644 index 0000000..a6f712b --- /dev/null +++ b/docs/_templates/autoapi/index.rst @@ -0,0 +1,46 @@ +API Reference +============= + +These pages are intended for developers of the `auto-archiver` package, +and include documentation on the core classes and functions used by +the auto-archiver + + +Core Classes +------------ + + +.. toctree:: + :titlesonly: + + {% for page in pages|selectattr("is_top_level_object") %} + {% if page.name == 'core' %} + {{ page.include_path }} + {% endif %} + {% endfor %} + +Util Functions +-------------- + +.. toctree:: + :titlesonly: + + {% for page in pages|selectattr("is_top_level_object") %} + {% if page.name == 'utils' %} + {{ page.include_path }} + {% endif %} + {% endfor %} + + +Core Modules +------------ + +.. toctree:: + :titlesonly: + + {% for page in pages|selectattr("is_top_level_object") %} + {% if page.name != 'core' and page.name != 'utils' %} + {{ page.include_path }} + {% endif %} + {% endfor %} + diff --git a/docs/_templates/autoapi/python/attribute.rst b/docs/_templates/autoapi/python/attribute.rst new file mode 100644 index 0000000..ebaba55 --- /dev/null +++ b/docs/_templates/autoapi/python/attribute.rst @@ -0,0 +1 @@ +{% extends "python/data.rst" %} diff --git a/docs/_templates/autoapi/python/class.rst b/docs/_templates/autoapi/python/class.rst new file mode 100644 index 0000000..379f83a --- /dev/null +++ b/docs/_templates/autoapi/python/class.rst @@ -0,0 +1,104 @@ +{% if obj.display %} + {% if is_own_page %} +{{ obj.id }} +{{ "=" * obj.id | length }} + + {% endif %} + {% set visible_children = obj.children|selectattr("display")|list %} + {% set own_page_children = visible_children|selectattr("type", "in", own_page_types)|list %} + {% if is_own_page and own_page_children %} +.. toctree:: + :hidden: + + {% for child in own_page_children %} + {{ child.include_path }} + {% endfor %} + + {% endif %} +.. py:{{ obj.type }}:: {% if is_own_page %}{{ obj.id }}{% else %}{{ obj.short_name }}{% endif %}{% if obj.args %}({{ obj.args }}){% endif %} + + {% for (args, return_annotation) in obj.overloads %} + {{ " " * (obj.type | length) }} {{ obj.short_name }}{% if args %}({{ args }}){% endif %} + + {% endfor %} + {% if obj.bases %} + {% if "show-inheritance" in autoapi_options %} + + Bases: {% for base in obj.bases %}{{ base|link_objs }}{% if not loop.last %}, {% endif %}{% endfor %} + {% endif %} + + + {% if "show-inheritance-diagram" in autoapi_options and obj.bases != ["object"] %} + .. autoapi-inheritance-diagram:: {{ obj.obj["full_name"] }} + :parts: 1 + {% if "private-members" in autoapi_options %} + :private-bases: + {% endif %} + + {% endif %} + {% endif %} + {% if obj.docstring %} + + {{ obj.docstring|indent(3) }} + {% endif %} + {% for obj_item in visible_children %} + {% if obj_item.type not in own_page_types %} + + {{ obj_item.render()|indent(3) }} + {% endif %} + {% endfor %} + {% if is_own_page and own_page_children %} + {% set visible_attributes = own_page_children|selectattr("type", "equalto", "attribute")|list %} + {% if visible_attributes %} +Attributes +---------- + +.. autoapisummary:: + + {% for attribute in visible_attributes %} + {{ attribute.id }} + {% endfor %} + + + {% endif %} + {% set visible_exceptions = own_page_children|selectattr("type", "equalto", "exception")|list %} + {% if visible_exceptions %} +Exceptions +---------- + +.. autoapisummary:: + + {% for exception in visible_exceptions %} + {{ exception.id }} + {% endfor %} + + + {% endif %} + {% set visible_classes = own_page_children|selectattr("type", "equalto", "class")|list %} + {% if visible_classes %} +Classes +------- + +.. autoapisummary:: + + {% for klass in visible_classes %} + {{ klass.id }} + {% endfor %} + + + {% endif %} + {% set visible_methods = own_page_children|selectattr("type", "equalto", "method")|list %} + {% if visible_methods %} +Methods +------- + +.. autoapisummary:: + + {% for method in visible_methods %} + {{ method.id }} + {% endfor %} + + + {% endif %} + {% endif %} +{% endif %} diff --git a/docs/_templates/autoapi/python/data.rst b/docs/_templates/autoapi/python/data.rst new file mode 100644 index 0000000..1a50250 --- /dev/null +++ b/docs/_templates/autoapi/python/data.rst @@ -0,0 +1,38 @@ +{% if obj.display %} + {% if is_own_page %} +{{ obj.id }} +{{ "=" * obj.id | length }} + + {% endif %} +.. py:{{ obj.type }}:: {% if is_own_page %}{{ obj.id }}{% else %}{{ obj.name }}{% endif %} + {% if obj.annotation is not none %} + + :type: {% if obj.annotation %} {{ obj.annotation }}{% endif %} + {% endif %} + {% if obj.value is not none %} + + {% if obj.value.splitlines()|count > 1 %} + :value: Multiline-String + + .. raw:: html + +
Show Value + + .. code-block:: python + + {{ obj.value|indent(width=6,blank=true) }} + + .. raw:: html + +
+ + {% else %} + :value: {{ obj.value|truncate(100) }} + {% endif %} + {% endif %} + + {% if obj.docstring %} + + {{ obj.docstring|indent(3) }} + {% endif %} +{% endif %} diff --git a/docs/_templates/autoapi/python/exception.rst b/docs/_templates/autoapi/python/exception.rst new file mode 100644 index 0000000..92f3d38 --- /dev/null +++ b/docs/_templates/autoapi/python/exception.rst @@ -0,0 +1 @@ +{% extends "python/class.rst" %} diff --git a/docs/_templates/autoapi/python/function.rst b/docs/_templates/autoapi/python/function.rst new file mode 100644 index 0000000..5dee5aa --- /dev/null +++ b/docs/_templates/autoapi/python/function.rst @@ -0,0 +1,21 @@ +{% if obj.display %} + {% if is_own_page %} +{{ obj.id }} +{{ "=" * obj.id | length }} + + {% endif %} +.. py:function:: {% if is_own_page %}{{ obj.id }}{% else %}{{ obj.short_name }}{% endif %}({{ obj.args }}){% if obj.return_annotation is not none %} -> {{ obj.return_annotation }}{% endif %} + {% for (args, return_annotation) in obj.overloads %} + + {%+ if is_own_page %}{{ obj.id }}{% else %}{{ obj.short_name }}{% endif %}({{ args }}){% if return_annotation is not none %} -> {{ return_annotation }}{% endif %} + {% endfor %} + {% for property in obj.properties %} + + :{{ property }}: + {% endfor %} + + {% if obj.docstring %} + + {{ obj.docstring|indent(3) }} + {% endif %} +{% endif %} diff --git a/docs/_templates/autoapi/python/method.rst b/docs/_templates/autoapi/python/method.rst new file mode 100644 index 0000000..12d42de --- /dev/null +++ b/docs/_templates/autoapi/python/method.rst @@ -0,0 +1,21 @@ +{% if obj.display %} + {% if is_own_page %} +{{ obj.id }} +{{ "=" * obj.id | length }} + + {% endif %} +.. py:method:: {% if is_own_page %}{{ obj.id }}{% else %}{{ obj.short_name }}{% endif %}({{ obj.args }}){% if obj.return_annotation is not none %} -> {{ obj.return_annotation }}{% endif %} + {% for (args, return_annotation) in obj.overloads %} + + {%+ if is_own_page %}{{ obj.id }}{% else %}{{ obj.short_name }}{% endif %}({{ args }}){% if return_annotation is not none %} -> {{ return_annotation }}{% endif %} + {% endfor %} + {% for property in obj.properties %} + + :{{ property }}: + {% endfor %} + + {% if obj.docstring %} + + {{ obj.docstring|indent(3) }} + {% endif %} +{% endif %} diff --git a/docs/_templates/autoapi/python/module.rst b/docs/_templates/autoapi/python/module.rst new file mode 100644 index 0000000..53cc65d --- /dev/null +++ b/docs/_templates/autoapi/python/module.rst @@ -0,0 +1,156 @@ +{% if obj.display %} + {% if is_own_page %} +{{ obj.id }} +{{ "=" * obj.id|length }} + +.. py:module:: {{ obj.name }} + + {% if obj.docstring %} +.. autoapi-nested-parse:: + + {{ obj.docstring|indent(3) }} + + {% endif %} + + {% block submodules %} + {% set visible_subpackages = obj.subpackages|selectattr("display")|list %} + {% set visible_submodules = obj.submodules|selectattr("display")|list %} + {% set visible_submodules = (visible_subpackages + visible_submodules)|sort %} + {% if visible_submodules %} +Submodules +---------- + +.. toctree:: + :maxdepth: 1 + + {% for submodule in visible_submodules %} + {{ submodule.include_path }} + {% endfor %} + + + {% endif %} + {% endblock %} + {% block content %} + {% set visible_children = obj.children|selectattr("display")|list %} + {% if visible_children %} + {% set visible_attributes = visible_children|selectattr("type", "equalto", "data")|list %} + {% if visible_attributes %} + {% if "attribute" in own_page_types or "show-module-summary" in autoapi_options %} +Attributes +---------- + + {% if "attribute" in own_page_types %} +.. toctree:: + :hidden: + + {% for attribute in visible_attributes %} + {{ attribute.include_path }} + {% endfor %} + + {% endif %} +.. autoapisummary:: + + {% for attribute in visible_attributes %} + {{ attribute.id }} + {% endfor %} + {% endif %} + + + {% endif %} + {% set visible_exceptions = visible_children|selectattr("type", "equalto", "exception")|list %} + {% if visible_exceptions %} + {% if "exception" in own_page_types or "show-module-summary" in autoapi_options %} +Exceptions +---------- + + {% if "exception" in own_page_types %} +.. toctree:: + :hidden: + + {% for exception in visible_exceptions %} + {{ exception.include_path }} + {% endfor %} + + {% endif %} +.. autoapisummary:: + + {% for exception in visible_exceptions %} + {{ exception.id }} + {% endfor %} + {% endif %} + + + {% endif %} + {% set visible_classes = visible_children|selectattr("type", "equalto", "class")|list %} + {% if visible_classes %} + {% if "class" in own_page_types or "show-module-summary" in autoapi_options %} +Classes +------- + + {% if "class" in own_page_types %} +.. toctree:: + :hidden: + + {% for klass in visible_classes %} + {{ klass.include_path }} + {% endfor %} + + {% endif %} +.. autoapisummary:: + + {% for klass in visible_classes %} + {{ klass.id }} + {% endfor %} + {% endif %} + + + {% endif %} + {% set visible_functions = visible_children|selectattr("type", "equalto", "function")|list %} + {% if visible_functions %} + {% if "function" in own_page_types or "show-module-summary" in autoapi_options %} +Functions +--------- + + {% if "function" in own_page_types %} +.. toctree:: + :hidden: + + {% for function in visible_functions %} + {{ function.include_path }} + {% endfor %} + + {% endif %} +.. autoapisummary:: + + {% for function in visible_functions %} + {{ function.id }} + {% endfor %} + {% endif %} + + + {% endif %} + {% set this_page_children = visible_children|rejectattr("type", "in", own_page_types)|list %} + {% if this_page_children %} +{{ obj.type|title }} Contents +{{ "-" * obj.type|length }}--------- + + {% for obj_item in this_page_children %} +{{ obj_item.render()|indent(0) }} + {% endfor %} + {% endif %} + {% endif %} + {% endblock %} + {% else %} +.. py:module:: {{ obj.name }} + + {% if obj.docstring %} + .. autoapi-nested-parse:: + + {{ obj.docstring|indent(6) }} + + {% endif %} + {% for obj_item in visible_children %} + {{ obj_item.render()|indent(3) }} + {% endfor %} + {% endif %} +{% endif %} diff --git a/docs/_templates/autoapi/python/package.rst b/docs/_templates/autoapi/python/package.rst new file mode 100644 index 0000000..fb9a649 --- /dev/null +++ b/docs/_templates/autoapi/python/package.rst @@ -0,0 +1 @@ +{% extends "python/module.rst" %} diff --git a/docs/_templates/autoapi/python/property.rst b/docs/_templates/autoapi/python/property.rst new file mode 100644 index 0000000..9165311 --- /dev/null +++ b/docs/_templates/autoapi/python/property.rst @@ -0,0 +1,21 @@ +{% if obj.display %} + {% if is_own_page %} +{{ obj.id }} +{{ "=" * obj.id | length }} + + {% endif %} +.. py:property:: {% if is_own_page %}{{ obj.id}}{% else %}{{ obj.short_name }}{% endif %} + {% if obj.annotation %} + + :type: {{ obj.annotation }} + {% endif %} + {% for property in obj.properties %} + + :{{ property }}: + {% endfor %} + + {% if obj.docstring %} + + {{ obj.docstring|indent(3) }} + {% endif %} +{% endif %} diff --git a/docs/scripts/__init__.py b/docs/scripts/__init__.py new file mode 100644 index 0000000..ba9737c --- /dev/null +++ b/docs/scripts/__init__.py @@ -0,0 +1 @@ +from scripts import generate_module_docs \ No newline at end of file diff --git a/docs/scripts/scripts.py b/docs/scripts/scripts.py new file mode 100644 index 0000000..a5f2998 --- /dev/null +++ b/docs/scripts/scripts.py @@ -0,0 +1,128 @@ +# iterate through all the modules in auto_archiver.modules and turn the __manifest__.py file into a markdown table +from pathlib import Path +from auto_archiver.core.module import ModuleFactory +from auto_archiver.core.base_module import BaseModule +from ruamel.yaml import YAML +import io + +MODULES_FOLDER = Path(__file__).parent.parent.parent.parent / "src" / "auto_archiver" / "modules" +SAVE_FOLDER = Path(__file__).parent.parent / "source" / "modules" / "autogen" + +type_color = { + 'feeder': "[feeder](/core_modules.md#feeder-modules)", + 'extractor': "[extractor](/core_modules.md#extractor-modules)", + 'enricher': "[enricher](/core_modules.md#enricher-modules)", + 'database': "[database](/core_modules.md#database-modules)", + 'storage': "[storage](/core_modules.md#storage-modules)", + 'formatter': "[formatter](/core_modules.md#formatter-modules)", +} + +TABLE_HEADER = ("Option", "Description", "Default", "Type") + +EXAMPLE_YAML = """ +# steps configuration +steps: +... +{steps_str} +... + +# module configuration +... + +{config_string} +""" + +def generate_module_docs(): + yaml = YAML() + SAVE_FOLDER.mkdir(exist_ok=True) + modules_by_type = {} + + header_row = "| " + " | ".join(TABLE_HEADER) + "|\n" + "| --- " * len(TABLE_HEADER) + "|\n" + configs_cheatsheet = "\n## Configuration Options\n" + configs_cheatsheet += header_row + + for module in sorted(ModuleFactory().available_modules(), key=lambda x: (x.requires_setup, x.name)): + # generate the markdown file from the __manifest__.py file. + + manifest = module.manifest + for type in manifest['type']: + modules_by_type.setdefault(type, []).append(module) + + description = "\n".join(l.lstrip() for l in manifest['description'].split("\n")) + types = ", ".join(type_color[t] for t in manifest['type']) + readme_str = f""" +# {manifest['name']} +```{{admonition}} Module type + +{types} +``` +{description} +""" + steps_str = "\n".join(f" {t}s:\n - {module.name}" for t in manifest['type']) + + if not manifest['configs']: + config_string = f"# No configuration options for {module.name}.*\n" + else: + + config_table = header_row + config_yaml = {} + for key, value in manifest['configs'].items(): + type = value.get('type', 'string') + if type == 'auto_archiver.utils.json_loader': + value['type'] = 'json' + elif type == 'str': + type = "string" + + default = value.get('default', '') + config_yaml[key] = default + help = "**Required**. " if value.get('required', False) else "Optional. " + help += value.get('help', '') + config_table += f"| `{module.name}.{key}` | {help} | {value.get('default', '')} | {type} |\n" + configs_cheatsheet += f"| `{module.name}.{key}` | {help} | {default} | {type} |\n" + readme_str += "\n## Configuration Options\n" + readme_str += "\n### YAML\n" + + config_string = io.BytesIO() + yaml.dump({module.name: config_yaml}, config_string) + config_string = config_string.getvalue().decode('utf-8') + yaml_string = EXAMPLE_YAML.format(steps_str=steps_str, config_string=config_string) + readme_str += f"```{{code}} yaml\n{yaml_string}\n```\n" + + if manifest['configs']: + readme_str += "\n### Command Line:\n" + readme_str += config_table + + # add a link to the autodoc refs + readme_str += f"\n[API Reference](../../../autoapi/{module.name}/index)\n" + # create the module.type folder, use the first type just for where to store the file + for type in manifest['type']: + type_folder = SAVE_FOLDER / type + type_folder.mkdir(exist_ok=True) + with open(type_folder / f"{module.name}.md", "w") as f: + print("writing", SAVE_FOLDER) + f.write(readme_str) + generate_index(modules_by_type) + + with open(SAVE_FOLDER / "configs_cheatsheet.md", "w") as f: + f.write(configs_cheatsheet) + + +def generate_index(modules_by_type): + readme_str = "" + for type in BaseModule.MODULE_TYPES: + modules = modules_by_type.get(type, []) + module_str = f"## {type.capitalize()} Modules\n" + for module in modules: + module_str += f"\n[{module.manifest['name']}](/modules/autogen/{module.type[0]}/{module.name}.md)\n" + with open(SAVE_FOLDER / f"{type}.md", "w") as f: + print("writing", SAVE_FOLDER / f"{type}.md") + f.write(module_str) + readme_str += module_str + + with open(SAVE_FOLDER / "module_list.md", "w") as f: + print("writing", SAVE_FOLDER / "module_list.md") + f.write(readme_str) + + +if __name__ == "__main__": + generate_module_docs() \ No newline at end of file diff --git a/docs/source/_auto/configs.rst b/docs/source/_auto/configs.rst deleted file mode 100644 index f6e81f0..0000000 --- a/docs/source/_auto/configs.rst +++ /dev/null @@ -1,742 +0,0 @@ - -Configs -------- - -This section documents all configuration options available for various components. - -InstagramAPIArchiver --------------------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - access_token - - None - - a valid instagrapi-api token - * - api_endpoint - - None - - API endpoint to use - * - full_profile - - False - - if true, will download all posts, tagged posts, stories, and highlights for a profile, if false, will only download the profile pic and information. - * - full_profile_max_posts - - 0 - - Use to limit the number of posts to download when full_profile is true. 0 means no limit. limit is applied softly since posts are fetched in batch, once to: posts, tagged posts, and highlights - * - minimize_json_output - - True - - if true, will remove empty values from the json output - -InstagramArchiver ------------------ - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - username - - None - - a valid Instagram username - * - password - - None - - the corresponding Instagram account password - * - download_folder - - instaloader - - name of a folder to temporarily download content to - * - session_file - - secrets/instaloader.session - - path to the instagram session which saves session credentials - -InstagramTbotArchiver ---------------------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - api_id - - None - - telegram API_ID value, go to https://my.telegram.org/apps - * - api_hash - - None - - telegram API_HASH value, go to https://my.telegram.org/apps - * - session_file - - secrets/anon-insta - - optional, records the telegram login session for future usage, '.session' will be appended to the provided value. - * - timeout - - 45 - - timeout to fetch the instagram content in seconds. - -TelethonArchiver ----------------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - api_id - - None - - telegram API_ID value, go to https://my.telegram.org/apps - * - api_hash - - None - - telegram API_HASH value, go to https://my.telegram.org/apps - * - bot_token - - None - - optional, but allows access to more content such as large videos, talk to @botfather - * - session_file - - secrets/anon - - optional, records the telegram login session for future usage, '.session' will be appended to the provided value. - * - join_channels - - True - - disables the initial setup with channel_invites config, useful if you have a lot and get stuck - * - channel_invites - - {} - - (JSON string) private channel invite links (format: t.me/joinchat/HASH OR t.me/+HASH) and (optional but important to avoid hanging for minutes on startup) channel id (format: CHANNEL_ID taken from a post url like https://t.me/c/CHANNEL_ID/1), the telegram account will join any new channels on setup - -TwitterApiArchiver ------------------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - bearer_token - - None - - [deprecated: see bearer_tokens] twitter API bearer_token which is enough for archiving, if not provided you will need consumer_key, consumer_secret, access_token, access_secret - * - bearer_tokens - - [] - - a list of twitter API bearer_token which is enough for archiving, if not provided you will need consumer_key, consumer_secret, access_token, access_secret, if provided you can still add those for better rate limits. CSV of bearer tokens if provided via the command line - * - consumer_key - - None - - twitter API consumer_key - * - consumer_secret - - None - - twitter API consumer_secret - * - access_token - - None - - twitter API access_token - * - access_secret - - None - - twitter API access_secret - -VkArchiver ----------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - username - - None - - valid VKontakte username - * - password - - None - - valid VKontakte password - * - session_file - - secrets/vk_config.v2.json - - valid VKontakte password - -YoutubeDLArchiver ------------------ - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - facebook_cookie - - None - - optional facebook cookie to have more access to content, from browser, looks like 'cookie: datr= xxxx' - * - subtitles - - True - - download subtitles if available - * - comments - - False - - download all comments if available, may lead to large metadata - * - livestreams - - False - - if set, will download live streams, otherwise will skip them; see --max-filesize for more control - * - live_from_start - - False - - if set, will download live streams from their earliest available moment, otherwise starts now. - * - proxy - - - - http/socks (https seems to not work atm) proxy to use for the webdriver, eg https://proxy- user:password@proxy-ip:port - * - end_means_success - - True - - if True, any archived content will mean a 'success', if False this archiver will not return a 'success' stage; this is useful for cases when the yt-dlp will archive a video but ignore other types of content like images or text only pages that the subsequent archivers can retrieve. - * - allow_playlist - - False - - If True will also download playlists, set to False if the expectation is to download a single video. - * - max_downloads - - inf - - Use to limit the number of videos to download when a channel or long page is being extracted. 'inf' means no limit. - * - cookies_from_browser - - None - - optional browser for ytdl to extract cookies from, can be one of: brave, chrome, chromium, edge, firefox, opera, safari, vivaldi, whale - * - cookie_file - - None - - optional cookie file to use for Youtube, see instructions here on how to export from your browser: https://github.com/yt-dlp/yt- dlp/wiki/FAQ#how-do-i-pass-cookies-to-yt-dlp - -AAApiDb -------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - api_endpoint - - None - - API endpoint where calls are made to - * - api_token - - None - - API Bearer token. - * - public - - False - - whether the URL should be publicly available via the API - * - author_id - - None - - which email to assign as author - * - group_id - - None - - which group of users have access to the archive in case public=false as author - * - allow_rearchive - - True - - if False then the API database will be queried prior to any archiving operations and stop if the link has already been archived - * - store_results - - True - - when set, will send the results to the API database. - * - tags - - [] - - what tags to add to the archived URL - -AtlosDb -------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - api_token - - None - - An Atlos API token. For more information, see https://docs.atlos.org/technical/api/ - * - atlos_url - - https://platform.atlos.org - - The URL of your Atlos instance (e.g., https://platform.atlos.org), without a trailing slash. - -CSVDb ------ - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - csv_file - - db.csv - - CSV file name - -HashEnricher ------------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - algorithm - - SHA-256 - - hash algorithm to use - * - chunksize - - 16000000 - - number of bytes to use when reading files in chunks (if this value is too large you will run out of RAM), default is 16MB - -ScreenshotEnricher ------------------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - width - - 1280 - - width of the screenshots - * - height - - 720 - - height of the screenshots - * - timeout - - 60 - - timeout for taking the screenshot - * - sleep_before_screenshot - - 4 - - seconds to wait for the pages to load before taking screenshot - * - http_proxy - - - - http proxy to use for the webdriver, eg http://proxy-user:password@proxy-ip:port - * - save_to_pdf - - False - - save the page as pdf along with the screenshot. PDF saving options can be adjusted with the 'print_options' parameter - * - print_options - - {} - - options to pass to the pdf printer - -SSLEnricher ------------ - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - skip_when_nothing_archived - - True - - if true, will skip enriching when no media is archived - -ThumbnailEnricher ------------------ - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - thumbnails_per_minute - - 60 - - how many thumbnails to generate per minute of video, can be limited by max_thumbnails - * - max_thumbnails - - 16 - - limit the number of thumbnails to generate per video, 0 means no limit - -TimestampingEnricher --------------------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - tsa_urls - - ['http://timestamp.digicert.com', 'http://timestamp.identrust.com', 'http://timestamp.globalsign.com/tsa/r6advanced1', 'http://tss.accv.es:8318/tsa'] - - List of RFC3161 Time Stamp Authorities to use, separate with commas if passed via the command line. - -WaczArchiverEnricher --------------------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - profile - - None - - browsertrix-profile (for profile generation see https://github.com/webrecorder/browsertrix- crawler#creating-and-using-browser-profiles). - * - docker_commands - - None - - if a custom docker invocation is needed - * - timeout - - 120 - - timeout for WACZ generation in seconds - * - extract_media - - False - - If enabled all the images/videos/audio present in the WACZ archive will be extracted into separate Media and appear in the html report. The .wacz file will be kept untouched. - * - extract_screenshot - - True - - If enabled the screenshot captured by browsertrix will be extracted into separate Media and appear in the html report. The .wacz file will be kept untouched. - * - socks_proxy_host - - None - - SOCKS proxy host for browsertrix-crawler, use in combination with socks_proxy_port. eg: user:password@host - * - socks_proxy_port - - None - - SOCKS proxy port for browsertrix-crawler, use in combination with socks_proxy_host. eg 1234 - * - proxy_server - - None - - SOCKS server proxy URL, in development - -WaybackArchiverEnricher ------------------------ - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - timeout - - 15 - - seconds to wait for successful archive confirmation from wayback, if more than this passes the result contains the job_id so the status can later be checked manually. - * - if_not_archived_within - - None - - only tell wayback to archive if no archive is available before the number of seconds specified, use None to ignore this option. For more information: https://docs.google.com/document/d/1N sv52MvSjbLb2PCpHlat0gkzw0EvtSgpKHu4mk0MnrA - * - key - - None - - wayback API key. to get credentials visit https://archive.org/account/s3.php - * - secret - - None - - wayback API secret. to get credentials visit https://archive.org/account/s3.php - * - proxy_http - - None - - http proxy to use for wayback requests, eg http://proxy-user:password@proxy-ip:port - * - proxy_https - - None - - https proxy to use for wayback requests, eg https://proxy-user:password@proxy-ip:port - -WhisperEnricher ---------------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - api_endpoint - - None - - WhisperApi api endpoint, eg: https://whisperbox- api.com/api/v1, a deployment of https://github.com/bellingcat/whisperbox- transcribe. - * - api_key - - None - - WhisperApi api key for authentication - * - include_srt - - False - - Whether to include a subtitle SRT (SubRip Subtitle file) for the video (can be used in video players). - * - timeout - - 90 - - How many seconds to wait at most for a successful job completion. - * - action - - translate - - which Whisper operation to execute - -AtlosFeeder ------------ - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - api_token - - None - - An Atlos API token. For more information, see https://docs.atlos.org/technical/api/ - * - atlos_url - - https://platform.atlos.org - - The URL of your Atlos instance (e.g., https://platform.atlos.org), without a trailing slash. - -CLIFeeder ---------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - urls - - None - - URL(s) to archive, either a single URL or a list of urls, should not come from config.yaml - -GsheetsFeeder -------------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - sheet - - None - - name of the sheet to archive - * - sheet_id - - None - - (alternative to sheet name) the id of the sheet to archive - * - header - - 1 - - index of the header row (starts at 1) - * - service_account - - secrets/service_account.json - - service account JSON file path - * - columns - - {'url': 'link', 'status': 'archive status', 'folder': 'destination folder', 'archive': 'archive location', 'date': 'archive date', 'thumbnail': 'thumbnail', 'timestamp': 'upload timestamp', 'title': 'upload title', 'text': 'text content', 'screenshot': 'screenshot', 'hash': 'hash', 'pdq_hash': 'perceptual hashes', 'wacz': 'wacz', 'replaywebpage': 'replaywebpage'} - - names of columns in the google sheet (stringified JSON object) - * - allow_worksheets - - set() - - (CSV) only worksheets whose name is included in allow are included (overrides worksheet_block), leave empty so all are allowed - * - block_worksheets - - set() - - (CSV) explicitly block some worksheets from being processed - * - use_sheet_names_in_stored_paths - - True - - if True the stored files path will include 'workbook_name/worksheet_name/...' - -HtmlFormatter -------------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - detect_thumbnails - - True - - if true will group by thumbnails generated by thumbnail enricher by id 'thumbnail_00' - -AtlosStorage ------------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - path_generator - - url - - how to store the file in terms of directory structure: 'flat' sets to root; 'url' creates a directory based on the provided URL; 'random' creates a random directory. - * - filename_generator - - random - - how to name stored files: 'random' creates a random string; 'static' uses a replicable strategy such as a hash. - * - api_token - - None - - An Atlos API token. For more information, see https://docs.atlos.org/technical/api/ - * - atlos_url - - https://platform.atlos.org - - The URL of your Atlos instance (e.g., https://platform.atlos.org), without a trailing slash. - -GDriveStorage -------------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - path_generator - - url - - how to store the file in terms of directory structure: 'flat' sets to root; 'url' creates a directory based on the provided URL; 'random' creates a random directory. - * - filename_generator - - random - - how to name stored files: 'random' creates a random string; 'static' uses a replicable strategy such as a hash. - * - root_folder_id - - None - - root google drive folder ID to use as storage, found in URL: 'https://drive.google.com/drive/folders/FOLDER_ID' - * - oauth_token - - None - - JSON filename with Google Drive OAuth token: check auto-archiver repository scripts folder for create_update_gdrive_oauth_token.py. NOTE: storage used will count towards owner of GDrive folder, therefore it is best to use oauth_token_filename over service_account. - * - service_account - - secrets/service_account.json - - service account JSON file path, same as used for Google Sheets. NOTE: storage used will count towards the developer account. - -LocalStorage ------------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - path_generator - - url - - how to store the file in terms of directory structure: 'flat' sets to root; 'url' creates a directory based on the provided URL; 'random' creates a random directory. - * - filename_generator - - random - - how to name stored files: 'random' creates a random string; 'static' uses a replicable strategy such as a hash. - * - save_to - - ./archived - - folder where to save archived content - * - save_absolute - - False - - whether the path to the stored file is absolute or relative in the output result inc. formatters (WARN: leaks the file structure) - -S3Storage ---------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - path_generator - - url - - how to store the file in terms of directory structure: 'flat' sets to root; 'url' creates a directory based on the provided URL; 'random' creates a random directory. - * - filename_generator - - random - - how to name stored files: 'random' creates a random string; 'static' uses a replicable strategy such as a hash. - * - bucket - - None - - S3 bucket name - * - region - - None - - S3 region name - * - key - - None - - S3 API key - * - secret - - None - - S3 API secret - * - random_no_duplicate - - False - - if set, it will override `path_generator`, `filename_generator` and `folder`. It will check if the file already exists and if so it will not upload it again. Creates a new root folder path `no-dups/` - * - endpoint_url - - https://{region}.digitaloceanspaces.com - - S3 bucket endpoint, {region} are inserted at runtime - * - cdn_url - - https://{bucket}.{region}.cdn.digitaloceanspaces.com/{key} - - S3 CDN url, {bucket}, {region} and {key} are inserted at runtime - * - private - - False - - if true S3 files will not be readable online - -Storage -------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - path_generator - - url - - how to store the file in terms of directory structure: 'flat' sets to root; 'url' creates a directory based on the provided URL; 'random' creates a random directory. - * - filename_generator - - random - - how to name stored files: 'random' creates a random string; 'static' uses a replicable strategy such as a hash. - -Gsheets -------- - -The following table lists all configuration options for this component: - -.. list-table:: Configuration Options - :header-rows: 1 - :widths: 25 20 55 - - * - **Key** - - **Default** - - **Description** - * - sheet - - None - - name of the sheet to archive - * - sheet_id - - None - - (alternative to sheet name) the id of the sheet to archive - * - header - - 1 - - index of the header row (starts at 1) - * - service_account - - secrets/service_account.json - - service account JSON file path - * - columns - - {'url': 'link', 'status': 'archive status', 'folder': 'destination folder', 'archive': 'archive location', 'date': 'archive date', 'thumbnail': 'thumbnail', 'timestamp': 'upload timestamp', 'title': 'upload title', 'text': 'text content', 'screenshot': 'screenshot', 'hash': 'hash', 'pdq_hash': 'perceptual hashes', 'wacz': 'wacz', 'replaywebpage': 'replaywebpage'} - - names of columns in the google sheet (stringified JSON object) - diff --git a/docs/source/conf.py b/docs/source/conf.py index 3168b22..5b1ad9b 100644 --- a/docs/source/conf.py +++ b/docs/source/conf.py @@ -1,23 +1,33 @@ # Configuration file for the Sphinx documentation builder. # https://www.sphinx-doc.org/en/master/usage/configuration.html - -# -- Project information ----------------------------------------------------- +import sys +import os from importlib.metadata import metadata +sys.path.append(os.path.abspath('../scripts')) +from scripts import generate_module_docs + +# -- Project Hooks ----------------------------------------------------------- +# convert the module __manifest__.py files into markdown files +generate_module_docs() + + +# -- Project information ----------------------------------------------------- package_metadata = metadata("auto-archiver") project = package_metadata["name"] -authors = package_metadata["authors"] +authors = "Bellingcat" release = package_metadata["version"] - +language = 'en' # -- General configuration --------------------------------------------------- extensions = [ - "autoapi.extension", # Generate API documentation from docstrings "myst_parser", # Markdown support - 'sphinxcontrib.mermaid', # Mermaid diagrams + "autoapi.extension", # Generate API documentation from docstrings + "sphinxcontrib.mermaid", # Mermaid diagrams "sphinx.ext.viewcode", # Source code links + "sphinx_copybutton", "sphinx.ext.napoleon", # Google-style and NumPy-style docstrings - # "sphinx.ext.autodoc", # Include custom docstrings + "sphinx.ext.autosectionlabel", # 'sphinx.ext.autosummary', # Summarize module/class/function docs ] @@ -27,24 +37,25 @@ exclude_patterns = [] # -- AutoAPI Configuration --------------------------------------------------- autoapi_type = 'python' -autoapi_dirs = ["../../src"] +autoapi_dirs = ["../../src/auto_archiver/core/", "../../src/auto_archiver/utils/"] +# get all the modules and add them to the autoapi_dirs +autoapi_dirs.extend([f"../../src/auto_archiver/modules/{m}" for m in os.listdir("../../src/auto_archiver/modules")]) autodoc_typehints = "signature" # Include type hints in the signature -autoapi_ignore = [] # Ignore specific modules +autoapi_ignore = ["*/version.py", ] # Ignore specific modules autoapi_keep_files = True # Option to retain intermediate JSON files for debugging autoapi_add_toctree_entry = True # Include API docs in the TOC -autoapi_template_dir = None # Use default templates +autoapi_python_use_implicit_namespaces = True +autoapi_template_dir = "../_templates/autoapi" autoapi_options = [ "members", "undoc-members", "show-inheritance", - "show-module-summary", "imported-members", ] # -- Markdown Support -------------------------------------------------------- myst_enable_extensions = [ - "colon_fence", # ::: fences "deflist", # Definition lists "html_admonition", # HTML-style admonitions "html_image", # Inline HTML images @@ -53,12 +64,19 @@ myst_enable_extensions = [ "linkify", # Auto-detect links "substitution", # Text substitutions ] +myst_heading_anchors = 2 +myst_fence_as_directive = ["mermaid"] + source_suffix = { ".rst": "restructuredtext", ".md": "markdown", } # -- Options for HTML output ------------------------------------------------- -html_theme = 'furo' -# html_static_path = ['_static'] +html_theme = 'sphinx_book_theme' +html_static_path = ["../_static"] +html_css_files = ["custom.css"] +copybutton_prompt_text = r">>> |\.\.\." +copybutton_prompt_is_regexp = True +copybutton_only_copy_prompt_lines = False \ No newline at end of file diff --git a/docs/source/configurations.rst b/docs/source/configurations.rst deleted file mode 100644 index 85d7922..0000000 --- a/docs/source/configurations.rst +++ /dev/null @@ -1,34 +0,0 @@ - -Configurations -============== - -This section of the documentation provides guidelines for configuring the tool. - -File Reference --------------- - - -Below is the content of the `example.orchestration.yaml` file: - -.. raw:: html - -
- View example.orchestration.yaml - -.. literalinclude:: ../../example.orchestration.yaml - :language: yaml - :caption: example.orchestration.yaml - -.. raw:: html - -
- - -Configs -------- - -This section of the documentation will show the custom configurations for the individual steps of the tool. - -.. include:: _auto/configs.rst - - diff --git a/docs/source/contributing.md b/docs/source/contributing.md new file mode 100644 index 0000000..e75758c --- /dev/null +++ b/docs/source/contributing.md @@ -0,0 +1,2 @@ +```{include} ../../CONTRIBUTING.md +``` \ No newline at end of file diff --git a/docs/source/core_modules.md b/docs/source/core_modules.md new file mode 100644 index 0000000..3a8e5ec --- /dev/null +++ b/docs/source/core_modules.md @@ -0,0 +1,28 @@ +# Module Documentation + +These pages describe the core modules that come with `auto-archiver` and provide the main functionality for archiving websites on the internet. There are five core module types: + +1. Feeders - these 'feed' information (the URLs) from various sources to the `auto-archiver` for processing +2. Extractors - these 'extract' the page data for a given URL that is fed in by a feeder +3. Enrichers - these 'enrich' the data extracted in the previous step with additional information +4. Storage - these 'store' the data in a persistent location (on disk, Google Drive etc.) +5. Databases - these 'store' the status of the entire archiving process in a log file or database. + + +```{include} modules/autogen/module_list.md +``` + + +```{toctree} +:maxdepth: 1 +:caption: Core Modules +:hidden: + +modules/config_cheatsheet +modules/feeder +modules/extractor +modules/enricher +modules/storage +modules/database +modules/formatter +``` \ No newline at end of file diff --git a/docs/source/developer_guidelines.rst b/docs/source/developer_guidelines.rst deleted file mode 100644 index c0fdee0..0000000 --- a/docs/source/developer_guidelines.rst +++ /dev/null @@ -1,6 +0,0 @@ - -Developer Guidelines -==================== - -This section of the documentation provides guidelines for developers who want to modify or contribute to the tool. - diff --git a/docs/source/development/creating_modules.md b/docs/source/development/creating_modules.md new file mode 100644 index 0000000..0950251 --- /dev/null +++ b/docs/source/development/creating_modules.md @@ -0,0 +1,52 @@ +# Creating Your Own Modules + +Modules are what's used to extend `auto-archiver` to process different websites or media, and/or transform the data in a way that suits your needs. In most cases, the [Core Modules](../core_modules.md) should be sufficient for every day use, but the most common use-cases for making your own Modules include: + +1. Extracting data from a website which doesn't work with the current core extractors. +2. Enriching or altering the data before saving with additional information that the core enrichers do not offer. +3. Storing your data in a different format/location from what the core storage providers offer. + +## Setting up the folder structure + +1. First, decide what type of module you wish to create. Check the types of modules on the [](../core_modules.md) page to decide what type you need. (Note: a module can be more than one type, more on that below) +2. Create a new python package (a folder) with the name of your module (in this tutorial, we'll call it `awesome_extractor`). +3. Create the `__manifest__.py` and an the `awesome_extractor.py` files in this folder. + +When done, you should have a module structure as follows: + +``` +. +├── awesome_extractor +│ ├── __manifest__.py +│ └── awesome_extractor.py +``` + +Check out the [core modules](https://github.com/bellingcat/auto-archiver/tree/main/src/auto_archiver/modules) in the `auto-archiver` repository for examples of the folder structure for real-world modules. + +## Populating the Manifest File + +The manifest file is where you define the core information of your module. It is a python dict containing important information, here's an example file: + +```{include} ../../../tests/data/test_modules/example_module/__manifest__.py +:name: __manifest__.py +:literal: +:parser: python +``` + +## Creating the Python Code + +The next step is to create your module code. First, create a class which should subclass the base module types from `auto_archiver.core`, here's an example class for the `awesome_extractor` module which is an `extractor`: + +```{code-block} python +:filename: awesome_extractor.py + +from auto_archiver.core import Extractor, Metadata + +def AwesomeExtractor(Extractor): + + def download(self, item: Metadata) -> Metadata | False: + url = item.get_url() + # download the content and create the metadata object + metadata = ... + return metadata +``` diff --git a/docs/source/development/developer_guidelines.md b/docs/source/development/developer_guidelines.md new file mode 100644 index 0000000..e72193a --- /dev/null +++ b/docs/source/development/developer_guidelines.md @@ -0,0 +1,34 @@ + +# Developer Guidelines + +This section of the documentation provides guidelines for developers who want to modify or contribute to the tool. + + +## Developer Install + +1. Clone the project using `git clone https://github.com/bellingcat/auto-archiver.git` +2. Install poetry using `curl -sSL https://install.python-poetry.org | python3 -` ([other installation methods](https://python-poetry.org/docs/#installation)) +3. Install dependencies with `poetry install` + +## Running +4. Run the code with `poetry run auto-archiver [my args]` + +```{note} +Add the plugin [poetry-shell-plugin](https://github.com/python-poetry/poetry-plugin-shell) and run `poetry shell` to activate the virtual environment. +This allows you to run the auto-archiver without the `poetry run` prefix. +``` + +### Optional Development Packages + +Install development packages (used for unit tests etc.) using: +`poetry install -with dev` + + +```{toctree} +:hidden: +creating_modules +docker_development +testing +docs +release +``` \ No newline at end of file diff --git a/docs/source/development/docker_development.md b/docs/source/development/docker_development.md new file mode 100644 index 0000000..d770020 --- /dev/null +++ b/docs/source/development/docker_development.md @@ -0,0 +1,5 @@ +## Docker development +working with docker locally: + * `docker compose up` to build the first time and run a local image with the settings in `secrets/orchestration.yaml` + * To modify/pass additional command line args, use `docker compose run auto-archiver --config secrets/orchestration.yaml [OTHER ARGUMENTS]` + * To rebuild after code changes, just pass the `--build` flag, e.g. `docker compose up --build` \ No newline at end of file diff --git a/docs/source/development/docs.md b/docs/source/development/docs.md new file mode 100644 index 0000000..bb389ff --- /dev/null +++ b/docs/source/development/docs.md @@ -0,0 +1,38 @@ + +### Building the Docs + +The documentation is built using [Sphinx](https://www.sphinx-doc.org/en/master/) and [AutoAPI](https://sphinx-autoapi.readthedocs.io/en/latest/) and hosted on ReadTheDocs. +To build the documentation locally, run the following commands: + +**Install required dependencies:** +- Install the docs group of dependencies: +```shell +# only the docs dependencies +poetry install --only docs + +# or for all dependencies +poetry install +``` +- Either use [poetry-plugin-shell](https://github.com/python-poetry/poetry-plugin-shell) to activate the virtual environment: `poetry shell` +- Or prepend the following commands with `poetry run` + +**Create the documentation:** +- Build the documentation: +```shell +# Using makefile (Linux/macOS): +make -C docs html + +# or using sphinx directly (Windows/Linux/macOS): +sphinx-build -b html docs/source docs/_build/html +``` +- If you make significant changes and want a fresh build run: `make -C docs clean` to remove the old build files. + +**Viewing the documentation:** +```shell +# to open the documentation in your browser. +open docs/_build/html/index.html + +# or run autobuild to automatically update the documentation when you make changes +sphinx-autobuild docs/source docs/_build/html +``` + diff --git a/docs/source/development/release.md b/docs/source/development/release.md new file mode 100644 index 0000000..6939e97 --- /dev/null +++ b/docs/source/development/release.md @@ -0,0 +1,15 @@ +# Release Process + +```{note} This is a work in progress. +``` + +1. Update the version number in [version.py](src/auto_archiver/version.py) +2. Go to github releases > new release > use `vx.y.z` for matching version notation + 1. package is automatically updated in pypi + 2. docker image is automatically pushed to dockerhup + + + +manual release to docker hub + * `docker image tag auto-archiver bellingcat/auto-archiver:latest` + * `docker push bellingcat/auto-archiver` diff --git a/docs/source/development/testing.md b/docs/source/development/testing.md new file mode 100644 index 0000000..5de9574 --- /dev/null +++ b/docs/source/development/testing.md @@ -0,0 +1,21 @@ +# Testing + +`pytest` is used for testing. There are two main types of tests: + +1. 'core' tests which should be run on every change +2. 'download' tests which hit the network. These tests will do things like make API calls (e.g. Twitter, Bluesky etc.) and should be run regularly to make sure that APIs have not changed. + + +## Running Tests + +1. Make sure you've installed the dev dependencies with `pytest install --with dev` +2. Tests can be run as follows: +``` +#### Command prefix of 'poetry run' removed here for simplicity +# run core tests +pytest -ra -v -m "not download" +# run download tests +pytest -ra -v -m "download" +# run all tests +pytest -ra -v +``` \ No newline at end of file diff --git a/docs/source/example.orchestration.yaml b/docs/source/example.orchestration.yaml new file mode 100644 index 0000000..48d354d --- /dev/null +++ b/docs/source/example.orchestration.yaml @@ -0,0 +1,79 @@ +# Auto Archiver Configuration +# Steps are the modules that will be run in the order they are defined + +steps: + feeders: + - cli_feeder + extractors: + - generic_extractor + - telegram_extractor + enrichers: + - thumbnail_enricher + - meta_enricher + - pdq_hash_enricher + - ssl_enricher + - hash_enricher + databases: + - console_db + - csv_db + storages: + - local_storage + formatters: + - html_formatter + +# Global configuration + +# Authentication +# a dictionary of authentication information that can be used by extractors to login to website. +# you can use a comma separated list for multiple domains on the same line (common usecase: x.com,twitter.com) +# Common login 'types' are username/password, cookie, api key/token. +# There are two special keys for using cookies, they are: cookies_file and cookies_from_browser. +# Some Examples: +# facebook.com: +# username: "my_username" +# password: "my_password" +# or for a site that uses an API key: +# twitter.com,x.com: +# api_key +# api_secret +# youtube.com: +# cookie: "login_cookie=value ; other_cookie=123" # multiple 'key=value' pairs should be separated by ; + +authentication: {} + +# Logging settings for your project. See the logging settings with --help + +logging: + level: INFO + +# These are the global configurations that are used by the modules + + file: + rotation: +local_storage: + path_generator: flat + filename_generator: static + save_to: ./local_archive + save_absolute: false +html_formatter: + detect_thumbnails: true +thumbnail_enricher: + thumbnails_per_minute: 60 + max_thumbnails: 16 +generic_extractor: + subtitles: true + comments: false + livestreams: false + live_from_start: false + proxy: '' + end_means_success: true + allow_playlist: false + max_downloads: inf +csv_db: + csv_file: db.csv +ssl_enricher: + skip_when_nothing_archived: true +hash_enricher: + algorithm: SHA-256 + chunksize: 16000000 + diff --git a/docs/source/flow_overview.md b/docs/source/flow_overview.md new file mode 100644 index 0000000..5ffa3a8 --- /dev/null +++ b/docs/source/flow_overview.md @@ -0,0 +1,30 @@ + +# Archiving Overview + +The archiver archives web pages using the following workflow +1. **Feeder** gets the links (from a spreadsheet, from the console, ...) +2. **Extractor** tries to extract content from the given link (e.g. videos from youtube, images from Twitter...) +3. **Enricher** adds more info to the content (hashes, thumbnails, ...) +4. **Formatter** creates a report from all the archived content (HTML, PDF, ...) +5. **Database** knows what's been archived and also stores the archive result (spreadsheet, CSV, or just the console) + +Each step in the workflow is handled by 'modules' that interact with the data in different ways. For example, the Twitter Extractor Module would extract information from the Twitter website. The Screenshot Enricher Module will take screenshots of the given page. See the [core modules page](core_modules.md) for an overview of all the modules that are available. + +Auto-archiver must have at least one module defined for each step of the workflow. This is done by setting the [configuration](installation/configurations.md) for your auto-archiver instance. + +Here's the complete workflow that the auto-archiver goes through: + +```mermaid + +graph TD + s((start)) --> F(fa:fa-table Feeder) + F -->|get and clean URL| D1{fa:fa-database Database} + D1 -->|is already archived| e((end)) + D1 -->|not yet archived| a(fa:fa-download Archivers) + a -->|got media| E(fa:fa-chart-line Enrichers) + E --> S[fa:fa-box-archive Storages] + E --> Fo(fa:fa-code Formatter) + Fo --> S + Fo -->|update database| D2(fa:fa-database Database) + D2 --> e +``` \ No newline at end of file diff --git a/docs/source/how_to.md b/docs/source/how_to.md new file mode 100644 index 0000000..25e1e1d --- /dev/null +++ b/docs/source/how_to.md @@ -0,0 +1,54 @@ +# How-To Guides + +## How to use Google Sheets to load and store archive information +The `--gsheet_feeder.sheet` property is the name of the Google Sheet to check for URLs. +This sheet must have been shared with the Google Service account used by `gspread`. +This sheet must also have specific columns (case-insensitive) in the `header` - see the [Gsheet Feeder Docs](modules/autogen/feeder/gsheet_feeder.md) for more info. The default names of these columns and their purpose is: + +Inputs: + +* **Link** *(required)*: the URL of the post to archive +* **Destination folder**: custom folder for archived file (regardless of storage) + +Outputs: +* **Archive status** *(required)*: Status of archive operation +* **Archive location**: URL of archived post +* **Archive date**: Date archived +* **Thumbnail**: Embeds a thumbnail for the post in the spreadsheet +* **Timestamp**: Timestamp of original post +* **Title**: Post title +* **Text**: Post text +* **Screenshot**: Link to screenshot of post +* **Hash**: Hash of archived HTML file (which contains hashes of post media) - for checksums/verification +* **Perceptual Hash**: Perceptual hashes of found images - these can be used for de-duplication of content +* **WACZ**: Link to a WACZ web archive of post +* **ReplayWebpage**: Link to a ReplayWebpage viewer of the WACZ archive + +For example, this is a spreadsheet configured with all of the columns for the auto archiver and a few URLs to archive. (Note that the column names are not case sensitive.) + +![A screenshot of a Google Spreadsheet with column headers defined as above, and several Youtube and Twitter URLs in the "Link" column](../demo-before.png) + +Now the auto archiver can be invoked, with this command in this example: `docker run --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive bellingcat/auto-archiver:dockerize --config secrets/orchestration-global.yaml --gsheet_feeder.sheet "Auto archive test 2023-2"`. Note that the sheet name has been overridden/specified in the command line invocation. + +When the auto archiver starts running, it updates the "Archive status" column. + +![A screenshot of a Google Spreadsheet with column headers defined as above, and several Youtube and Twitter URLs in the "Link" column. The auto archiver has added "archive in progress" to one of the status columns.](../demo-progress.png) + +The links are downloaded and archived, and the spreadsheet is updated to the following: + +![A screenshot of a Google Spreadsheet with videos archived and metadata added per the description of the columns above.](../demo-after.png) + +Note that the first row is skipped, as it is assumed to be a header row (`--gsheet_feeder.header=1` and you can change it if you use more rows above). Rows with an empty URL column, or a non-empty archive column are also skipped. All sheets in the document will be checked. + +The "archive location" link contains the path of the archived file, in local storage, S3, or in Google Drive. + +![The archive result for a link in the demo sheet.](../demo-archive.png) + +--- + +```{toctree} +:maxdepth: 1 +:glob: + +how_to/* +``` \ No newline at end of file diff --git a/docs/source/how_to/authentication.md b/docs/source/how_to/authentication.md new file mode 100644 index 0000000..5f3bc48 --- /dev/null +++ b/docs/source/how_to/authentication.md @@ -0,0 +1,57 @@ +# Authentication + +The Authentication framework for auto-archiver allows you to add login details for various websites in a flexible way, directly from the configuration file. + +There are two main use cases for authentication: +* Some websites require some kind of authentication in order to view the content. Examples include Facebook, Telegram etc. +* Some websites use anti-bot systems to block bot-like tools from accessig the website. Adding real login information to auto-archiver can sometimes bypass this. + +## The Authentication Config + +You can save your authentication information directly inside your orchestration config file, or as a separate file (for security/multi-deploy purposes). Whether storing your settings inside the orchestration file, or as a separate file, the configuration format is the same. + +```{code} yaml +authentication: + # optional file to load authentication information from, for security or multi-system deploy purposes + load_from_file: path/to/authentication/file.txt + # optional setting to load cookies from the named browser on the system. + cookies_from_browser: firefox + # optional setting to load cookies from a cookies.txt/cookies.jar file. See note below on extracting these + cookies_file: path/to/cookies.jar + + twitter.com,x.com: + username: myusername + password: 123 + + facebook.com: + cookie: single_cookie + + othersite.com: + api_key: 123 + api_secret: 1234 + +# All available options: + # - username: str - the username to use for login + # - password: str - the password to use for login + # - api_key: str - the API key to use for login + # - api_secret: str - the API secret to use for login + # - cookie: str - a cookie string to use for login (specific to this site) +``` + +### Recommendations for authentication + +1. **Store authentication information separately:** +The authentication part of your configuration contains sensitive information. You should make efforts not to share this with others. For extra security, use the `load_from_file` option to keep your authentication settings out of your configuration file, ideally in a different folder. + +2. **Don't use your own personal credentials** +Depending on the website you are extracting information from, there may be rules (Terms of Service) that prohibit you from scraping or extracting information using a bot. If you use your own personal account, there's a possibility it might get blocked/disabled. It's recommended to set up a separate, 'throwaway' account. In that way, if it gets blocked you can easily create another one to continue your archiving. + + +### How to create a cookies.jar or pass cookies directly to auto-archiver + +auto-archiver uses yt-dlp's powerful cookies features under the hood. For instructions on how to extract a cookies.jar (or cookies.txt) file directly from your browser, see the FAQ in the [yt-dlp documentation](https://github.com/yt-dlp/yt-dlp/wiki/FAQ#how-do-i-pass-cookies-to-yt-dlp) + +```{note} For developers: + +For information on how to access and use authentication settings from within your module, see the `{generic_extractor}` for an example, or view the [`auth_for_site()` function in BaseModule](../autoapi/core/base_module/index.rst) +``` \ No newline at end of file diff --git a/docs/source/index.md b/docs/source/index.md new file mode 100644 index 0000000..6a7f769 --- /dev/null +++ b/docs/source/index.md @@ -0,0 +1,17 @@ + +```{include} ../../README.md +``` + +```{toctree} +:maxdepth: 2 +:hidden: +:caption: Contents: + +Overview +contributing +installation/installation.rst +core_modules.md +how_to +development/developer_guidelines +autoapi/index.rst +``` \ No newline at end of file diff --git a/docs/source/index.rst b/docs/source/index.rst deleted file mode 100644 index 52449b8..0000000 --- a/docs/source/index.rst +++ /dev/null @@ -1,26 +0,0 @@ -.. auto-archiver documentation master file, created by - sphinx-quickstart on Sun Jan 12 20:35:50 2025. - You can adapt this file completely to your liking, but it should at least - contain the root `toctree` directive. - -Auto Archiver documentation -=========================== - -.. note:: - - This is a work in progress. - - -.. include:: ../../README.md - :parser: myst - - -.. toctree:: - :maxdepth: 1 - :hidden: - :caption: Contents: - - user_guidelines - developer_guidelines - configurations - diff --git a/docs/source/installation/config_cheatsheet.md b/docs/source/installation/config_cheatsheet.md new file mode 100644 index 0000000..820e30c --- /dev/null +++ b/docs/source/installation/config_cheatsheet.md @@ -0,0 +1,6 @@ +# Configuration Cheat Sheet + +Below is a list of all configurations for the core modules in Auto Archiver + +```{include} ../modules/autogen/configs_cheatsheet.md +``` diff --git a/docs/source/installation/configurations.md b/docs/source/installation/configurations.md new file mode 100644 index 0000000..705b6c5 --- /dev/null +++ b/docs/source/installation/configurations.md @@ -0,0 +1,98 @@ + +# Configuration + +This section of the documentation provides guidelines for configuring the tool. + +## Configuring using a file + +The recommended way to configure auto-archiver for long-term and deployed projects is a configuration file, typically called `orchestration.yaml`. This is a YAML file containing all the settings for your entire workflow. + +The structure of orchestration file is split into 2 parts: `steps` (what [steps](../flow_overview.md) to use) and `configurations` (settings for different modules), here's a simplification: + +A default `orchestration.yaml` will be created for you the first time you run auto-archiver (without any arguments). Here's what it looks like: + +
+View exampleorchestration.yaml + +```{literalinclude} ../example.orchestration.yaml + :language: yaml + :caption: orchestration.yaml +``` + +
+ +## Configuring from the Command Line + +You can run auto-archiver directy from the command line, without the need for a configuration file, command line arguments are parsed using the format `module_name.config_value`. For example, a config value of `api_key` in the `instagram_extractor` module would be passed on the command line with the flag `--instagram_extractor.api_key=API_KEY`. + +The command line arguments are useful for testing or editing config values and enabling/disabling modules on the fly. When you are happy with your settings, you can store them back in your configuration file by passing the `-s/--store` flag on the command line. + +```bash +auto-archiver --instagram_extractor.api_key=123 --other_module.setting --store +# will store the new settings into the configuration file (default: orchestration.yaml) +``` + +```{note} Arguments passed on the command line override those saved in your settings file. Save them to your config file using the -s or --store flag +``` + +## Seeing all Configuration Options + +View the configurable settings for the core modules on the individual doc pages for each [](../core_modules.md). +You can also view all settings available for the modules you have on your system using the `--help` flag in auto-archiver. + +```{code-block} console +:caption: Example output when using the --help flag with auto-archiver +$ auto-archiver --help +... +Positional Arguments: + urls URL(s) to archive, either a single URL or a list of urls, should not come from config.yaml + +Options: + --help, -h show a full help message and exit + --version show program's version number and exit + --config CONFIG_FILE the filename of the YAML configuration file (defaults to 'config.yaml') + --mode {simple,full} the mode to run the archiver in + -s, --store, --no-store + Store the created config in the config file + --module_paths MODULE_PATHS [MODULE_PATHS ...] + additional paths to search for modules + --feeders STEPS.FEEDERS [STEPS.FEEDERS ...] + the feeders to use + --enrichers STEPS.ENRICHERS [STEPS.ENRICHERS ...] + the enrichers to use + --extractors STEPS.EXTRACTORS [STEPS.EXTRACTORS ...] + the extractors to use + --databases STEPS.DATABASES [STEPS.DATABASES ...] + the databases to use + --storages STEPS.STORAGES [STEPS.STORAGES ...] + the storages to use + --formatters STEPS.FORMATTERS [STEPS.FORMATTERS ...] + the formatter to use + --authentication AUTHENTICATION + A dictionary of sites and their authentication methods (token, username etc.) that extractors can use to log into a website. If passing this on the command line, use a JSON string. You may + also pass a path to a valid JSON/YAML file which will be parsed. + --logging.level {INFO,DEBUG,ERROR,WARNING} + the logging level to use + --logging.file LOGGING.FILE + the logging file to write to + --logging.rotation LOGGING.ROTATION + the logging rotation to use + +Wayback Machine Enricher: + Submits the current URL to the Wayback Machine for archiving and returns either a job ID or the... + + --wayback_extractor_enricher.timeout TIMEOUT + seconds to wait for successful archive confirmation from wayback, if more than this passes the result contains the job_id so the status can later be checked manually. + --wayback_extractor_enricher.if_not_archived_within IF_NOT_ARCHIVED_WITHIN + only tell wayback to archive if no archive is available before the number of seconds specified, use None to ignore this option. For more information: + https://docs.google.com/document/d/1Nsv52MvSjbLb2PCpHlat0gkzw0EvtSgpKHu4mk0MnrA + --wayback_extractor_enricher.key KEY + wayback API key. to get credentials visit https://archive.org/account/s3.php + --wayback_extractor_enricher.secret SECRET + wayback API secret. to get credentials visit https://archive.org/account/s3.php + --wayback_extractor_enricher.proxy_http PROXY_HTTP + http proxy to use for wayback requests, eg http://proxy-user:password@proxy-ip:port + --wayback_extractor_enricher.proxy_https PROXY_HTTPS + https proxy to use for wayback requests, eg https://proxy-user:password@proxy-ip:port +``` + diff --git a/docs/source/installation/installation.md b/docs/source/installation/installation.md new file mode 100644 index 0000000..fdd3184 --- /dev/null +++ b/docs/source/installation/installation.md @@ -0,0 +1,92 @@ +# Installing Auto Archiver + +```{toctree} +:depth: 1 +:hidden: + +configurations.md +config_cheatsheet.md +``` + +There are 3 main ways to use the auto-archiver: +1. Easiest: [via docker](#installing-with-docker) +2. Local Install: [using pip](#installing-locally-with-pip) +3. Developer Install: [see the developer guidelines](../development/developer_guidelines) + + +But **you always need a configuration/orchestration file**, which is where you'll configure where/what/how to archive. Make sure you read [orchestration](#orchestration). + + +## Installing with Docker + +[![dockeri.co](https://dockerico.blankenship.io/image/bellingcat/auto-archiver)](https://hub.docker.com/r/bellingcat/auto-archiver) + +Docker works like a virtual machine running inside your computer, it isolates everything and makes installation simple. Since it is an isolated environment when you need to pass it your orchestration file or get downloaded media out of docker you will need to connect folders on your machine with folders inside docker with the `-v` volume flag. + + +1. Install [docker](https://docs.docker.com/get-docker/) +2. Pull the auto-archiver docker [image](https://hub.docker.com/r/bellingcat/auto-archiver) with `docker pull bellingcat/auto-archiver` +3. Run the docker image locally in a container: `docker run --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive bellingcat/auto-archiver --config secrets/orchestration.yaml` breaking this command down: + 1. `docker run` tells docker to start a new container (an instance of the image) + 2. `--rm` makes sure this container is removed after execution (less garbage locally) + 3. `-v $PWD/secrets:/app/secrets` - your secrets folder + 1. `-v` is a volume flag which means a folder that you have on your computer will be connected to a folder inside the docker container + 2. `$PWD/secrets` points to a `secrets/` folder in your current working directory (where your console points to), we use this folder as a best practice to hold all the secrets/tokens/passwords/... you use + 3. `/app/secrets` points to the path the docker container where this image can be found + 4. `-v $PWD/local_archive:/app/local_archive` - (optional) if you use local_storage + 1. `-v` same as above, this is a volume instruction + 2. `$PWD/local_archive` is a folder `local_archive/` in case you want to archive locally and have the files accessible outside docker + 3. `/app/local_archive` is a folder inside docker that you can reference in your orchestration.yml file + +### Example invocations + +The invocations below will run the auto-archiver Docker image using a configuration file that you have specified + +```bash +# all the configurations come from ./secrets/orchestration.yaml +docker run --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive bellingcat/auto-archiver --config secrets/orchestration.yaml +# uses the same configurations but for another google docs sheet +# with a header on row 2 and with some different column names +# notice that columns is a dictionary so you need to pass it as JSON and it will override only the values provided +docker run --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive bellingcat/auto-archiver --config secrets/orchestration.yaml --gsheet_feeder.sheet="use it on another sheets doc" --gsheet_feeder.header=2 --gsheet_feeder.columns='{"url": "link"}' +# all the configurations come from orchestration.yaml and specifies that s3 files should be private +docker run --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive bellingcat/auto-archiver --config secrets/orchestration.yaml --s3_storage.private=1 +``` + +## Installing Locally with Pip + +1. Make sure you have python 3.10 or higher installed +2. Install the package with your preferred package manager: `pip/pipenv/conda install auto-archiver` or `poetry add auto-archiver` +3. Test it's installed with `auto-archiver --help` +4. Install other local dependency requirements (for ) +5. Run it with your orchestration file and pass any flags you want in the command line `auto-archiver --config secrets/orchestration.yaml` if your orchestration file is inside a `secrets/`, which we advise + +### Example invocations + +Once all your [local requirements](#installing-local-requirements) are correctly installed, the + +```bash +# all the configurations come from ./secrets/orchestration.yaml +auto-archiver --config secrets/orchestration.yaml +# uses the same configurations but for another google docs sheet +# with a header on row 2 and with some different column names +# notice that columns is a dictionary so you need to pass it as JSON and it will override only the values provided +auto-archiver --config secrets/orchestration.yaml --gsheet_feeder.sheet="use it on another sheets doc" --gsheet_feeder.header=2 --gsheet_feeder.columns='{"url": "link"}' +# all the configurations come from orchestration.yaml and specifies that s3 files should be private +auto-archiver --config secrets/orchestration.yaml --s3_storage.private=1 +``` + +### Installing Local Requirements + +If using the local installation method, you will also need to install the following dependencies locally: + +1.[ffmpeg](https://www.ffmpeg.org/) - for handling of downloaded videos +2. [firefox](https://www.mozilla.org/en-US/firefox/new/) and [geckodriver](https://github.com/mozilla/geckodriver/releases) on a path folder like `/usr/local/bin` - for taking webpage screenshots with the screenshot enricher +3. (optional) [fonts-noto](https://fonts.google.com/noto) to deal with multiple unicode characters during selenium/geckodriver's screenshots: `sudo apt install fonts-noto -y`. +4. [Browsertrix Crawler docker image](https://hub.docker.com/r/webrecorder/browsertrix-crawler) for the WACZ enricher/archiver + + + +## Developer Install + +[See the developer guidelines](../development/developer_guidelines) \ No newline at end of file diff --git a/docs/source/modules/database.md b/docs/source/modules/database.md new file mode 100644 index 0000000..9acecda --- /dev/null +++ b/docs/source/modules/database.md @@ -0,0 +1,15 @@ +# Database Modules + +Database modules are used to store the status and results of the extraction and enrichment processes somewhere. The database modules are responsible for creating and managing entires for each item that has been processed. + +The default (enabled) databases are the CSV Database and the Console Database. + +```{include} autogen/database.md +``` + +```{toctree} +:depth: 1 +:hidden: +:glob: +autogen/database/* +``` \ No newline at end of file diff --git a/docs/source/modules/enricher.md b/docs/source/modules/enricher.md new file mode 100644 index 0000000..30568c3 --- /dev/null +++ b/docs/source/modules/enricher.md @@ -0,0 +1,14 @@ +# Enricher Modules + +Enricher modules are used to add additional information to the items that have been extracted. Common enrichment tasks include adding metadata to items, such as the hash of the item, a screenshot of the webpage when the item was extracted, or general metadata like the date and time the item was extracted. + + +```{include} autogen/enricher.md +``` + +```{toctree} +:depth: 1 +:hidden: +:glob: +autogen/enricher/* +``` \ No newline at end of file diff --git a/docs/source/modules/extractor.md b/docs/source/modules/extractor.md new file mode 100644 index 0000000..7f218fb --- /dev/null +++ b/docs/source/modules/extractor.md @@ -0,0 +1,18 @@ +# Extractor Modules + +Extractor modules are used to extract the content of a given URL. Typically, one extractor will work for one website or platform (e.g. a Telegram extractor or an Instagram), however, there are several wide-ranging extractors which work for a wide range of websites. + +Extractors that are able to extract content from a wide range of websites include: +1. Generic Extractor: parses videos and images on sites using the powerful yt-dlp library. +2. Wayback Machine Extractor: sends pages to the Waygback machine for archiving, and stores the link. +3. WACZ Extractor: runs a web browser to 'browse' the URL and save a copy of the page in WACZ format. + +```{include} autogen/extractor.md +``` + +```{toctree} +:depth: 1 +:hidden: +:glob: +autogen/extractor/* +``` \ No newline at end of file diff --git a/docs/source/modules/feeder.md b/docs/source/modules/feeder.md new file mode 100644 index 0000000..ce5f7ca --- /dev/null +++ b/docs/source/modules/feeder.md @@ -0,0 +1,20 @@ +# Feeder Modules + +Feeder modules are used to feed URLs into the `auto-archiver` for processing. Feeders can take these URLs from a variety of sources, such as a file, a database, or the command line. + +The default feeder is the command line feeder (`cli_feeder`), which allows you to input URLs directly into the `auto-archiver` from the command line. + +Command line feeder usage: +```{code} bash +auto-archiver [options] -- URL1 URL2 ... +``` + +```{include} autogen/feeder.md +``` + +```{toctree} +:depth: 1 +:glob: +:hidden: +autogen/feeder/* +``` \ No newline at end of file diff --git a/docs/source/modules/formatter.md b/docs/source/modules/formatter.md new file mode 100644 index 0000000..b7ae77e --- /dev/null +++ b/docs/source/modules/formatter.md @@ -0,0 +1,13 @@ +# Formatter Modules + +Formatter modules are used to format the data extracted from a URL into a specific format. Currently the most widely-used formatter is the HTML formatter, which formats the data into an easily viewable HTML page. + +```{include} autogen/formatter.md +``` + +```{toctree} +:depth: 1 +:hidden: +:glob: +autogen/formatter/* +``` \ No newline at end of file diff --git a/docs/source/modules/storage.md b/docs/source/modules/storage.md new file mode 100644 index 0000000..427213c --- /dev/null +++ b/docs/source/modules/storage.md @@ -0,0 +1,15 @@ +# Storage Modules + +Storage modules are used to store the data extracted from a URL in a persistent location. This can be on your local hard disk, or on a remote server (e.g. S3 or Google Drive). + +The default is to store the files downloaded (e.g. images, videos) in a local directory. + +```{include} autogen/storage.md +``` + +```{toctree} +:depth: 1 +:hidden: +:glob: +autogen/storage/* +``` \ No newline at end of file diff --git a/docs/source/overview.md b/docs/source/overview.md new file mode 100644 index 0000000..57e8d60 --- /dev/null +++ b/docs/source/overview.md @@ -0,0 +1,16 @@ + +```{include} ../../README.md +``` + +```{toctree} +:maxdepth: 2 +:hidden: +:caption: Contents: + +Overview +installation/installation.rst +core_modules.md +how_to +development/developer_guidelines +autoapi/index.rst +``` \ No newline at end of file diff --git a/docs/source/user_guidelines.rst b/docs/source/user_guidelines.rst deleted file mode 100644 index 93fb2f2..0000000 --- a/docs/source/user_guidelines.rst +++ /dev/null @@ -1,11 +0,0 @@ - -User Guidelines -=============== - -This section of the documentation provides guidelines for users who want to use the tool, -without needing to modify the code. -To see the developer guidelines, see :ref:`developer_guidelines`. - -.. note:: - - This is a work in progress. diff --git a/example.orchestration.yaml b/example.orchestration.yaml deleted file mode 100644 index f1eed2a..0000000 --- a/example.orchestration.yaml +++ /dev/null @@ -1,156 +0,0 @@ -steps: - # only 1 feeder allowed - feeder: gsheet_feeder # defaults to cli_feeder - archivers: # order matters, uncomment to activate - - bluesky_archiver - # - vk_archiver - # - telethon_archiver - # - telegram_archiver - # - twitter_archiver - # - twitter_api_archiver - # - instagram_api_archiver - # - instagram_tbot_archiver - # - instagram_archiver - # - tiktok_archiver - - youtubedl_archiver - # - wayback_archiver_enricher - # - wacz_archiver_enricher - enrichers: - - hash_enricher - # - meta_enricher - # - metadata_enricher - # - screenshot_enricher - # - pdq_hash_enricher - # - ssl_enricher - # - timestamping_enricher - # - whisper_enricher - # - thumbnail_enricher - # - wayback_archiver_enricher - # - wacz_archiver_enricher - # - pdq_hash_enricher # if you want to calculate hashes for thumbnails, include this after thumbnail_enricher - formatter: html_formatter # defaults to mute_formatter - storages: - - local_storage - # - s3_storage - # - gdrive_storage - databases: - - console_db - # - csv_db - # - gsheet_db - # - mongo_db - -configurations: - gsheet_feeder: - sheet: "your sheet name" - header: 1 - service_account: "secrets/service_account.json" - # allow_worksheets: "only parse this worksheet" - # block_worksheets: "blocked sheet 1,blocked sheet 2" - use_sheet_names_in_stored_paths: false - columns: - url: link - status: archive status - folder: destination folder - archive: archive location - date: archive date - thumbnail: thumbnail - timestamp: upload timestamp - title: upload title - text: textual content - screenshot: screenshot - hash: hash - pdq_hash: perceptual hashes - wacz: wacz - replaywebpage: replaywebpage - instagram_tbot_archiver: - api_id: "TELEGRAM_BOT_API_ID" - api_hash: "TELEGRAM_BOT_API_HASH" - # session_file: "secrets/anon" - telethon_archiver: - api_id: "TELEGRAM_BOT_API_ID" - api_hash: "TELEGRAM_BOT_API_HASH" - # session_file: "secrets/anon" - join_channels: false - channel_invites: # if you want to archive from private channels - - invite: https://t.me/+123456789 - id: 0000000001 - - invite: https://t.me/+123456788 - id: 0000000002 - - twitter_api_archiver: - # either bearer_token only - bearer_token: "TWITTER_BEARER_TOKEN" - # OR all of the below - # consumer_key: "" - # consumer_secret: "" - # access_token: "" - # access_secret: "" - instagram_archiver: - username: "INSTAGRAM_USERNAME" - password: "INSTAGRAM_PASSWORD" - # session_file: "secrets/instaloader.session" - - vk_archiver: - username: "or phone number" - password: "vk pass" - session_file: "secrets/vk_config.v2.json" - - youtubedl_archiver: - subtitles: true - # use one of the following two methods to authenticate in youtube - either provide a cookies file or use the cookies of the given browser - # for more information, see https://github.com/yt-dlp/yt-dlp/wiki/FAQ#how-do-i-pass-cookies-to-yt-dlp - # cookie_file: "secrets/youtube_cookies.txt" - # cookies_from_browser: firefox - # proxy: socks5://proxy-user:password@proxy-ip:port - - screenshot_enricher: - width: 1280 - height: 2300 - # to save as pdf, uncomment the following lines and adjust the print options - # save_to_pdf: true - # print_options: - # for all options see https://www.selenium.dev/selenium/docs/api/py/webdriver/selenium.webdriver.common.print_page_options.html - # background: true - # orientation: "portrait" - # scale: 1 - # page_width: 8.5in - # page_height: 11in - # margin_top: 0.4in - # margin_bottom: 0.4in - # margin_left: 0.4in - # margin_right: 0.4in - # page_ranges: "" - # shrink_to_fit: true - - wayback_archiver_enricher: - timeout: 10 - key: "wayback key" - secret: "wayback secret" - hash_enricher: - algorithm: "SHA3-512" # can also be SHA-256 - wacz_archiver_enricher: - profile: secrets/profile.tar.gz - local_storage: - save_to: "./local_archive" - save_absolute: true - filename_generator: static - path_generator: flat - s3_storage: - bucket: your-bucket-name - region: reg1 - key: S3_KEY - secret: S3_SECRET - endpoint_url: "https://{region}.digitaloceanspaces.com" - cdn_url: "https://{bucket}.{region}.cdn.digitaloceanspaces.com/{key}" - # if private:true S3 urls will not be readable online - private: false - # with 'random' you can generate a random UUID for the URL instead of a predictable path, useful to still have public but unlisted files, alternative is 'default' or not omitted from config - key_path: random - gdrive_storage: - path_generator: url - filename_generator: random - root_folder_id: folder_id_from_url - oauth_token: secrets/gd-token.json # needs to be generated with scripts/create_update_gdrive_oauth_token.py - service_account: "secrets/service_account.json" - csv_db: - csv_file: "./local_archive/db.csv" diff --git a/poetry.lock b/poetry.lock index 8fb48ec..83b2860 100644 --- a/poetry.lock +++ b/poetry.lock @@ -1,5 +1,24 @@ # This file is automatically @generated by Poetry 2.0.1 and should not be changed by hand. +[[package]] +name = "accessible-pygments" +version = "0.0.5" +description = "A collection of accessible pygments styles" +optional = false +python-versions = ">=3.9" +groups = ["docs"] +files = [ + {file = "accessible_pygments-0.0.5-py3-none-any.whl", hash = "sha256:88ae3211e68a1d0b011504b2ffc1691feafce124b845bd072ab6f9f66f34d4b7"}, + {file = "accessible_pygments-0.0.5.tar.gz", hash = "sha256:40918d3e6a2b619ad424cb91e556bd3bd8865443d9f22f1dcdf79e33c8046872"}, +] + +[package.dependencies] +pygments = ">=1.5" + +[package.extras] +dev = ["pillow", "pkginfo (>=1.10)", "playwright", "pre-commit", "setuptools", "twine (>=5.0)"] +tests = ["hypothesis", "pytest"] + [[package]] name = "alabaster" version = "1.0.0" @@ -84,14 +103,14 @@ tests-mypy = ["mypy (>=1.11.1)", "pytest-mypy-plugins"] [[package]] name = "authlib" -version = "1.4.0" +version = "1.4.1" description = "The ultimate Python library in building OAuth and OpenID Connect servers and clients." optional = false python-versions = ">=3.9" groups = ["main"] files = [ - {file = "Authlib-1.4.0-py2.py3-none-any.whl", hash = "sha256:4bb20b978c8b636222b549317c1815e1fe62234fc1c5efe8855d84aebf3a74e3"}, - {file = "authlib-1.4.0.tar.gz", hash = "sha256:1c1e6608b5ed3624aeeee136ca7f8c120d6f51f731aa152b153d54741840e1f2"}, + {file = "Authlib-1.4.1-py2.py3-none-any.whl", hash = "sha256:edc29c3f6a3e72cd9e9f45fff67fc663a2c364022eb0371c003f22d5405915c1"}, + {file = "authlib-1.4.1.tar.gz", hash = "sha256:30ead9ea4993cdbab821dc6e01e818362f92da290c04c7f6a1940f86507a790d"}, ] [package.dependencies] @@ -115,33 +134,34 @@ tomli = {version = "*", markers = "python_version < \"3.11\""} [[package]] name = "babel" -version = "2.16.0" +version = "2.17.0" description = "Internationalization utilities" optional = false python-versions = ">=3.8" groups = ["docs"] files = [ - {file = "babel-2.16.0-py3-none-any.whl", hash = "sha256:368b5b98b37c06b7daf6696391c3240c938b37767d4584413e8438c5c435fa8b"}, - {file = "babel-2.16.0.tar.gz", hash = "sha256:d1f3554ca26605fe173f3de0c65f750f5a42f924499bf134de6423582298e316"}, + {file = "babel-2.17.0-py3-none-any.whl", hash = "sha256:4d0b53093fdfb4b21c92b5213dba5a1b23885afa8383709427046b21c366e5f2"}, + {file = "babel-2.17.0.tar.gz", hash = "sha256:0c54cffb19f690cdcc52a3b50bcbf71e07a808d1c80d549f2459b9d2cf0afb9d"}, ] [package.extras] -dev = ["freezegun (>=1.0,<2.0)", "pytest (>=6.0)", "pytest-cov"] +dev = ["backports.zoneinfo", "freezegun (>=1.0,<2.0)", "jinja2 (>=3.0)", "pytest (>=6.0)", "pytest-cov", "pytz", "setuptools", "tzdata"] [[package]] name = "beautifulsoup4" -version = "4.12.3" +version = "4.13.3" description = "Screen-scraping library" optional = false -python-versions = ">=3.6.0" +python-versions = ">=3.7.0" groups = ["main", "docs"] files = [ - {file = "beautifulsoup4-4.12.3-py3-none-any.whl", hash = "sha256:b80878c9f40111313e55da8ba20bdba06d8fa3969fc68304167741bbf9e082ed"}, - {file = "beautifulsoup4-4.12.3.tar.gz", hash = "sha256:74e3d1928edc070d21748185c46e3fb33490f22f52a3addee9aee0f4f7781051"}, + {file = "beautifulsoup4-4.13.3-py3-none-any.whl", hash = "sha256:99045d7d3f08f91f0d656bc9b7efbae189426cd913d830294a15eefa0ea4df16"}, + {file = "beautifulsoup4-4.13.3.tar.gz", hash = "sha256:1bd32405dacc920b42b83ba01644747ed77456a65760e285fbc47633ceddaf8b"}, ] [package.dependencies] soupsieve = ">1.2" +typing-extensions = ">=4.0.0" [package.extras] cchardet = ["cchardet"] @@ -152,18 +172,18 @@ lxml = ["lxml"] [[package]] name = "boto3" -version = "1.36.6" +version = "1.36.22" description = "The AWS SDK for Python" optional = false python-versions = ">=3.8" groups = ["main"] files = [ - {file = "boto3-1.36.6-py3-none-any.whl", hash = "sha256:6d473f0f340d02b4e9ad5b8e68786a09728101a8b950231b89ebdaf72b6dca21"}, - {file = "boto3-1.36.6.tar.gz", hash = "sha256:b36feae061dc0793cf311468956a0a9e99215ce38bc99a1a4e55a5b105f16297"}, + {file = "boto3-1.36.22-py3-none-any.whl", hash = "sha256:39957eabdce009353d72d131046489fbbfa15891865d5f069f1e8bfa414e6b81"}, + {file = "boto3-1.36.22.tar.gz", hash = "sha256:768c8a4d4a6227fe2258105efa086f1424cba5ca915a5eb2305b2cd979306ad1"}, ] [package.dependencies] -botocore = ">=1.36.6,<1.37.0" +botocore = ">=1.36.22,<1.37.0" jmespath = ">=0.7.1,<2.0.0" s3transfer = ">=0.11.0,<0.12.0" @@ -172,14 +192,14 @@ crt = ["botocore[crt] (>=1.21.0,<2.0a0)"] [[package]] name = "botocore" -version = "1.36.6" +version = "1.36.22" description = "Low-level, data-driven core of boto 3." optional = false python-versions = ">=3.8" groups = ["main"] files = [ - {file = "botocore-1.36.6-py3-none-any.whl", hash = "sha256:f77bbbb03fb420e260174650fb5c0cc142ec20a96967734eed2b0ef24334ef34"}, - {file = "botocore-1.36.6.tar.gz", hash = "sha256:4864c53d638da191a34daf3ede3ff1371a3719d952cc0c6bd24ce2836a38dd77"}, + {file = "botocore-1.36.22-py3-none-any.whl", hash = "sha256:75d6b34acb0686ee4d54ff6eb285e78ccfe318407428769d1e3e13351714d890"}, + {file = "botocore-1.36.22.tar.gz", hash = "sha256:59520247d5a479731724f97c995d5a1c2aae3b303b324f39d99efcfad1d3019e"}, ] [package.dependencies] @@ -188,7 +208,7 @@ python-dateutil = ">=2.1,<3.0.0" urllib3 = {version = ">=1.25.4,<2.2.0 || >2.2.0,<3", markers = "python_version >= \"3.10\""} [package.extras] -crt = ["awscrt (==0.23.4)"] +crt = ["awscrt (==0.23.8)"] [[package]] name = "brotli" @@ -355,14 +375,14 @@ files = [ [[package]] name = "certifi" -version = "2024.12.14" +version = "2025.1.31" description = "Python package for providing Mozilla's CA Bundle." optional = false python-versions = ">=3.6" groups = ["main", "docs"] files = [ - {file = "certifi-2024.12.14-py3-none-any.whl", hash = "sha256:1275f7a45be9464efc1173084eaa30f866fe2e47d389406136d332ed4967ec56"}, - {file = "certifi-2024.12.14.tar.gz", hash = "sha256:b650d30f370c2b724812bee08008be0c4163b163ddaec3f2546c1caf65f191db"}, + {file = "certifi-2025.1.31-py3-none-any.whl", hash = "sha256:ca78db4565a652026a4db2bcdf68f2fb589ea80d0be70e03929ed730746b84fe"}, + {file = "certifi-2025.1.31.tar.gz", hash = "sha256:3d5da6925056f6f18f119200434a4780a94263f10d1c21d032a6f6b2baa20651"}, ] [[package]] @@ -655,26 +675,26 @@ typing-inspect = ">=0.4.0,<1" [[package]] name = "dateparser" -version = "1.2.0" +version = "1.2.1" description = "Date parsing library designed to parse dates from HTML pages" optional = false -python-versions = ">=3.7" +python-versions = ">=3.8" groups = ["main"] files = [ - {file = "dateparser-1.2.0-py2.py3-none-any.whl", hash = "sha256:0b21ad96534e562920a0083e97fd45fa959882d4162acc358705144520a35830"}, - {file = "dateparser-1.2.0.tar.gz", hash = "sha256:7975b43a4222283e0ae15be7b4999d08c9a70e2d378ac87385b1ccf2cffbbb30"}, + {file = "dateparser-1.2.1-py3-none-any.whl", hash = "sha256:bdcac262a467e6260030040748ad7c10d6bacd4f3b9cdb4cfd2251939174508c"}, + {file = "dateparser-1.2.1.tar.gz", hash = "sha256:7e4919aeb48481dbfc01ac9683c8e20bfe95bb715a38c1e9f6af889f4f30ccc3"}, ] [package.dependencies] -python-dateutil = "*" -pytz = "*" -regex = "<2019.02.19 || >2019.02.19,<2021.8.27 || >2021.8.27" -tzlocal = "*" +python-dateutil = ">=2.7.0" +pytz = ">=2024.2" +regex = ">=2015.06.24,<2019.02.19 || >2019.02.19,<2021.8.27 || >2021.8.27" +tzlocal = ">=0.2" [package.extras] -calendars = ["convertdate", "hijri-converter"] -fasttext = ["fasttext"] -langdetect = ["langdetect"] +calendars = ["convertdate (>=2.2.1)", "hijridate"] +fasttext = ["fasttext (>=0.9.1)", "numpy (>=1.19.3,<2)"] +langdetect = ["langdetect (>=1.0.0)"] [[package]] name = "docutils" @@ -722,24 +742,6 @@ future = "*" [package.extras] dev = ["Sphinx (==2.1.0)", "future (==0.17.1)", "numpy (==1.16.4)", "pytest (==4.6.1)", "pytest-mock (==1.10.4)", "tox (==3.12.1)"] -[[package]] -name = "furo" -version = "2024.8.6" -description = "A clean customisable Sphinx documentation theme." -optional = false -python-versions = ">=3.8" -groups = ["docs"] -files = [ - {file = "furo-2024.8.6-py3-none-any.whl", hash = "sha256:6cd97c58b47813d3619e63e9081169880fbe331f0ca883c871ff1f3f11814f5c"}, - {file = "furo-2024.8.6.tar.gz", hash = "sha256:b63e4cee8abfc3136d3bc03a3d45a76a850bada4d6374d24c1716b0e01394a01"}, -] - -[package.dependencies] -beautifulsoup4 = "*" -pygments = ">=2.7" -sphinx = ">=6.0,<9.0" -sphinx-basic-ng = ">=1.0.0.beta2" - [[package]] name = "future" version = "1.0.0" @@ -754,14 +756,14 @@ files = [ [[package]] name = "google-api-core" -version = "2.24.0" +version = "2.24.1" description = "Google API client core library" optional = false python-versions = ">=3.7" groups = ["main"] files = [ - {file = "google_api_core-2.24.0-py3-none-any.whl", hash = "sha256:10d82ac0fca69c82a25b3efdeefccf6f28e02ebb97925a8cce8edbfe379929d9"}, - {file = "google_api_core-2.24.0.tar.gz", hash = "sha256:e255640547a597a4da010876d333208ddac417d60add22b6851a0c66a831fcaf"}, + {file = "google_api_core-2.24.1-py3-none-any.whl", hash = "sha256:bc78d608f5a5bf853b80bd70a795f703294de656c096c0968320830a4bc280f1"}, + {file = "google_api_core-2.24.1.tar.gz", hash = "sha256:f8b36f5456ab0dd99a1b693a40a31d1e7757beea380ad1b38faaf8941eae9d8a"}, ] [package.dependencies] @@ -779,14 +781,14 @@ grpcio-gcp = ["grpcio-gcp (>=0.2.2,<1.0.dev0)"] [[package]] name = "google-api-python-client" -version = "2.159.0" +version = "2.161.0" description = "Google API Client Library for Python" optional = false python-versions = ">=3.7" groups = ["main"] files = [ - {file = "google_api_python_client-2.159.0-py2.py3-none-any.whl", hash = "sha256:baef0bb631a60a0bd7c0bf12a5499e3a40cd4388484de7ee55c1950bf820a0cf"}, - {file = "google_api_python_client-2.159.0.tar.gz", hash = "sha256:55197f430f25c907394b44fa078545ffef89d33fd4dca501b7db9f0d8e224bd6"}, + {file = "google_api_python_client-2.161.0-py2.py3-none-any.whl", hash = "sha256:9476a5a4f200bae368140453df40f9cda36be53fa7d0e9a9aac4cdb859a26448"}, + {file = "google_api_python_client-2.161.0.tar.gz", hash = "sha256:324c0cce73e9ea0a0d2afd5937e01b7c2d6a4d7e2579cdb6c384f9699d6c9f37"}, ] [package.dependencies] @@ -858,14 +860,14 @@ tool = ["click (>=6.0.0)"] [[package]] name = "googleapis-common-protos" -version = "1.66.0" +version = "1.67.0" description = "Common protobufs used in Google APIs" optional = false python-versions = ">=3.7" groups = ["main"] files = [ - {file = "googleapis_common_protos-1.66.0-py2.py3-none-any.whl", hash = "sha256:d7abcd75fabb2e0ec9f74466401f6c119a0b498e27370e9be4c94cb7e382b8ed"}, - {file = "googleapis_common_protos-1.66.0.tar.gz", hash = "sha256:c3e7b33d15fdca5374cc0a7346dd92ffa847425cc4ea941d970f13680052ec8c"}, + {file = "googleapis_common_protos-1.67.0-py2.py3-none-any.whl", hash = "sha256:579de760800d13616f51cf8be00c876f00a9f146d3e6510e19d1f4111758b741"}, + {file = "googleapis_common_protos-1.67.0.tar.gz", hash = "sha256:21398025365f138be356d5923e9168737d94d46a72aefee4a6110a1f23463c86"}, ] [package.dependencies] @@ -1019,6 +1021,27 @@ files = [ [package.dependencies] attrs = ">=19.2.0" +[[package]] +name = "linkify-it-py" +version = "2.0.3" +description = "Links recognition library with FULL unicode support." +optional = false +python-versions = ">=3.7" +groups = ["docs"] +files = [ + {file = "linkify-it-py-2.0.3.tar.gz", hash = "sha256:68cda27e162e9215c17d786649d1da0021a451bdc436ef9e0fa0ba5234b9b048"}, + {file = "linkify_it_py-2.0.3-py3-none-any.whl", hash = "sha256:6bcbc417b0ac14323382aef5c5192c0075bf8a9d6b41820a2b66371eac6b6d79"}, +] + +[package.dependencies] +uc-micro-py = "*" + +[package.extras] +benchmark = ["pytest", "pytest-benchmark"] +dev = ["black", "flake8", "isort", "pre-commit", "pyproject-flake8"] +doc = ["myst-parser", "sphinx", "sphinx-book-theme"] +test = ["coverage", "pytest", "pytest-cov"] + [[package]] name = "loguru" version = "0.7.3" @@ -1136,14 +1159,14 @@ files = [ [[package]] name = "marshmallow" -version = "3.26.0" +version = "3.26.1" description = "A lightweight library for converting complex datatypes to and from native Python datatypes." optional = false python-versions = ">=3.9" groups = ["main"] files = [ - {file = "marshmallow-3.26.0-py3-none-any.whl", hash = "sha256:1287bca04e6a5f4094822ac153c03da5e214a0a60bcd557b140f3e66991b8ca1"}, - {file = "marshmallow-3.26.0.tar.gz", hash = "sha256:eb36762a1cc76d7abf831e18a3a1b26d3d481bbc74581b8e532a3d3a8115e1cb"}, + {file = "marshmallow-3.26.1-py3-none-any.whl", hash = "sha256:3350409f20a70a7e4e11a27661187b77cdcaeb20abca41c1454fe33636bea09c"}, + {file = "marshmallow-3.26.1.tar.gz", hash = "sha256:e6d8affb6cb61d39d26402096dc0aee12d5a26d490a121f118d2e81dc0719dc6"}, ] [package.dependencies] @@ -1212,14 +1235,14 @@ files = [ [[package]] name = "myst-parser" -version = "4.0.0" +version = "4.0.1" description = "An extended [CommonMark](https://spec.commonmark.org/) compliant parser," optional = false python-versions = ">=3.10" groups = ["docs"] files = [ - {file = "myst_parser-4.0.0-py3-none-any.whl", hash = "sha256:b9317997552424448c6096c2558872fdb6f81d3ecb3a40ce84a7518798f3f28d"}, - {file = "myst_parser-4.0.0.tar.gz", hash = "sha256:851c9dfb44e36e56d15d05e72f02b80da21a9e0d07cba96baf5e2d476bb91531"}, + {file = "myst_parser-4.0.1-py3-none-any.whl", hash = "sha256:9134e88959ec3b5780aedf8a99680ea242869d012e8821db3126d427edc9c95d"}, + {file = "myst_parser-4.0.1.tar.gz", hash = "sha256:5cfea715e4f3574138aecbf7d54132296bfd72bb614d31168f48c477a830a7c4"}, ] [package.dependencies] @@ -1231,10 +1254,10 @@ pyyaml = "*" sphinx = ">=7,<9" [package.extras] -code-style = ["pre-commit (>=3.0,<4.0)"] +code-style = ["pre-commit (>=4.0,<5.0)"] linkify = ["linkify-it-py (>=2.0,<3.0)"] rtd = ["ipython", "sphinx (>=7)", "sphinx-autodoc2 (>=0.5.0,<0.6.0)", "sphinx-book-theme (>=1.1,<2.0)", "sphinx-copybutton", "sphinx-design", "sphinx-pyscript", "sphinx-tippy (>=0.4.3)", "sphinx-togglebutton", "sphinxext-opengraph (>=0.9.0,<0.10.0)", "sphinxext-rediraffe (>=0.2.7,<0.3.0)"] -testing = ["beautifulsoup4", "coverage[toml]", "defusedxml", "pytest (>=8,<9)", "pytest-cov", "pytest-param-files (>=0.6.0,<0.7.0)", "pytest-regressions", "sphinx-pytest"] +testing = ["beautifulsoup4", "coverage[toml]", "defusedxml", "pygments (<2.19)", "pytest (>=8,<9)", "pytest-cov", "pytest-param-files (>=0.6.0,<0.7.0)", "pytest-regressions", "sphinx-pytest"] testing-docutils = ["pygments", "pytest (>=8,<9)", "pytest-param-files (>=0.6.0,<0.7.0)"] [[package]] @@ -1345,18 +1368,14 @@ description = "TLS (SSL) sockets, key generation, encryption, decryption, signin optional = false python-versions = "*" groups = ["main"] -files = [] -develop = false +files = [ + {file = "oscrypto-1.3.0-py2.py3-none-any.whl", hash = "sha256:2b2f1d2d42ec152ca90ccb5682f3e051fb55986e1b170ebde472b133713e7085"}, + {file = "oscrypto-1.3.0.tar.gz", hash = "sha256:6f5fef59cb5b3708321db7cca56aed8ad7e662853351e7991fcf60ec606d47a4"}, +] [package.dependencies] asn1crypto = ">=1.5.1" -[package.source] -type = "git" -url = "https://github.com/wbond/oscrypto.git" -reference = "d5f3437ed24257895ae1edd9e503cfb352e635a8" -resolved_reference = "d5f3437ed24257895ae1edd9e503cfb352e635a8" - [[package]] name = "outcome" version = "1.3.0.post0" @@ -1512,14 +1531,14 @@ testing = ["pytest", "pytest-benchmark"] [[package]] name = "proto-plus" -version = "1.25.0" -description = "Beautiful, Pythonic protocol buffers." +version = "1.26.0" +description = "Beautiful, Pythonic protocol buffers" optional = false python-versions = ">=3.7" groups = ["main"] files = [ - {file = "proto_plus-1.25.0-py3-none-any.whl", hash = "sha256:c91fc4a65074ade8e458e95ef8bac34d4008daa7cce4a12d6707066fca648961"}, - {file = "proto_plus-1.25.0.tar.gz", hash = "sha256:fbb17f57f7bd05a68b7707e745e26528b0b3c34e378db91eef93912c54982d91"}, + {file = "proto_plus-1.26.0-py3-none-any.whl", hash = "sha256:bf2dfaa3da281fc3187d12d224c707cb57214fb2c22ba854eb0c105a3fb2d4d7"}, + {file = "proto_plus-1.26.0.tar.gz", hash = "sha256:6e93d5f5ca267b54300880fff156b6a3386b3fa3f43b1da62e680fc0c586ef22"}, ] [package.dependencies] @@ -1653,6 +1672,34 @@ files = [ {file = "pycryptodomex-3.21.0.tar.gz", hash = "sha256:222d0bd05381dd25c32dd6065c071ebf084212ab79bab4599ba9e6a3e0009e6c"}, ] +[[package]] +name = "pydata-sphinx-theme" +version = "0.16.1" +description = "Bootstrap-based Sphinx theme from the PyData community" +optional = false +python-versions = ">=3.9" +groups = ["docs"] +files = [ + {file = "pydata_sphinx_theme-0.16.1-py3-none-any.whl", hash = "sha256:225331e8ac4b32682c18fcac5a57a6f717c4e632cea5dd0e247b55155faeccde"}, + {file = "pydata_sphinx_theme-0.16.1.tar.gz", hash = "sha256:a08b7f0b7f70387219dc659bff0893a7554d5eb39b59d3b8ef37b8401b7642d7"}, +] + +[package.dependencies] +accessible-pygments = "*" +Babel = "*" +beautifulsoup4 = "*" +docutils = "!=0.17.0" +pygments = ">=2.7" +sphinx = ">=6.1" +typing-extensions = "*" + +[package.extras] +a11y = ["pytest-playwright"] +dev = ["pandoc", "pre-commit", "pydata-sphinx-theme[doc,test]", "pyyaml", "sphinx-theme-builder[cli]", "tox"] +doc = ["ablog (>=0.11.8)", "colorama", "graphviz", "ipykernel", "ipyleaflet", "ipywidgets", "jupyter_sphinx", "jupyterlite-sphinx", "linkify-it-py", "matplotlib", "myst-parser", "nbsphinx", "numpy", "numpydoc", "pandas", "plotly", "rich", "sphinx-autoapi (>=3.0.0)", "sphinx-copybutton", "sphinx-design", "sphinx-favicon (>=1.0.1)", "sphinx-sitemap", "sphinx-togglebutton", "sphinxcontrib-youtube (>=1.4.1)", "sphinxext-rediraffe", "xarray"] +i18n = ["Babel", "jinja2"] +test = ["pytest", "pytest-cov", "pytest-regressions", "sphinx[test]"] + [[package]] name = "pygments" version = "2.19.1" @@ -1768,6 +1815,24 @@ loguru = "*" [package.extras] test = ["pytest", "pytest-cov"] +[[package]] +name = "pytest-mock" +version = "3.14.0" +description = "Thin-wrapper around the mock package for easier use with pytest" +optional = false +python-versions = ">=3.8" +groups = ["dev"] +files = [ + {file = "pytest-mock-3.14.0.tar.gz", hash = "sha256:2719255a1efeceadbc056d6bf3df3d1c5015530fb40cf347c0f9afac88410bd0"}, + {file = "pytest_mock-3.14.0-py3-none-any.whl", hash = "sha256:0b72c38033392a5f4621342fe11e9219ac11ec9d375f8e2a0c164539e0d70f6f"}, +] + +[package.dependencies] +pytest = ">=6.2.5" + +[package.extras] +dev = ["pre-commit", "pytest-asyncio", "tox"] + [[package]] name = "python-dateutil" version = "2.9.0.post0" @@ -1820,14 +1885,14 @@ requests = ">=2.28" [[package]] name = "pytz" -version = "2024.2" +version = "2025.1" description = "World timezone definitions, modern and historical" optional = false python-versions = "*" groups = ["main"] files = [ - {file = "pytz-2024.2-py2.py3-none-any.whl", hash = "sha256:31c7c1817eb7fae7ca4b8c7ee50c72f93aa2dd863de768e1ef4245d426aa0725"}, - {file = "pytz-2024.2.tar.gz", hash = "sha256:2aa355083c50a0f93fa581709deac0c9ad65cca8a9e9beac660adcbd493c798a"}, + {file = "pytz-2025.1-py2.py3-none-any.whl", hash = "sha256:89dd22dca55b46eac6eda23b2d72721bf1bdfef212645d81513ef5d03038de57"}, + {file = "pytz-2025.1.tar.gz", hash = "sha256:c2db42be2a2518b28e65f9207c4d05e6ff547d1efa4086469ef855e4ab70178e"}, ] [[package]] @@ -2076,14 +2141,14 @@ jupyter = ["ipywidgets (>=7.5.1,<9)"] [[package]] name = "rich-argparse" -version = "1.6.0" +version = "1.7.0" description = "Rich help formatters for argparse and optparse" optional = false python-versions = ">=3.8" groups = ["main"] files = [ - {file = "rich_argparse-1.6.0-py3-none-any.whl", hash = "sha256:fbe70a1d821b3f2fa8958cddf0cae131870a6e9faa04ab52b409cb1eda809bd7"}, - {file = "rich_argparse-1.6.0.tar.gz", hash = "sha256:092083c30da186f25bcdff8b1d47fdfb571288510fb051e0488a72cc3128de13"}, + {file = "rich_argparse-1.7.0-py3-none-any.whl", hash = "sha256:b8ec8943588e9731967f4f97b735b03dc127c416f480a083060433a97baf2fd3"}, + {file = "rich_argparse-1.7.0.tar.gz", hash = "sha256:f31d809c465ee43f367d599ccaf88b73bc2c4d75d74ed43f2d538838c53544ba"}, ] [package.dependencies] @@ -2316,24 +2381,24 @@ test = ["cython (>=3.0)", "defusedxml (>=0.7.1)", "pytest (>=8.0)", "setuptools [[package]] name = "sphinx-autoapi" -version = "3.4.0" +version = "3.6.0" description = "Sphinx API documentation generator" optional = false -python-versions = ">=3.8" +python-versions = ">=3.9" groups = ["docs"] files = [ - {file = "sphinx_autoapi-3.4.0-py3-none-any.whl", hash = "sha256:4027fef2875a22c5f2a57107c71641d82f6166bf55beb407a47aaf3ef14e7b92"}, - {file = "sphinx_autoapi-3.4.0.tar.gz", hash = "sha256:e6d5371f9411bbb9fca358c00a9e57aef3ac94cbfc5df4bab285946462f69e0c"}, + {file = "sphinx_autoapi-3.6.0-py3-none-any.whl", hash = "sha256:f3b66714493cab140b0e896d33ce7137654a16ac1edb6563edcbd47bf975f711"}, + {file = "sphinx_autoapi-3.6.0.tar.gz", hash = "sha256:c685f274e41d0842ae7e199460c322c4bd7fec816ccc2da8d806094b4f64af06"}, ] [package.dependencies] astroid = [ {version = ">=2.7", markers = "python_version < \"3.12\""}, - {version = ">=3.0.0a1", markers = "python_version >= \"3.12\""}, + {version = ">=3", markers = "python_version >= \"3.12\""}, ] Jinja2 = "*" PyYAML = "*" -sphinx = ">=6.1.0" +sphinx = ">=7.4.0" [[package]] name = "sphinx-autobuild" @@ -2359,22 +2424,25 @@ websockets = ">=11" test = ["httpx", "pytest (>=6)"] [[package]] -name = "sphinx-basic-ng" -version = "1.0.0b2" -description = "A modern skeleton for Sphinx themes." +name = "sphinx-book-theme" +version = "1.1.3" +description = "A clean book theme for scientific explanations and documentation with Sphinx" optional = false -python-versions = ">=3.7" +python-versions = ">=3.9" groups = ["docs"] files = [ - {file = "sphinx_basic_ng-1.0.0b2-py3-none-any.whl", hash = "sha256:eb09aedbabfb650607e9b4b68c9d240b90b1e1be221d6ad71d61c52e29f7932b"}, - {file = "sphinx_basic_ng-1.0.0b2.tar.gz", hash = "sha256:9ec55a47c90c8c002b5960c57492ec3021f5193cb26cebc2dc4ea226848651c9"}, + {file = "sphinx_book_theme-1.1.3-py3-none-any.whl", hash = "sha256:a554a9a7ac3881979a87a2b10f633aa2a5706e72218a10f71be38b3c9e831ae9"}, + {file = "sphinx_book_theme-1.1.3.tar.gz", hash = "sha256:1f25483b1846cb3d353a6bc61b3b45b031f4acf845665d7da90e01ae0aef5b4d"}, ] [package.dependencies] -sphinx = ">=4.0" +pydata-sphinx-theme = ">=0.15.2" +sphinx = ">=5" [package.extras] -docs = ["furo", "ipython", "myst-parser", "sphinx-copybutton", "sphinx-inline-tabs"] +code-style = ["pre-commit"] +doc = ["ablog", "folium", "ipywidgets", "matplotlib", "myst-nb", "nbclient", "numpy", "numpydoc", "pandas", "plotly", "sphinx-copybutton", "sphinx-design", "sphinx-examples", "sphinx-tabs", "sphinx-thebe", "sphinx-togglebutton", "sphinxcontrib-bibtex", "sphinxcontrib-youtube", "sphinxext-opengraph"] +test = ["beautifulsoup4", "coverage", "defusedxml", "myst-nb", "pytest", "pytest-cov", "pytest-regressions", "sphinx_thebe"] [[package]] name = "sphinx-copybutton" @@ -2630,14 +2698,14 @@ telegram = ["requests"] [[package]] name = "trio" -version = "0.28.0" +version = "0.29.0" description = "A friendly Python library for async concurrency and I/O" optional = false python-versions = ">=3.9" groups = ["main"] files = [ - {file = "trio-0.28.0-py3-none-any.whl", hash = "sha256:56d58977acc1635735a96581ec70513cc781b8b6decd299c487d3be2a721cd94"}, - {file = "trio-0.28.0.tar.gz", hash = "sha256:4e547896fe9e8a5658e54e4c7c5fa1db748cbbbaa7c965e7d40505b928c73c05"}, + {file = "trio-0.29.0-py3-none-any.whl", hash = "sha256:d8c463f1a9cc776ff63e331aba44c125f423a5a13c684307e828d930e625ba66"}, + {file = "trio-0.29.0.tar.gz", hash = "sha256:ea0d3967159fc130acb6939a0be0e558e364fee26b5deeecc893a6b08c361bdf"}, ] [package.dependencies] @@ -2651,18 +2719,19 @@ sortedcontainers = "*" [[package]] name = "trio-websocket" -version = "0.11.1" +version = "0.12.1" description = "WebSocket library for Trio" optional = false -python-versions = ">=3.7" +python-versions = ">=3.8" groups = ["main"] files = [ - {file = "trio-websocket-0.11.1.tar.gz", hash = "sha256:18c11793647703c158b1f6e62de638acada927344d534e3c7628eedcb746839f"}, - {file = "trio_websocket-0.11.1-py3-none-any.whl", hash = "sha256:520d046b0d030cf970b8b2b2e00c4c2245b3807853ecd44214acd33d74581638"}, + {file = "trio_websocket-0.12.1-py3-none-any.whl", hash = "sha256:608ec746bb287e5d5a66baf483e41194193c5cf05ffaad6240e7d1fcd80d1e6f"}, + {file = "trio_websocket-0.12.1.tar.gz", hash = "sha256:d55ccd4d3eae27c494f3fdae14823317839bdcb8214d1173eacc4d42c69fc91b"}, ] [package.dependencies] exceptiongroup = {version = "*", markers = "python_version < \"3.11\""} +outcome = ">=1.2.0" trio = ">=0.11" wsproto = ">=0.14" @@ -2729,14 +2798,14 @@ files = [ [[package]] name = "tzlocal" -version = "5.2" +version = "5.3" description = "tzinfo object for the local timezone" optional = false -python-versions = ">=3.8" +python-versions = ">=3.9" groups = ["main"] files = [ - {file = "tzlocal-5.2-py3-none-any.whl", hash = "sha256:49816ef2fe65ea8ac19d19aa7a1ae0551c834303d5014c6d5a62e4cbda8047b8"}, - {file = "tzlocal-5.2.tar.gz", hash = "sha256:8d399205578f1a9342816409cc1e46a93ebd5755e39ea2d85334bea911bf0e6e"}, + {file = "tzlocal-5.3-py3-none-any.whl", hash = "sha256:3814135a1bb29763c6e4f08fd6e41dbb435c7a60bfbb03270211bcc537187d8c"}, + {file = "tzlocal-5.3.tar.gz", hash = "sha256:2fafbfc07e9d8b49ade18f898d6bcd37ae88ce3ad6486842a2e4f03af68323d2"}, ] [package.dependencies] @@ -2745,6 +2814,21 @@ tzdata = {version = "*", markers = "platform_system == \"Windows\""} [package.extras] devenv = ["check-manifest", "pytest (>=4.3)", "pytest-cov", "pytest-mock (>=3.3)", "zest.releaser"] +[[package]] +name = "uc-micro-py" +version = "1.0.3" +description = "Micro subset of unicode data files for linkify-it-py projects." +optional = false +python-versions = ">=3.7" +groups = ["docs"] +files = [ + {file = "uc-micro-py-1.0.3.tar.gz", hash = "sha256:d321b92cff673ec58027c04015fcaa8bb1e005478643ff4a500882eaab88c48a"}, + {file = "uc_micro_py-1.0.3-py3-none-any.whl", hash = "sha256:db1dffff340817673d7b466ec86114a9dc0e9d4d9b5ba229d9d60e5c12600cd5"}, +] + +[package.extras] +test = ["coverage", "pytest", "pytest-cov"] + [[package]] name = "uritemplate" version = "4.1.1" @@ -2967,81 +3051,81 @@ test = ["websockets"] [[package]] name = "websockets" -version = "14.2" +version = "15.0" description = "An implementation of the WebSocket Protocol (RFC 6455 & 7692)" optional = false python-versions = ">=3.9" groups = ["main", "docs"] files = [ - {file = "websockets-14.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:e8179f95323b9ab1c11723e5d91a89403903f7b001828161b480a7810b334885"}, - {file = "websockets-14.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:0d8c3e2cdb38f31d8bd7d9d28908005f6fa9def3324edb9bf336d7e4266fd397"}, - {file = "websockets-14.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:714a9b682deb4339d39ffa674f7b674230227d981a37d5d174a4a83e3978a610"}, - {file = "websockets-14.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f2e53c72052f2596fb792a7acd9704cbc549bf70fcde8a99e899311455974ca3"}, - {file = "websockets-14.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e3fbd68850c837e57373d95c8fe352203a512b6e49eaae4c2f4088ef8cf21980"}, - {file = "websockets-14.2-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4b27ece32f63150c268593d5fdb82819584831a83a3f5809b7521df0685cd5d8"}, - {file = "websockets-14.2-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:4daa0faea5424d8713142b33825fff03c736f781690d90652d2c8b053345b0e7"}, - {file = "websockets-14.2-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:bc63cee8596a6ec84d9753fd0fcfa0452ee12f317afe4beae6b157f0070c6c7f"}, - {file = "websockets-14.2-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:7a570862c325af2111343cc9b0257b7119b904823c675b22d4ac547163088d0d"}, - {file = "websockets-14.2-cp310-cp310-win32.whl", hash = "sha256:75862126b3d2d505e895893e3deac0a9339ce750bd27b4ba515f008b5acf832d"}, - {file = "websockets-14.2-cp310-cp310-win_amd64.whl", hash = "sha256:cc45afb9c9b2dc0852d5c8b5321759cf825f82a31bfaf506b65bf4668c96f8b2"}, - {file = "websockets-14.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:3bdc8c692c866ce5fefcaf07d2b55c91d6922ac397e031ef9b774e5b9ea42166"}, - {file = "websockets-14.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:c93215fac5dadc63e51bcc6dceca72e72267c11def401d6668622b47675b097f"}, - {file = "websockets-14.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:1c9b6535c0e2cf8a6bf938064fb754aaceb1e6a4a51a80d884cd5db569886910"}, - {file = "websockets-14.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0a52a6d7cf6938e04e9dceb949d35fbdf58ac14deea26e685ab6368e73744e4c"}, - {file = "websockets-14.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9f05702e93203a6ff5226e21d9b40c037761b2cfb637187c9802c10f58e40473"}, - {file = "websockets-14.2-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:22441c81a6748a53bfcb98951d58d1af0661ab47a536af08920d129b4d1c3473"}, - {file = "websockets-14.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:efd9b868d78b194790e6236d9cbc46d68aba4b75b22497eb4ab64fa640c3af56"}, - {file = "websockets-14.2-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:1a5a20d5843886d34ff8c57424cc65a1deda4375729cbca4cb6b3353f3ce4142"}, - {file = "websockets-14.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:34277a29f5303d54ec6468fb525d99c99938607bc96b8d72d675dee2b9f5bf1d"}, - {file = "websockets-14.2-cp311-cp311-win32.whl", hash = "sha256:02687db35dbc7d25fd541a602b5f8e451a238ffa033030b172ff86a93cb5dc2a"}, - {file = "websockets-14.2-cp311-cp311-win_amd64.whl", hash = "sha256:862e9967b46c07d4dcd2532e9e8e3c2825e004ffbf91a5ef9dde519ee2effb0b"}, - {file = "websockets-14.2-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:1f20522e624d7ffbdbe259c6b6a65d73c895045f76a93719aa10cd93b3de100c"}, - {file = "websockets-14.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:647b573f7d3ada919fd60e64d533409a79dcf1ea21daeb4542d1d996519ca967"}, - {file = "websockets-14.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:6af99a38e49f66be5a64b1e890208ad026cda49355661549c507152113049990"}, - {file = "websockets-14.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:091ab63dfc8cea748cc22c1db2814eadb77ccbf82829bac6b2fbe3401d548eda"}, - {file = "websockets-14.2-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b374e8953ad477d17e4851cdc66d83fdc2db88d9e73abf755c94510ebddceb95"}, - {file = "websockets-14.2-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a39d7eceeea35db85b85e1169011bb4321c32e673920ae9c1b6e0978590012a3"}, - {file = "websockets-14.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:0a6f3efd47ffd0d12080594f434faf1cd2549b31e54870b8470b28cc1d3817d9"}, - {file = "websockets-14.2-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:065ce275e7c4ffb42cb738dd6b20726ac26ac9ad0a2a48e33ca632351a737267"}, - {file = "websockets-14.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:e9d0e53530ba7b8b5e389c02282f9d2aa47581514bd6049d3a7cffe1385cf5fe"}, - {file = "websockets-14.2-cp312-cp312-win32.whl", hash = "sha256:20e6dd0984d7ca3037afcb4494e48c74ffb51e8013cac71cf607fffe11df7205"}, - {file = "websockets-14.2-cp312-cp312-win_amd64.whl", hash = "sha256:44bba1a956c2c9d268bdcdf234d5e5ff4c9b6dc3e300545cbe99af59dda9dcce"}, - {file = "websockets-14.2-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:6f1372e511c7409a542291bce92d6c83320e02c9cf392223272287ce55bc224e"}, - {file = "websockets-14.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:4da98b72009836179bb596a92297b1a61bb5a830c0e483a7d0766d45070a08ad"}, - {file = "websockets-14.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:f8a86a269759026d2bde227652b87be79f8a734e582debf64c9d302faa1e9f03"}, - {file = "websockets-14.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:86cf1aaeca909bf6815ea714d5c5736c8d6dd3a13770e885aafe062ecbd04f1f"}, - {file = "websockets-14.2-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a9b0f6c3ba3b1240f602ebb3971d45b02cc12bd1845466dd783496b3b05783a5"}, - {file = "websockets-14.2-cp313-cp313-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:669c3e101c246aa85bc8534e495952e2ca208bd87994650b90a23d745902db9a"}, - {file = "websockets-14.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:eabdb28b972f3729348e632ab08f2a7b616c7e53d5414c12108c29972e655b20"}, - {file = "websockets-14.2-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:2066dc4cbcc19f32c12a5a0e8cc1b7ac734e5b64ac0a325ff8353451c4b15ef2"}, - {file = "websockets-14.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:ab95d357cd471df61873dadf66dd05dd4709cae001dd6342edafc8dc6382f307"}, - {file = "websockets-14.2-cp313-cp313-win32.whl", hash = "sha256:a9e72fb63e5f3feacdcf5b4ff53199ec8c18d66e325c34ee4c551ca748623bbc"}, - {file = "websockets-14.2-cp313-cp313-win_amd64.whl", hash = "sha256:b439ea828c4ba99bb3176dc8d9b933392a2413c0f6b149fdcba48393f573377f"}, - {file = "websockets-14.2-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:7cd5706caec1686c5d233bc76243ff64b1c0dc445339bd538f30547e787c11fe"}, - {file = "websockets-14.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:ec607328ce95a2f12b595f7ae4c5d71bf502212bddcea528290b35c286932b12"}, - {file = "websockets-14.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:da85651270c6bfb630136423037dd4975199e5d4114cae6d3066641adcc9d1c7"}, - {file = "websockets-14.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c3ecadc7ce90accf39903815697917643f5b7cfb73c96702318a096c00aa71f5"}, - {file = "websockets-14.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1979bee04af6a78608024bad6dfcc0cc930ce819f9e10342a29a05b5320355d0"}, - {file = "websockets-14.2-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2dddacad58e2614a24938a50b85969d56f88e620e3f897b7d80ac0d8a5800258"}, - {file = "websockets-14.2-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:89a71173caaf75fa71a09a5f614f450ba3ec84ad9fca47cb2422a860676716f0"}, - {file = "websockets-14.2-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:6af6a4b26eea4fc06c6818a6b962a952441e0e39548b44773502761ded8cc1d4"}, - {file = "websockets-14.2-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:80c8efa38957f20bba0117b48737993643204645e9ec45512579132508477cfc"}, - {file = "websockets-14.2-cp39-cp39-win32.whl", hash = "sha256:2e20c5f517e2163d76e2729104abc42639c41cf91f7b1839295be43302713661"}, - {file = "websockets-14.2-cp39-cp39-win_amd64.whl", hash = "sha256:b4c8cef610e8d7c70dea92e62b6814a8cd24fbd01d7103cc89308d2bfe1659ef"}, - {file = "websockets-14.2-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:d7d9cafbccba46e768be8a8ad4635fa3eae1ffac4c6e7cb4eb276ba41297ed29"}, - {file = "websockets-14.2-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:c76193c1c044bd1e9b3316dcc34b174bbf9664598791e6fb606d8d29000e070c"}, - {file = "websockets-14.2-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fd475a974d5352390baf865309fe37dec6831aafc3014ffac1eea99e84e83fc2"}, - {file = "websockets-14.2-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2c6c0097a41968b2e2b54ed3424739aab0b762ca92af2379f152c1aef0187e1c"}, - {file = "websockets-14.2-pp310-pypy310_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6d7ff794c8b36bc402f2e07c0b2ceb4a2424147ed4785ff03e2a7af03711d60a"}, - {file = "websockets-14.2-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:dec254fcabc7bd488dab64846f588fc5b6fe0d78f641180030f8ea27b76d72c3"}, - {file = "websockets-14.2-pp39-pypy39_pp73-macosx_10_15_x86_64.whl", hash = "sha256:bbe03eb853e17fd5b15448328b4ec7fb2407d45fb0245036d06a3af251f8e48f"}, - {file = "websockets-14.2-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:a3c4aa3428b904d5404a0ed85f3644d37e2cb25996b7f096d77caeb0e96a3b42"}, - {file = "websockets-14.2-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:577a4cebf1ceaf0b65ffc42c54856214165fb8ceeba3935852fc33f6b0c55e7f"}, - {file = "websockets-14.2-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ad1c1d02357b7665e700eca43a31d52814ad9ad9b89b58118bdabc365454b574"}, - {file = "websockets-14.2-pp39-pypy39_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f390024a47d904613577df83ba700bd189eedc09c57af0a904e5c39624621270"}, - {file = "websockets-14.2-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:3c1426c021c38cf92b453cdf371228d3430acd775edee6bac5a4d577efc72365"}, - {file = "websockets-14.2-py3-none-any.whl", hash = "sha256:7a6ceec4ea84469f15cf15807a747e9efe57e369c384fa86e022b3bea679b79b"}, - {file = "websockets-14.2.tar.gz", hash = "sha256:5059ed9c54945efb321f097084b4c7e52c246f2c869815876a69d1efc4ad6eb5"}, + {file = "websockets-15.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:5e6ee18a53dd5743e6155b8ff7e8e477c25b29b440f87f65be8165275c87fef0"}, + {file = "websockets-15.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ee06405ea2e67366a661ed313e14cf2a86e84142a3462852eb96348f7219cee3"}, + {file = "websockets-15.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8711682a629bbcaf492f5e0af72d378e976ea1d127a2d47584fa1c2c080b436b"}, + {file = "websockets-15.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:94c4a9b01eede952442c088d415861b0cf2053cbd696b863f6d5022d4e4e2453"}, + {file = "websockets-15.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:45535fead66e873f411c1d3cf0d3e175e66f4dd83c4f59d707d5b3e4c56541c4"}, + {file = "websockets-15.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0e389efe46ccb25a1f93d08c7a74e8123a2517f7b7458f043bd7529d1a63ffeb"}, + {file = "websockets-15.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:67a04754d121ea5ca39ddedc3f77071651fb5b0bc6b973c71c515415b44ed9c5"}, + {file = "websockets-15.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:bd66b4865c8b853b8cca7379afb692fc7f52cf898786537dfb5e5e2d64f0a47f"}, + {file = "websockets-15.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:a4cc73a6ae0a6751b76e69cece9d0311f054da9b22df6a12f2c53111735657c8"}, + {file = "websockets-15.0-cp310-cp310-win32.whl", hash = "sha256:89da58e4005e153b03fe8b8794330e3f6a9774ee9e1c3bd5bc52eb098c3b0c4f"}, + {file = "websockets-15.0-cp310-cp310-win_amd64.whl", hash = "sha256:4ff380aabd7a74a42a760ee76c68826a8f417ceb6ea415bd574a035a111fd133"}, + {file = "websockets-15.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:dd24c4d256558429aeeb8d6c24ebad4e982ac52c50bc3670ae8646c181263965"}, + {file = "websockets-15.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:f83eca8cbfd168e424dfa3b3b5c955d6c281e8fc09feb9d870886ff8d03683c7"}, + {file = "websockets-15.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:4095a1f2093002c2208becf6f9a178b336b7572512ee0a1179731acb7788e8ad"}, + {file = "websockets-15.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fb915101dfbf318486364ce85662bb7b020840f68138014972c08331458d41f3"}, + {file = "websockets-15.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:45d464622314973d78f364689d5dbb9144e559f93dca11b11af3f2480b5034e1"}, + {file = "websockets-15.0-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ace960769d60037ca9625b4c578a6f28a14301bd2a1ff13bb00e824ac9f73e55"}, + {file = "websockets-15.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:c7cd4b1015d2f60dfe539ee6c95bc968d5d5fad92ab01bb5501a77393da4f596"}, + {file = "websockets-15.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:4f7290295794b5dec470867c7baa4a14182b9732603fd0caf2a5bf1dc3ccabf3"}, + {file = "websockets-15.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:3abd670ca7ce230d5a624fd3d55e055215d8d9b723adee0a348352f5d8d12ff4"}, + {file = "websockets-15.0-cp311-cp311-win32.whl", hash = "sha256:110a847085246ab8d4d119632145224d6b49e406c64f1bbeed45c6f05097b680"}, + {file = "websockets-15.0-cp311-cp311-win_amd64.whl", hash = "sha256:8d7bbbe2cd6ed80aceef2a14e9f1c1b61683194c216472ed5ff33b700e784e37"}, + {file = "websockets-15.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:cccc18077acd34c8072578394ec79563664b1c205f7a86a62e94fafc7b59001f"}, + {file = "websockets-15.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:d4c22992e24f12de340ca5f824121a5b3e1a37ad4360b4e1aaf15e9d1c42582d"}, + {file = "websockets-15.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:1206432cc6c644f6fc03374b264c5ff805d980311563202ed7fef91a38906276"}, + {file = "websockets-15.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5d3cc75ef3e17490042c47e0523aee1bcc4eacd2482796107fd59dd1100a44bc"}, + {file = "websockets-15.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b89504227a5311610e4be16071465885a0a3d6b0e82e305ef46d9b064ce5fb72"}, + {file = "websockets-15.0-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:56e3efe356416bc67a8e093607315951d76910f03d2b3ad49c4ade9207bf710d"}, + {file = "websockets-15.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:0f2205cdb444a42a7919690238fb5979a05439b9dbb73dd47c863d39640d85ab"}, + {file = "websockets-15.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:aea01f40995fa0945c020228ab919b8dfc93fc8a9f2d3d705ab5b793f32d9e99"}, + {file = "websockets-15.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:a9f8e33747b1332db11cf7fcf4a9512bef9748cb5eb4d3f7fbc8c30d75dc6ffc"}, + {file = "websockets-15.0-cp312-cp312-win32.whl", hash = "sha256:32e02a2d83f4954aa8c17e03fe8ec6962432c39aca4be7e8ee346b05a3476904"}, + {file = "websockets-15.0-cp312-cp312-win_amd64.whl", hash = "sha256:ffc02b159b65c05f2ed9ec176b715b66918a674bd4daed48a9a7a590dd4be1aa"}, + {file = "websockets-15.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:d2244d8ab24374bed366f9ff206e2619345f9cd7fe79aad5225f53faac28b6b1"}, + {file = "websockets-15.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:3a302241fbe825a3e4fe07666a2ab513edfdc6d43ce24b79691b45115273b5e7"}, + {file = "websockets-15.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:10552fed076757a70ba2c18edcbc601c7637b30cdfe8c24b65171e824c7d6081"}, + {file = "websockets-15.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c53f97032b87a406044a1c33d1e9290cc38b117a8062e8a8b285175d7e2f99c9"}, + {file = "websockets-15.0-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1caf951110ca757b8ad9c4974f5cac7b8413004d2f29707e4d03a65d54cedf2b"}, + {file = "websockets-15.0-cp313-cp313-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8bf1ab71f9f23b0a1d52ec1682a3907e0c208c12fef9c3e99d2b80166b17905f"}, + {file = "websockets-15.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:bfcd3acc1a81f106abac6afd42327d2cf1e77ec905ae11dc1d9142a006a496b6"}, + {file = "websockets-15.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:c8c5c8e1bac05ef3c23722e591ef4f688f528235e2480f157a9cfe0a19081375"}, + {file = "websockets-15.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:86bfb52a9cfbcc09aba2b71388b0a20ea5c52b6517c0b2e316222435a8cdab72"}, + {file = "websockets-15.0-cp313-cp313-win32.whl", hash = "sha256:26ba70fed190708551c19a360f9d7eca8e8c0f615d19a574292b7229e0ae324c"}, + {file = "websockets-15.0-cp313-cp313-win_amd64.whl", hash = "sha256:ae721bcc8e69846af00b7a77a220614d9b2ec57d25017a6bbde3a99473e41ce8"}, + {file = "websockets-15.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:c348abc5924caa02a62896300e32ea80a81521f91d6db2e853e6b1994017c9f6"}, + {file = "websockets-15.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:5294fcb410ed0a45d5d1cdedc4e51a60aab5b2b3193999028ea94afc2f554b05"}, + {file = "websockets-15.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:c24ba103ecf45861e2e1f933d40b2d93f5d52d8228870c3e7bf1299cd1cb8ff1"}, + {file = "websockets-15.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cc8821a03bcfb36e4e4705316f6b66af28450357af8a575dc8f4b09bf02a3dee"}, + {file = "websockets-15.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ffc5ae23ada6515f31604f700009e2df90b091b67d463a8401c1d8a37f76c1d7"}, + {file = "websockets-15.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7ac67b542505186b3bbdaffbc303292e1ee9c8729e5d5df243c1f20f4bb9057e"}, + {file = "websockets-15.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:c86dc2068f1c5ca2065aca34f257bbf4f78caf566eb230f692ad347da191f0a1"}, + {file = "websockets-15.0-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:30cff3ef329682b6182c01c568f551481774c476722020b8f7d0daacbed07a17"}, + {file = "websockets-15.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:98dcf978d4c6048965d1762abd534c9d53bae981a035bfe486690ba11f49bbbb"}, + {file = "websockets-15.0-cp39-cp39-win32.whl", hash = "sha256:37d66646f929ae7c22c79bc73ec4074d6db45e6384500ee3e0d476daf55482a9"}, + {file = "websockets-15.0-cp39-cp39-win_amd64.whl", hash = "sha256:24d5333a9b2343330f0f4eb88546e2c32a7f5c280f8dd7d3cc079beb0901781b"}, + {file = "websockets-15.0-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:b499caef4bca9cbd0bd23cd3386f5113ee7378094a3cb613a2fa543260fe9506"}, + {file = "websockets-15.0-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:17f2854c6bd9ee008c4b270f7010fe2da6c16eac5724a175e75010aacd905b31"}, + {file = "websockets-15.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:89f72524033abbfde880ad338fd3c2c16e31ae232323ebdfbc745cbb1b3dcc03"}, + {file = "websockets-15.0-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1657a9eecb29d7838e3b415458cc494e6d1b194f7ac73a34aa55c6fb6c72d1f3"}, + {file = "websockets-15.0-pp310-pypy310_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e413352a921f5ad5d66f9e2869b977e88d5103fc528b6deb8423028a2befd842"}, + {file = "websockets-15.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:8561c48b0090993e3b2a54db480cab1d23eb2c5735067213bb90f402806339f5"}, + {file = "websockets-15.0-pp39-pypy39_pp73-macosx_10_15_x86_64.whl", hash = "sha256:190bc6ef8690cd88232a038d1b15714c258f79653abad62f7048249b09438af3"}, + {file = "websockets-15.0-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:327adab7671f3726b0ba69be9e865bba23b37a605b585e65895c428f6e47e766"}, + {file = "websockets-15.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2bd8ef197c87afe0a9009f7a28b5dc613bfc585d329f80b7af404e766aa9e8c7"}, + {file = "websockets-15.0-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:789c43bf4a10cd067c24c321238e800b8b2716c863ddb2294d2fed886fa5a689"}, + {file = "websockets-15.0-pp39-pypy39_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7394c0b7d460569c9285fa089a429f58465db930012566c03046f9e3ab0ed181"}, + {file = "websockets-15.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:2ea4f210422b912ebe58ef0ad33088bc8e5c5ff9655a8822500690abc3b1232d"}, + {file = "websockets-15.0-py3-none-any.whl", hash = "sha256:51ffd53c53c4442415b613497a34ba0aa7b99ac07f1e4a62db5dcd640ae6c3c3"}, + {file = "websockets-15.0.tar.gz", hash = "sha256:ca36151289a15b39d8d683fd8b7abbe26fc50be311066c5f8dcf3cb8cee107ab"}, ] [[package]] @@ -3100,4 +3184,4 @@ test = ["pytest (>=8.1,<9.0)", "pytest-rerunfailures (>=14.0,<15.0)"] [metadata] lock-version = "2.1" python-versions = ">=3.10,<3.13" -content-hash = "9ca114395e73af8982abbccc25b385bbca62e50ba7cca8239e52e5c1227cb4b0" +content-hash = "2d0a953383901fe12e97f6f56a76a9d8008788695425792eedbf739a18585188" diff --git a/pyproject.toml b/pyproject.toml index f1be273..3c64eae 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api" [project] name = "auto-archiver" -version = "0.13.0" +version = "0.13.4" description = "Automatically archive links to videos, images, and social media content from Google Sheets (and more)." requires-python = ">=3.10,<3.13" @@ -22,7 +22,6 @@ classifiers = [ ] dependencies = [ - "oscrypto @ git+https://github.com/wbond/oscrypto.git@d5f3437ed24257895ae1edd9e503cfb352e635a8", "gspread (>=0.0.0)", "beautifulsoup4 (>=0.0.0)", "bs4 (>=0.0.0)", @@ -64,6 +63,7 @@ dependencies = [ pytest = "^8.3.4" autopep8 = "^2.3.1" pytest-loguru = "^0.4.0" +pytest-mock = "^3.14.0" [tool.poetry.group.docs.dependencies] sphinx = "^8.1.3" @@ -72,7 +72,8 @@ sphinxcontrib-mermaid = "^1.0.0" sphinx-autobuild = "^2024.10.3" sphinx-copybutton = "^0.5.2" myst-parser = "^4.0.0" -furo = "^2024.8.6" +sphinx-book-theme = "^1.1.3" +linkify-it-py = "^2.0.3" [project.scripts] diff --git a/src/auto_archiver/__main__.py b/src/auto_archiver/__main__.py index 0023a59..f901d21 100644 --- a/src/auto_archiver/__main__.py +++ b/src/auto_archiver/__main__.py @@ -3,7 +3,7 @@ from auto_archiver.core.orchestrator import ArchivingOrchestrator import sys def main(): - ArchivingOrchestrator().run(sys.argv[1:]) + for _ in ArchivingOrchestrator()._command_line_run(sys.argv[1:]): pass if __name__ == "__main__": main() diff --git a/src/auto_archiver/core/__init__.py b/src/auto_archiver/core/__init__.py index ae4c41c..78d9a3d 100644 --- a/src/auto_archiver/core/__init__.py +++ b/src/auto_archiver/core/__init__.py @@ -3,7 +3,7 @@ """ from .metadata import Metadata from .media import Media -from .module import BaseModule +from .base_module import BaseModule # cannot import ArchivingOrchestrator/Config to avoid circular dep # from .orchestrator import ArchivingOrchestrator diff --git a/src/auto_archiver/core/base_module.py b/src/auto_archiver/core/base_module.py index ece4719..50ea3ff 100644 --- a/src/auto_archiver/core/base_module.py +++ b/src/auto_archiver/core/base_module.py @@ -1,13 +1,18 @@ -from urllib.parse import urlparse -from typing import Mapping, Any +from __future__ import annotations + +from typing import Mapping, Any, Type, TYPE_CHECKING from abc import ABC from copy import deepcopy, copy from tempfile import TemporaryDirectory from auto_archiver.utils import url as UrlUtil +from auto_archiver.core.consts import MODULE_TYPES as CONF_MODULE_TYPES from loguru import logger +if TYPE_CHECKING: + from .module import ModuleFactory + class BaseModule(ABC): """ @@ -17,41 +22,24 @@ class BaseModule(ABC): however modules can have a .setup() method to run any setup code (e.g. logging in to a site, spinning up a browser etc.) - See BaseModule.MODULE_TYPES for the types of modules you can create, noting that + See consts.MODULE_TYPES for the types of modules you can create, noting that a subclass can be of multiple types. For example, a module that extracts data from a website and stores it in a database would be both an 'extractor' and a 'database' module. Each module is a python package, and should have a __manifest__.py file in the same directory as the module file. The __manifest__.py specifies the module information - like name, author, version, dependencies etc. See BaseModule._DEFAULT_MANIFEST for the + like name, author, version, dependencies etc. See DEFAULT_MANIFEST for the default manifest structure. """ - MODULE_TYPES = [ - 'feeder', - 'extractor', - 'enricher', - 'database', - 'storage', - 'formatter' - ] - - _DEFAULT_MANIFEST = { - 'name': '', # the display name of the module - 'author': 'Bellingcat', # creator of the module, leave this as Bellingcat or set your own name! - 'type': [], # the type of the module, can be one or more of BaseModule.MODULE_TYPES - 'requires_setup': True, # whether or not this module requires additional setup such as setting API Keys or installing additional softare - 'description': '', # a description of the module - 'dependencies': {}, # external dependencies, e.g. python packages or binaries, in dictionary format - 'entry_point': '', # the entry point for the module, in the format 'module_name::ClassName'. This can be left blank to use the default entry point of module_name::ModuleName - 'version': '1.0', # the version of the module - 'configs': {} # any configuration options this module has, these will be exposed to the user in the config file or via the command line -} + MODULE_TYPES = CONF_MODULE_TYPES + # NOTE: these here are declard as class variables, but they are overridden by the instance variables in the __init__ method config: Mapping[str, Any] authentication: Mapping[str, Mapping[str, str]] name: str + module_factory: ModuleFactory # this is set by the orchestrator prior to archiving tmp_dir: TemporaryDirectory = None @@ -63,12 +51,6 @@ class BaseModule(ABC): def config_setup(self, config: dict): authentication = config.get('authentication', {}) - # extract out concatenated sites - for key, val in copy(authentication).items(): - if "," in key: - for site in key.split(","): - authentication[site] = val - del authentication[key] # this is important. Each instance is given its own deepcopied config, so modules cannot # change values to affect other modules @@ -89,16 +71,21 @@ class BaseModule(ABC): Returns the authentication information for a given site. This is used to authenticate with a site before extracting data. The site should be the domain of the site, e.g. 'twitter.com' - extract_cookies: bool - whether or not to extract cookies from the given browser and return the - cookie jar (disabling can speed up) processing if you don't actually need the cookies jar + :param site: the domain of the site to get authentication information for + :param extract_cookies: whether or not to extract cookies from the given browser/file and return the cookie jar (disabling can speed up processing if you don't actually need the cookies jar). - Currently, the dict can have keys of the following types: - - username: str - the username to use for login - - password: str - the password to use for login - - api_key: str - the API key to use for login - - api_secret: str - the API secret to use for login - - cookie: str - a cookie string to use for login (specific to this site) - - cookies_jar: YoutubeDLCookieJar | http.cookiejar.MozillaCookieJar - a cookie jar compatible with requests (e.g. `requests.get(cookies=cookie_jar)`) + :returns: authdict dict of login information for the given site + + **Global options:**\n + * cookies_from_browser: str - the name of the browser to extract cookies from (e.g. 'chrome', 'firefox' - uses ytdlp under the hood to extract\n + * cookies_file: str - the path to a cookies file to use for login\n + + **Currently, the sites dict can have keys of the following types:**\n + * username: str - the username to use for login\n + * password: str - the password to use for login\n + * api_key: str - the API key to use for login\n + * api_secret: str - the API secret to use for login\n + * cookie: str - a cookie string to use for login (specific to this site)\n """ # TODO: think about if/how we can deal with sites that have multiple domains (main one is x.com/twitter.com) # for now the user must enter them both, like "x.com,twitter.com" in their config. Maybe we just hard-code? diff --git a/src/auto_archiver/core/config.py b/src/auto_archiver/core/config.py index 9bb080f..c3bc706 100644 --- a/src/auto_archiver/core/config.py +++ b/src/auto_archiver/core/config.py @@ -11,7 +11,7 @@ from ruamel.yaml import YAML, CommentedMap, add_representer from loguru import logger from copy import deepcopy -from .module import BaseModule +from auto_archiver.core.consts import MODULE_TYPES from typing import Any, List, Type, Tuple @@ -21,7 +21,7 @@ EMPTY_CONFIG = _yaml.load(""" # Auto Archiver Configuration # Steps are the modules that will be run in the order they are defined -steps:""" + "".join([f"\n {module}s: []" for module in BaseModule.MODULE_TYPES]) + \ +steps:""" + "".join([f"\n {module}s: []" for module in MODULE_TYPES]) + \ """ # Global configuration @@ -48,6 +48,7 @@ authentication: {} logging: level: INFO + """) # note: 'logging' is explicitly added above in order to better format the config file @@ -128,6 +129,11 @@ def merge_dicts(dotdict: dict, yaml_dict: CommentedMap) -> CommentedMap: yaml_subdict[key] = value continue + if key == 'steps': + for module_type, modules in value.items(): + # overwrite the 'steps' from the config file with the ones from the CLI + yaml_subdict[key][module_type] = modules + if is_dict_type(value): update_dict(value, yaml_subdict[key]) elif is_list_type(value): @@ -136,7 +142,6 @@ def merge_dicts(dotdict: dict, yaml_dict: CommentedMap) -> CommentedMap: yaml_subdict[key] = value update_dict(from_dot_notation(dotdict), yaml_dict) - return yaml_dict def read_yaml(yaml_filename: str) -> CommentedMap: @@ -158,6 +163,11 @@ def read_yaml(yaml_filename: str) -> CommentedMap: def store_yaml(config: CommentedMap, yaml_filename: str) -> None: config_to_save = deepcopy(config) + auth_dict = config_to_save.get("authentication", {}) + if auth_dict and auth_dict.get('load_from_file'): + # remove all other values from the config, don't want to store it in the config file + auth_dict = {"load_from_file": auth_dict["load_from_file"]} + config_to_save.pop('urls', None) with open(yaml_filename, "w", encoding="utf-8") as outf: _yaml.dump(config_to_save, outf) \ No newline at end of file diff --git a/src/auto_archiver/core/consts.py b/src/auto_archiver/core/consts.py new file mode 100644 index 0000000..0fb81fb --- /dev/null +++ b/src/auto_archiver/core/consts.py @@ -0,0 +1,23 @@ + +MODULE_TYPES = [ + 'feeder', + 'extractor', + 'enricher', + 'database', + 'storage', + 'formatter' +] + +MANIFEST_FILE = "__manifest__.py" + +DEFAULT_MANIFEST = { + 'name': '', # the display name of the module + 'author': 'Bellingcat', # creator of the module, leave this as Bellingcat or set your own name! + 'type': [], # the type of the module, can be one or more of MODULE_TYPES + 'requires_setup': True, # whether or not this module requires additional setup such as setting API Keys or installing additional softare + 'description': '', # a description of the module + 'dependencies': {}, # external dependencies, e.g. python packages or binaries, in dictionary format + 'entry_point': '', # the entry point for the module, in the format 'module_name::ClassName'. This can be left blank to use the default entry point of module_name::ModuleName + 'version': '1.0', # the version of the module + 'configs': {} # any configuration options this module has, these will be exposed to the user in the config file or via the command line +} \ No newline at end of file diff --git a/src/auto_archiver/core/database.py b/src/auto_archiver/core/database.py index 0eb5d81..a6e76e5 100644 --- a/src/auto_archiver/core/database.py +++ b/src/auto_archiver/core/database.py @@ -1,3 +1,8 @@ +""" +Database module for the auto-archiver that defines the interface for implementing database modules +in the media archiving framework. +""" + from __future__ import annotations from abc import abstractmethod from typing import Union @@ -5,6 +10,11 @@ from typing import Union from auto_archiver.core import Metadata, BaseModule class Database(BaseModule): + """ + Base class for implementing database modules in the media archiving framework. + + Subclasses must implement the `fetch` and `done` methods to define platform-specific behavior. + """ def started(self, item: Metadata) -> None: """signals the DB that the given item archival has started""" diff --git a/src/auto_archiver/core/enricher.py b/src/auto_archiver/core/enricher.py index 0e50fa9..45e75d7 100644 --- a/src/auto_archiver/core/enricher.py +++ b/src/auto_archiver/core/enricher.py @@ -1,5 +1,5 @@ """ -Enrichers are modular components that enhance archived content by adding +Base module for Enrichers – modular components that enhance archived content by adding context, metadata, or additional processing. These add additional information to the context, such as screenshots, hashes, and metadata. @@ -13,7 +13,16 @@ from abc import abstractmethod from auto_archiver.core import Metadata, BaseModule class Enricher(BaseModule): - """Base classes and utilities for enrichers in the Auto-Archiver system.""" + """Base classes and utilities for enrichers in the Auto-Archiver system. + + Enricher modules must implement the `enrich` method to define their behavior. + """ @abstractmethod - def enrich(self, to_enrich: Metadata) -> None: pass + def enrich(self, to_enrich: Metadata) -> None: + """ + Enriches a Metadata object with additional information or context. + + Takes the metadata object to enrich as an argument and modifies it in place, returning None. + """ + pass diff --git a/src/auto_archiver/core/extractor.py b/src/auto_archiver/core/extractor.py index 794c06c..484a09d 100644 --- a/src/auto_archiver/core/extractor.py +++ b/src/auto_archiver/core/extractor.py @@ -29,14 +29,24 @@ class Extractor(BaseModule): valid_url: re.Pattern = None def cleanup(self) -> None: - # called when extractors are done, or upon errors, cleanup any resources + """ + Called when extractors are done, or upon errors, cleanup any resources + """ pass def sanitize_url(self, url: str) -> str: - # used to clean unnecessary URL parameters OR unfurl redirect links + """ + Used to clean unnecessary URL parameters OR unfurl redirect links + """ return url def match_link(self, url: str) -> re.Match: + """ + Returns a match object if the given URL matches the valid_url pattern or False/None if not. + + Normally used in the `suitable` method to check if the URL is supported by this extractor. + + """ return self.valid_url.match(url) def suitable(self, url: str) -> bool: @@ -80,8 +90,8 @@ class Extractor(BaseModule): d.raise_for_status() # get mimetype from the response headers - if not Path(to_filename).suffix: - content_type = d.headers.get('Content-Type') + if not mimetypes.guess_type(to_filename)[0]: + content_type = d.headers.get('Content-Type') or self._guess_file_type(url) extension = mimetypes.guess_extension(content_type) if extension: to_filename += extension diff --git a/src/auto_archiver/core/feeder.py b/src/auto_archiver/core/feeder.py index 352cfd9..e8302e6 100644 --- a/src/auto_archiver/core/feeder.py +++ b/src/auto_archiver/core/feeder.py @@ -1,3 +1,7 @@ +""" +The feeder base module defines the interface for implementing feeders in the media archiving framework. +""" + from __future__ import annotations from abc import abstractmethod from auto_archiver.core import Metadata @@ -5,5 +9,17 @@ from auto_archiver.core import BaseModule class Feeder(BaseModule): + """ + Base class for implementing feeders in the media archiving framework. + + Subclasses must implement the `__iter__` method to define platform-specific behavior. + """ + @abstractmethod - def __iter__(self) -> Metadata: return None \ No newline at end of file + def __iter__(self) -> Metadata: + """ + Returns an iterator (use `yield`) over the items to be archived. + + These should be instances of Metadata, typically created with Metadata().set_url(url). + """ + return None \ No newline at end of file diff --git a/src/auto_archiver/core/formatter.py b/src/auto_archiver/core/formatter.py index cf27cb3..3bfc250 100644 --- a/src/auto_archiver/core/formatter.py +++ b/src/auto_archiver/core/formatter.py @@ -1,9 +1,24 @@ +""" +Base module for formatters – modular components that format metadata into media objects for storage. + +The most commonly used formatter is the HTML formatter, which takes metadata and formats it into an HTML file for storage. +""" + from __future__ import annotations from abc import abstractmethod from auto_archiver.core import Metadata, Media, BaseModule class Formatter(BaseModule): + """ + Base class for implementing formatters in the media archiving framework. + + Subclasses must implement the `format` method to define their behavior. + """ @abstractmethod - def format(self, item: Metadata) -> Media: return None \ No newline at end of file + def format(self, item: Metadata) -> Media: + """ + Formats a Metadata object into a user-viewable format (e.g. HTML) and stores it if needed. + """ + return None \ No newline at end of file diff --git a/src/auto_archiver/core/module.py b/src/auto_archiver/core/module.py index c81e26a..9556621 100644 --- a/src/auto_archiver/core/module.py +++ b/src/auto_archiver/core/module.py @@ -6,7 +6,7 @@ by handling user configuration, validating the steps properties, and implementin from __future__ import annotations from dataclasses import dataclass -from typing import List +from typing import List, TYPE_CHECKING import shutil import ast import copy @@ -16,99 +16,113 @@ import os from os.path import join from loguru import logger import auto_archiver -from .base_module import BaseModule +from auto_archiver.core.consts import DEFAULT_MANIFEST, MANIFEST_FILE -_LAZY_LOADED_MODULES = {} - -MANIFEST_FILE = "__manifest__.py" +if TYPE_CHECKING: + from .base_module import BaseModule -def setup_paths(paths: list[str]) -> None: - """ - Sets up the paths for the modules to be loaded from - - This is necessary for the modules to be imported correctly - - """ - for path in paths: - # check path exists, if it doesn't, log a warning - if not os.path.exists(path): - logger.warning(f"Path '{path}' does not exist. Skipping...") - continue +HAS_SETUP_PATHS = False - # see odoo/module/module.py -> initialize_sys_path - if path not in auto_archiver.modules.__path__: - auto_archiver.modules.__path__.append(path) +class ModuleFactory: - # sort based on the length of the path, so that the longest path is last in the list - auto_archiver.modules.__path__ = sorted(auto_archiver.modules.__path__, key=len, reverse=True) + def __init__(self): + self._lazy_modules = {} -def get_module(module_name: str, config: dict) -> BaseModule: - """ - Gets and sets up a module using the provided config - - This will actually load and instantiate the module, and load all its dependencies (i.e. not lazy) - - """ - return get_module_lazy(module_name).load(config) + def setup_paths(self, paths: list[str]) -> None: + """ + Sets up the paths for the modules to be loaded from + + This is necessary for the modules to be imported correctly + + """ + global HAS_SETUP_PATHS -def get_module_lazy(module_name: str, suppress_warnings: bool = False) -> LazyBaseModule: - """ - Lazily loads a module, returning a LazyBaseModule - - This has all the information about the module, but does not load the module itself or its dependencies - - To load an actual module, call .setup() on a lazy module - - """ - if module_name in _LAZY_LOADED_MODULES: - return _LAZY_LOADED_MODULES[module_name] - - available = available_modules(limit_to_modules=[module_name], suppress_warnings=suppress_warnings) - if not available: - raise IndexError(f"Module '{module_name}' not found. Are you sure it's installed/exists?") - return available[0] - -def available_modules(with_manifest: bool=False, limit_to_modules: List[str]= [], suppress_warnings: bool = False) -> List[LazyBaseModule]: - - # search through all valid 'modules' paths. Default is 'modules' in the current directory - - # see odoo/modules/module.py -> get_modules - def is_really_module(module_path): - if os.path.isfile(join(module_path, MANIFEST_FILE)): - return True - - all_modules = [] - - for module_folder in auto_archiver.modules.__path__: - # walk through each module in module_folder and check if it has a valid manifest - try: - possible_modules = os.listdir(module_folder) - except FileNotFoundError: - logger.warning(f"Module folder {module_folder} does not exist") - continue - - for possible_module in possible_modules: - if limit_to_modules and possible_module not in limit_to_modules: + for path in paths: + # check path exists, if it doesn't, log a warning + if not os.path.exists(path): + logger.warning(f"Path '{path}' does not exist. Skipping...") continue - possible_module_path = join(module_folder, possible_module) - if not is_really_module(possible_module_path): + # see odoo/module/module.py -> initialize_sys_path + if path not in auto_archiver.modules.__path__: + if HAS_SETUP_PATHS == True: + logger.warning(f"You are attempting to re-initialise the module paths with: '{path}' for a 2nd time. \ + This could lead to unexpected behaviour. It is recommended to only use a single modules path. \ + If you wish to load modules from different paths then load a 2nd python interpreter (e.g. using multiprocessing).") + auto_archiver.modules.__path__.append(path) + + # sort based on the length of the path, so that the longest path is last in the list + auto_archiver.modules.__path__ = sorted(auto_archiver.modules.__path__, key=len, reverse=True) + + HAS_SETUP_PATHS = True + + def get_module(self, module_name: str, config: dict) -> BaseModule: + """ + Gets and sets up a module using the provided config + + This will actually load and instantiate the module, and load all its dependencies (i.e. not lazy) + + """ + return self.get_module_lazy(module_name).load(config) + + def get_module_lazy(self, module_name: str, suppress_warnings: bool = False) -> LazyBaseModule: + """ + Lazily loads a module, returning a LazyBaseModule + + This has all the information about the module, but does not load the module itself or its dependencies + + To load an actual module, call .setup() on a lazy module + + """ + if module_name in self._lazy_modules: + return self._lazy_modules[module_name] + + available = self.available_modules(limit_to_modules=[module_name], suppress_warnings=suppress_warnings) + if not available: + raise IndexError(f"Module '{module_name}' not found. Are you sure it's installed/exists?") + return available[0] + + def available_modules(self, limit_to_modules: List[str]= [], suppress_warnings: bool = False) -> List[LazyBaseModule]: + + # search through all valid 'modules' paths. Default is 'modules' in the current directory + + # see odoo/modules/module.py -> get_modules + def is_really_module(module_path): + if os.path.isfile(join(module_path, MANIFEST_FILE)): + return True + + all_modules = [] + + for module_folder in auto_archiver.modules.__path__: + # walk through each module in module_folder and check if it has a valid manifest + try: + possible_modules = os.listdir(module_folder) + except FileNotFoundError: + logger.warning(f"Module folder {module_folder} does not exist") continue - if _LAZY_LOADED_MODULES.get(possible_module): - continue - lazy_module = LazyBaseModule(possible_module, possible_module_path) - _LAZY_LOADED_MODULES[possible_module] = lazy_module + for possible_module in possible_modules: + if limit_to_modules and possible_module not in limit_to_modules: + continue - all_modules.append(lazy_module) - - if not suppress_warnings: - for module in limit_to_modules: - if not any(module == m.name for m in all_modules): - logger.warning(f"Module '{module}' not found. Are you sure it's installed?") + possible_module_path = join(module_folder, possible_module) + if not is_really_module(possible_module_path): + continue + if self._lazy_modules.get(possible_module): + continue + lazy_module = LazyBaseModule(possible_module, possible_module_path, factory=self) - return all_modules + self._lazy_modules[possible_module] = lazy_module + + all_modules.append(lazy_module) + + if not suppress_warnings: + for module in limit_to_modules: + if not any(module == m.name for m in all_modules): + logger.warning(f"Module '{module}' not found. Are you sure it's installed?") + + return all_modules @dataclass class LazyBaseModule: @@ -123,14 +137,16 @@ class LazyBaseModule: type: list description: str path: str + module_factory: ModuleFactory _manifest: dict = None _instance: BaseModule = None _entry_point: str = None - def __init__(self, module_name, path): + def __init__(self, module_name, path, factory: ModuleFactory): self.name = module_name self.path = path + self.module_factory = factory @property def entry_point(self): @@ -161,7 +177,7 @@ class LazyBaseModule: return self._manifest # print(f"Loading manifest for module {module_path}") # load the manifest file - manifest = copy.deepcopy(BaseModule._DEFAULT_MANIFEST) + manifest = copy.deepcopy(DEFAULT_MANIFEST) with open(join(self.path, MANIFEST_FILE)) as f: try: @@ -189,13 +205,14 @@ class LazyBaseModule: # clear out any empty strings that a user may have erroneously added continue if not check(dep): - logger.error(f"Module '{self.name}' requires external dependency '{dep}' which is not available/setup. Have you installed the required dependencies for the '{self.name}' module? See the README for more information.") + logger.error(f"Module '{self.name}' requires external dependency '{dep}' which is not available/setup. \ + Have you installed the required dependencies for the '{self.name}' module? See the README for more information.") exit(1) def check_python_dep(dep): # first check if it's a module: try: - m = get_module_lazy(dep, suppress_warnings=True) + m = self.module_factory.get_module_lazy(dep, suppress_warnings=True) try: # we must now load this module and set it up with the config m.load(config) @@ -230,19 +247,21 @@ class LazyBaseModule: __import__(f'{qualname}.{file_name}', fromlist=[self.entry_point]) # finally, get the class instance instance: BaseModule = getattr(sys.modules[sub_qualname], class_name)() - if not getattr(instance, 'name', None): - instance.name = self.name - - if not getattr(instance, 'display_name', None): - instance.display_name = self.display_name - - self._instance = instance + # set the name, display name and module factory + instance.name = self.name + instance.display_name = self.display_name + instance.module_factory = self.module_factory + # merge the default config with the user config default_config = dict((k, v['default']) for k, v in self.configs.items() if v.get('default')) + config[self.name] = default_config | config.get(self.name, {}) instance.config_setup(config) instance.setup() + + # save the instance for future easy loading + self._instance = instance return instance def __repr__(self): diff --git a/src/auto_archiver/core/orchestrator.py b/src/auto_archiver/core/orchestrator.py index bb5f9e3..10d9215 100644 --- a/src/auto_archiver/core/orchestrator.py +++ b/src/auto_archiver/core/orchestrator.py @@ -5,9 +5,10 @@ """ from __future__ import annotations -from typing import Generator, Union, List, Type +from typing import Generator, Union, List, Type, TYPE_CHECKING from urllib.parse import urlparse from ipaddress import ip_address +from copy import copy import argparse import os import sys @@ -21,15 +22,18 @@ from rich_argparse import RichHelpFormatter from .metadata import Metadata, Media from auto_archiver.version import __version__ from .config import _yaml, read_yaml, store_yaml, to_dot_notation, merge_dicts, EMPTY_CONFIG, DefaultValidatingParser -from .module import available_modules, LazyBaseModule, get_module, setup_paths +from .module import ModuleFactory, LazyBaseModule from . import validators, Feeder, Extractor, Database, Storage, Formatter, Enricher -from .module import BaseModule - +from .consts import MODULE_TYPES from loguru import logger +if TYPE_CHECKING: + from .base_module import BaseModule + from .module import LazyBaseModule DEFAULT_CONFIG_FILE = "orchestration.yaml" + class JsonParseAction(argparse.Action): def __call__(self, parser, namespace, values, option_string=None): try: @@ -42,51 +46,85 @@ class AuthenticationJsonParseAction(JsonParseAction): def __call__(self, parser, namespace, values, option_string=None): super().__call__(parser, namespace, values, option_string) auth_dict = getattr(namespace, self.dest) - if isinstance(auth_dict, str): - # if it's a string + + def load_from_file(path): try: - with open(auth_dict, 'r') as f: + with open(path, 'r') as f: try: auth_dict = json.load(f) except json.JSONDecodeError: + f.seek(0) # maybe it's yaml, try that auth_dict = _yaml.load(f) + if auth_dict.get('authentication'): + auth_dict = auth_dict['authentication'] + auth_dict['load_from_file'] = path + return auth_dict except: - pass + return None + if isinstance(auth_dict, dict) and auth_dict.get('from_file'): + auth_dict = load_from_file(auth_dict['from_file']) + elif isinstance(auth_dict, str): + # if it's a string + auth_dict = load_from_file(auth_dict) + if not isinstance(auth_dict, dict): raise argparse.ArgumentTypeError("Authentication must be a dictionary of site names and their authentication methods") - for site, auth in auth_dict.items(): - if not isinstance(site, str) or not isinstance(auth, dict): - raise argparse.ArgumentTypeError("Authentication must be a dictionary of site names and their authentication methods") + global_options = ['cookies_from_browser', 'cookies_file', 'load_from_file'] + for key, auth in auth_dict.items(): + if key in global_options: + continue + if not isinstance(key, str) or not isinstance(auth, dict): + raise argparse.ArgumentTypeError(f"Authentication must be a dictionary of site names and their authentication methods. Valid global configs are {global_options}") + + # extract out concatenated sites + for key, val in copy(auth_dict).items(): + if "," in key: + for site in key.split(","): + auth_dict[site] = val + del auth_dict[key] + setattr(namespace, self.dest, auth_dict) + + class UniqueAppendAction(argparse.Action): def __call__(self, parser, namespace, values, option_string=None): - if not hasattr(namespace, self.dest): - setattr(namespace, self.dest, []) for value in values: if value not in getattr(namespace, self.dest): getattr(namespace, self.dest).append(value) + class ArchivingOrchestrator: + # instance variables + module_factory: ModuleFactory + setup_finished: bool + logger_id: int + + # instance variables, used for convenience to access modules by step feeders: List[Type[Feeder]] extractors: List[Type[Extractor]] enrichers: List[Type[Enricher]] databases: List[Type[Database]] storages: List[Type[Storage]] formatters: List[Type[Formatter]] - + + def __init__(self): + self.module_factory = ModuleFactory() + self.setup_finished = False + self.logger_id = None + def setup_basic_parser(self): parser = argparse.ArgumentParser( - prog="auto-archiver", - add_help=False, - description=""" + prog="auto-archiver", + add_help=False, + description=""" Auto Archiver is a CLI tool to archive media/metadata from online URLs; it can read URLs from many sources (Google Sheets, Command Line, ...); and write results to many destinations too (CSV, Google Sheets, MongoDB, ...)! """, - epilog="Check the code at https://github.com/bellingcat/auto-archiver", - formatter_class=RichHelpFormatter, + epilog="Check the code at https://github.com/bellingcat/auto-archiver", + formatter_class=RichHelpFormatter, ) parser.add_argument('--help', '-h', action='store_true', dest='help', help='show a full help message and exit') parser.add_argument('--version', action='version', version=__version__) @@ -100,101 +138,115 @@ class ArchivingOrchestrator: return parser def setup_complete_parser(self, basic_config: dict, yaml_config: dict, unused_args: list[str]) -> None: + + + # modules parser to get the overridden 'steps' values + modules_parser = argparse.ArgumentParser( + add_help=False, + ) + self.add_modules_args(modules_parser) + cli_modules, unused_args = modules_parser.parse_known_args(unused_args) + for module_type in MODULE_TYPES: + yaml_config['steps'][f"{module_type}s"] = getattr(cli_modules, f"{module_type}s", []) or yaml_config['steps'].get(f"{module_type}s", []) + parser = DefaultValidatingParser( add_help=False, ) self.add_additional_args(parser) + # merge command line module args (--feeders, --enrichers etc.) and add them to the config + # check what mode we're in # if we have a config file, use that to decide which modules to load # if simple, we'll load just the modules that has requires_setup = False # if full, we'll load all modules # TODO: BUG** - basic_config won't have steps in it, since these args aren't added to 'basic_parser' # but should we add them? Or should we just add them to the 'complete' parser? + if yaml_config != EMPTY_CONFIG: # only load the modules enabled in config # TODO: if some steps are empty (e.g. 'feeders' is empty), should we default to the 'simple' ones? Or only if they are ALL empty? enabled_modules = [] # first loads the modules from the config file, then from the command line - for config in [yaml_config['steps'], basic_config.__dict__]: - for module_type in BaseModule.MODULE_TYPES: - enabled_modules.extend(config.get(f"{module_type}s", [])) + for module_type in MODULE_TYPES: + enabled_modules.extend(yaml_config['steps'].get(f"{module_type}s", [])) # clear out duplicates, but keep the order enabled_modules = list(dict.fromkeys(enabled_modules)) - avail_modules = available_modules(with_manifest=True, limit_to_modules=enabled_modules, suppress_warnings=True) - self.add_module_args(avail_modules, parser) + avail_modules = self.module_factory.available_modules(limit_to_modules=enabled_modules, suppress_warnings=True) + self.add_individual_module_args(avail_modules, parser) elif basic_config.mode == 'simple': - simple_modules = [module for module in available_modules(with_manifest=True) if not module.requires_setup] - self.add_module_args(simple_modules, parser) + simple_modules = [module for module in self.module_factory.available_modules() if not module.requires_setup] + self.add_individual_module_args(simple_modules, parser) # for simple mode, we use the cli_feeder and any modules that don't require setup - yaml_config['steps']['feeders'] = ['cli_feeder'] - + if not yaml_config['steps']['feeders']: + yaml_config['steps']['feeders'] = ['cli_feeder'] + # add them to the config for module in simple_modules: for module_type in module.type: yaml_config['steps'].setdefault(f"{module_type}s", []).append(module.name) else: # load all modules, they're not using the 'simple' mode - self.add_module_args(available_modules(with_manifest=True), parser) - + self.add_individual_module_args(self.module_factory.available_modules(), parser) + parser.set_defaults(**to_dot_notation(yaml_config)) # reload the parser with the new arguments, now that we have them parsed, unknown = parser.parse_known_args(unused_args) - # merge the new config with the old one - self.config = merge_dicts(vars(parsed), yaml_config) + config = merge_dicts(vars(parsed), yaml_config) + # clean out args from the base_parser that we don't want in the config for key in vars(basic_config): - self.config.pop(key, None) + config.pop(key, None) # setup the logging - self.setup_logging() + self.setup_logging(config) if unknown: logger.warning(f"Ignoring unknown/unused arguments: {unknown}\nPerhaps you don't have this module enabled?") - - if (self.config != yaml_config and basic_config.store) or not os.path.isfile(basic_config.config_file): + + if (config != yaml_config and basic_config.store) or not os.path.isfile(basic_config.config_file): logger.info(f"Storing configuration file to {basic_config.config_file}") - store_yaml(self.config, basic_config.config_file) - - return self.config + store_yaml(config, basic_config.config_file) + + return config + def add_modules_args(self, parser: argparse.ArgumentParser = None): + if not parser: + parser = self.parser + + # Module loading from the command line + for module_type in MODULE_TYPES: + parser.add_argument(f'--{module_type}s', dest=f'{module_type}s', nargs='+', help=f'the {module_type}s to use', default=[], action=UniqueAppendAction) + def add_additional_args(self, parser: argparse.ArgumentParser = None): if not parser: parser = self.parser - # allow passing URLs directly on the command line parser.add_argument('urls', nargs='*', default=[], help='URL(s) to archive, either a single URL or a list of urls, should not come from config.yaml') - parser.add_argument('--feeders', dest='steps.feeders', nargs='+', default=['cli_feeder'], help='the feeders to use', action=UniqueAppendAction) - parser.add_argument('--enrichers', dest='steps.enrichers', nargs='+', help='the enrichers to use', action=UniqueAppendAction) - parser.add_argument('--extractors', dest='steps.extractors', nargs='+', help='the extractors to use', action=UniqueAppendAction) - parser.add_argument('--databases', dest='steps.databases', nargs='+', help='the databases to use', action=UniqueAppendAction) - parser.add_argument('--storages', dest='steps.storages', nargs='+', help='the storages to use', action=UniqueAppendAction) - parser.add_argument('--formatters', dest='steps.formatters', nargs='+', help='the formatter to use', action=UniqueAppendAction) - parser.add_argument('--authentication', dest='authentication', help='A dictionary of sites and their authentication methods \ (token, username etc.) that extractors can use to log into \ a website. If passing this on the command line, use a JSON string. \ - You may also pass a path to a valid JSON/YAML file which will be parsed.',\ + You may also pass a path to a valid JSON/YAML file which will be parsed.', default={}, + nargs="?", action=AuthenticationJsonParseAction) + # logging arguments parser.add_argument('--logging.level', action='store', dest='logging.level', choices=['INFO', 'DEBUG', 'ERROR', 'WARNING'], help='the logging level to use', default='INFO', type=str.upper) parser.add_argument('--logging.file', action='store', dest='logging.file', help='the logging file to write to', default=None) parser.add_argument('--logging.rotation', action='store', dest='logging.rotation', help='the logging rotation to use', default=None) - - def add_module_args(self, modules: list[LazyBaseModule] = None, parser: argparse.ArgumentParser = None) -> None: + def add_individual_module_args(self, modules: list[LazyBaseModule] = None, parser: argparse.ArgumentParser = None) -> None: if not modules: - modules = available_modules(with_manifest=True) - - module: LazyBaseModule + modules = self.module_factory.available_modules() + for module in modules: if not module.configs: @@ -224,21 +276,29 @@ class ArchivingOrchestrator: arg.should_store = should_store def show_help(self, basic_config: dict): - # for the help message, we want to load *all* possible modules and show the help - # add configs as arg parser arguments - + # for the help message, we want to load manifests from *all* possible modules and show their help/settings + # add configs as arg parser arguments + + self.add_modules_args(self.basic_parser) self.add_additional_args(self.basic_parser) - self.add_module_args(parser=self.basic_parser) + self.add_individual_module_args(parser=self.basic_parser) self.basic_parser.print_help() self.basic_parser.exit() - - def setup_logging(self): + + def setup_logging(self, config): # setup loguru logging - logger.remove(0) # remove the default logger - logging_config = self.config['logging'] - logger.add(sys.stderr, level=logging_config['level']) - if log_file := logging_config['file']: - logger.add(log_file) if not logging_config['rotation'] else logger.add(log_file, rotation=logging_config['rotation']) + try: + logger.remove(0) # remove the default logger + except ValueError: + pass + + logging_config = config['logging'] + + # add other logging info + if self.logger_id is None: # note - need direct comparison to None since need to consider falsy value 0 + self.logger_id = logger.add(sys.stderr, level=logging_config['level']) + if log_file := logging_config['file']: + logger.add(log_file) if not logging_config['rotation'] else logger.add(log_file, rotation=logging_config['rotation']) def install_modules(self, modules_by_type): """ @@ -246,9 +306,9 @@ class ArchivingOrchestrator: orchestrator's attributes (self.feeders, self.extractors etc.). If no modules of a certain type are loaded, the program will exit with an error message. """ - + invalid_modules = [] - for module_type in BaseModule.MODULE_TYPES: + for module_type in MODULE_TYPES: step_items = [] modules_to_load = modules_by_type[f"{module_type}s"] @@ -273,6 +333,7 @@ class ArchivingOrchestrator: logger.error("No URLs provided. Please provide at least one URL via the command line, or set up an alternative feeder. Use --help for more information.") exit() # cli_feeder is a pseudo module, it just takes the command line args + def feed(self) -> Generator[Metadata]: for url in urls: logger.debug(f"Processing URL: '{url}'") @@ -284,7 +345,6 @@ class ArchivingOrchestrator: '__iter__': feed })() - pseudo_module.__iter__ = feed step_items.append(pseudo_module) @@ -293,7 +353,7 @@ class ArchivingOrchestrator: if module in invalid_modules: continue try: - loaded_module: BaseModule = get_module(module, self.config) + loaded_module: BaseModule = self.module_factory.get_module(module, self.config) except (KeyboardInterrupt, Exception) as e: logger.error(f"Error during setup of modules: {e}\n{traceback.format_exc()}") if module_type == 'extractor' and loaded_module.name == module: @@ -308,48 +368,85 @@ class ArchivingOrchestrator: check_steps_ok() setattr(self, f"{module_type}s", step_items) - + def load_config(self, config_file: str) -> dict: if not os.path.exists(config_file) and config_file != DEFAULT_CONFIG_FILE: logger.error(f"The configuration file {config_file} was not found. Make sure the file exists and try again, or run without the --config file to use the default settings.") exit() return read_yaml(config_file) + + def setup_config(self, args: list) -> dict: + """ + Sets up the configuration file, merging the default config with the user's config + + This function should only ever be run once. + """ - def run(self, args: list) -> None: - self.setup_basic_parser() # parse the known arguments for now (basically, we want the config file) basic_config, unused_args = self.basic_parser.parse_known_args(args) # setup any custom module paths, so they'll show in the help and for arg parsing - setup_paths(basic_config.module_paths) + self.module_factory.setup_paths(basic_config.module_paths) # if help flag was called, then show the help if basic_config.help: self.show_help(basic_config) - + # merge command line --feeder etc. args with what's in the yaml config yaml_config = self.load_config(basic_config.config_file) - self.setup_complete_parser(basic_config, yaml_config, unused_args) + + return self.setup_complete_parser(basic_config, yaml_config, unused_args) + + def setup(self, args: list): + """ + Function to configure all setup of the orchestrator: setup configs and load modules. + + This method should only ever be called once + """ + + if self.setup_finished: + logger.warning("The `setup_config()` function should only ever be run once. \ + If you need to re-run the setup, please re-instantiate a new instance of the orchestrator. \ + For code implementatations, you should call .setup_config() once then you may call .feed() \ + multiple times to archive multiple URLs.") + return + + self.setup_basic_parser() + self.config = self.setup_config(args) logger.info(f"======== Welcome to the AUTO ARCHIVER ({__version__}) ==========") self.install_modules(self.config['steps']) # log out the modules that were loaded - for module_type in BaseModule.MODULE_TYPES: + for module_type in MODULE_TYPES: logger.info(f"{module_type.upper()}S: " + ", ".join(m.display_name for m in getattr(self, f"{module_type}s"))) + + self.setup_finished = True - for _ in self.feed(): - pass + def _command_line_run(self, args: list) -> Generator[Metadata]: + """ + This is the main entry point for the orchestrator, when run from the command line. - def cleanup(self)->None: + :param args: list of arguments to pass to the orchestrator - these are the command line args + + You should not call this method from code implementations. + + This method sets up the configuration, loads the modules, and runs the feed. + If you wish to make code invocations yourself, you should use the 'setup' and 'feed' methods separately. + To test configurations, without loading any modules you can also first call 'setup_configs' + """ + self.setup(args) + return self.feed() + + def cleanup(self) -> None: logger.info("Cleaning up") for e in self.extractors: e.cleanup() def feed(self) -> Generator[Metadata]: - + url_count = 0 for feeder in self.feeders: for item in feeder: @@ -393,7 +490,6 @@ class ArchivingOrchestrator: m.tmp_dir = None tmp_dir.cleanup() - def archive(self, result: Metadata) -> Union[Metadata, None]: """ Runs the archiving process for a single URL @@ -440,13 +536,13 @@ class ArchivingOrchestrator: try: result.merge(a.download(result)) if result.is_success(): break - except Exception as e: + except Exception as e: logger.error(f"ERROR archiver {a.name}: {e}: {traceback.format_exc()}") # 4 - call enrichers to work with archived content for e in self.enrichers: try: e.enrich(result) - except Exception as exc: + except Exception as exc: logger.error(f"ERROR enricher {e.name}: {exc}: {traceback.format_exc()}") # 5 - store all downloaded/generated media @@ -474,13 +570,13 @@ class ArchivingOrchestrator: Blocks localhost, private, reserved, and link-local IPs and all non-http/https schemes. """ assert url.startswith("http://") or url.startswith("https://"), f"Invalid URL scheme" - + parsed = urlparse(url) assert parsed.scheme in ["http", "https"], f"Invalid URL scheme" assert parsed.hostname, f"Invalid URL hostname" assert parsed.hostname != "localhost", f"Invalid URL" - try: # special rules for IP addresses + try: # special rules for IP addresses ip = ip_address(parsed.hostname) except ValueError: pass else: @@ -489,9 +585,8 @@ class ArchivingOrchestrator: assert not ip.is_link_local, f"Invalid IP used" assert not ip.is_private, f"Invalid IP used" - # Helper Properties - + @property def all_modules(self) -> List[Type[BaseModule]]: - return self.feeders + self.extractors + self.enrichers + self.databases + self.storages + self.formatters \ No newline at end of file + return self.feeders + self.extractors + self.enrichers + self.databases + self.storages + self.formatters diff --git a/src/auto_archiver/core/storage.py b/src/auto_archiver/core/storage.py index 5dfa39d..1535eab 100644 --- a/src/auto_archiver/core/storage.py +++ b/src/auto_archiver/core/storage.py @@ -1,3 +1,7 @@ +""" +Base module for Storage modules – modular components that store media objects in various locations. +""" + from __future__ import annotations from abc import abstractmethod from typing import IO @@ -10,8 +14,14 @@ from auto_archiver.utils.misc import random_str from auto_archiver.core import Media, BaseModule, Metadata from auto_archiver.modules.hash_enricher.hash_enricher import HashEnricher -from auto_archiver.core.module import get_module + class Storage(BaseModule): + + """ + Base class for implementing storage modules in the media archiving framework. + + Subclasses must implement the `get_cdn_url` and `uploadf` methods to define their behavior. + """ def store(self, media: Media, url: str, metadata: Metadata=None) -> None: if media.is_stored(in_storage=self): @@ -22,10 +32,18 @@ class Storage(BaseModule): media.add_url(self.get_cdn_url(media)) @abstractmethod - def get_cdn_url(self, media: Media) -> str: pass + def get_cdn_url(self, media: Media) -> str: + """ + Returns the URL of the media object stored in the CDN. + """ + pass @abstractmethod - def uploadf(self, file: IO[bytes], key: str, **kwargs: dict) -> bool: pass + def uploadf(self, file: IO[bytes], key: str, **kwargs: dict) -> bool: + """ + Uploads (or saves) a file to the storage service/location. + """ + pass def upload(self, media: Media, **kwargs) -> bool: logger.debug(f'[{self.__class__.__name__}] storing file {media.filename} with key {media.key}') @@ -56,7 +74,7 @@ class Storage(BaseModule): filename = random_str(24) elif filename_generator == "static": # load the hash_enricher module - he = get_module(HashEnricher, self.config) + he = self.module_factory.get_module(HashEnricher, self.config) hd = he.calculate_hash(media.filename) filename = hd[:24] else: diff --git a/src/auto_archiver/modules/atlos_db/__init__.py b/src/auto_archiver/modules/atlos_db/__init__.py index 1552e39..e14d202 100644 --- a/src/auto_archiver/modules/atlos_db/__init__.py +++ b/src/auto_archiver/modules/atlos_db/__init__.py @@ -1 +1 @@ -from atlos_db import AtlosDb \ No newline at end of file +from .atlos_db import AtlosDb \ No newline at end of file diff --git a/src/auto_archiver/modules/atlos_db/__manifest__.py b/src/auto_archiver/modules/atlos_db/__manifest__.py index b9cabf2..d23ff23 100644 --- a/src/auto_archiver/modules/atlos_db/__manifest__.py +++ b/src/auto_archiver/modules/atlos_db/__manifest__.py @@ -11,6 +11,8 @@ "api_token": { "default": None, "help": "An Atlos API token. For more information, see https://docs.atlos.org/technical/api/", + "required": True, + "type": "str", }, "atlos_url": { "default": "https://platform.atlos.org", diff --git a/src/auto_archiver/modules/atlos_db/base_configs.py b/src/auto_archiver/modules/atlos_db/base_configs.py deleted file mode 100644 index f672f82..0000000 --- a/src/auto_archiver/modules/atlos_db/base_configs.py +++ /dev/null @@ -1,13 +0,0 @@ -def get_atlos_config_options(): - return { - "api_token": { - "default": None, - "help": "An Atlos API token. For more information, see https://docs.atlos.org/technical/api/", - "type": str - }, - "atlos_url": { - "default": "https://platform.atlos.org", - "help": "The URL of your Atlos instance (e.g., https://platform.atlos.org), without a trailing slash.", - "type": str - }, - } \ No newline at end of file diff --git a/src/auto_archiver/modules/atlos_storage/__init__.py b/src/auto_archiver/modules/atlos_storage/__init__.py new file mode 100644 index 0000000..9e815c7 --- /dev/null +++ b/src/auto_archiver/modules/atlos_storage/__init__.py @@ -0,0 +1 @@ +from .atlos_storage import AtlosStorage \ No newline at end of file diff --git a/src/auto_archiver/modules/atlos_storage/__manifest__.py b/src/auto_archiver/modules/atlos_storage/__manifest__.py new file mode 100644 index 0000000..55b5120 --- /dev/null +++ b/src/auto_archiver/modules/atlos_storage/__manifest__.py @@ -0,0 +1,32 @@ +{ + "name": "Atlos Storage", + "type": ["storage"], + "requires_setup": True, + "dependencies": { + "python": ["loguru", "boto3"], + "bin": [] + }, + "description": """ + Stores media files in a [Atlos](https://www.atlos.org/). + + ### Features + - Saves media files to Atlos, organizing them into folders based on the provided path structure. + + ### Notes + - Requires setup with Atlos credentials. + - Files are uploaded to the specified `root_folder_id` and organized by the `media.key` structure. + """, + "configs": { + "api_token": { + "default": None, + "help": "An Atlos API token. For more information, see https://docs.atlos.org/technical/api/", + "required": True, + "type": "str" + }, + "atlos_url": { + "default": "https://platform.atlos.org", + "help": "The URL of your Atlos instance (e.g., https://platform.atlos.org), without a trailing slash.", + "type": "str" + }, + } +} \ No newline at end of file diff --git a/src/auto_archiver/modules/gdrive_storage/__manifest__.py b/src/auto_archiver/modules/gdrive_storage/__manifest__.py index 632e52b..73784b8 100644 --- a/src/auto_archiver/modules/gdrive_storage/__manifest__.py +++ b/src/auto_archiver/modules/gdrive_storage/__manifest__.py @@ -32,7 +32,6 @@ GDriveStorage: A storage module for saving archived content to Google Drive. - Author: Dave Mateer, (And maintained by: ) Source Documentation: https://davemateer.com/2022/04/28/google-drive-with-python ### Features diff --git a/src/auto_archiver/modules/generic_extractor/bluesky.py b/src/auto_archiver/modules/generic_extractor/bluesky.py index f2086b0..5eef520 100644 --- a/src/auto_archiver/modules/generic_extractor/bluesky.py +++ b/src/auto_archiver/modules/generic_extractor/bluesky.py @@ -39,11 +39,11 @@ class Bluesky(GenericDropin): for image_media in image_medias: url = media_url.format(image_media['image']['ref']['$link'], post['author']['did']) image_media = archiver.download_from_url(url) - media.append(image_media) + media.append(Media(image_media)) for video_media in video_medias: url = media_url.format(video_media['ref']['$link'], post['author']['did']) video_media = archiver.download_from_url(url) - media.append(video_media) + media.append(Media(video_media)) return media diff --git a/src/auto_archiver/modules/generic_extractor/facebook.py b/src/auto_archiver/modules/generic_extractor/facebook.py index 352d44e..fed8e09 100644 --- a/src/auto_archiver/modules/generic_extractor/facebook.py +++ b/src/auto_archiver/modules/generic_extractor/facebook.py @@ -8,7 +8,8 @@ class Facebook(GenericDropin): url.replace('://m.facebook.com/', '://www.facebook.com/'), video_id) webpage = ie_instance._download_webpage(url, ie_instance._match_valid_url(url).group('id')) - post_data = ie_instance._extract_from_url.extract_metadata(webpage) + # TODO: fix once https://github.com/yt-dlp/yt-dlp/pull/12275 is merged + post_data = ie_instance._extract_metadata(webpage) return post_data def create_metadata(self, post: dict, ie_instance, archiver, url): diff --git a/src/auto_archiver/modules/generic_extractor/generic_extractor.py b/src/auto_archiver/modules/generic_extractor/generic_extractor.py index 86e978f..72fe3e0 100644 --- a/src/auto_archiver/modules/generic_extractor/generic_extractor.py +++ b/src/auto_archiver/modules/generic_extractor/generic_extractor.py @@ -1,6 +1,6 @@ import datetime, os, yt_dlp, pysubs2 import importlib -from typing import Type +from typing import Generator, Type from yt_dlp.extractor.common import InfoExtractor from loguru import logger @@ -11,7 +11,7 @@ from auto_archiver.core import Metadata, Media class GenericExtractor(Extractor): _dropins = {} - def suitable_extractors(self, url: str) -> list[str]: + def suitable_extractors(self, url: str) -> Generator[str, None, None]: """ Returns a list of valid extractors for the given URL""" for info_extractor in yt_dlp.YoutubeDL()._ies.values(): @@ -116,7 +116,7 @@ class GenericExtractor(Extractor): def get_metadata_for_post(self, info_extractor: Type[InfoExtractor], url: str, ydl: yt_dlp.YoutubeDL) -> Metadata: """ - Calls into the ytdlp InfoExtract subclass to use the prive _extract_post method to get the post metadata. + Calls into the ytdlp InfoExtract subclass to use the private _extract_post method to get the post metadata. """ ie_instance = info_extractor(downloader=ydl) @@ -266,6 +266,11 @@ class GenericExtractor(Extractor): def download(self, item: Metadata) -> Metadata: url = item.get_url() + #TODO: this is a temporary hack until this issue is closed: https://github.com/yt-dlp/yt-dlp/issues/11025 + if url.startswith("https://ya.ru"): + url = url.replace("https://ya.ru", "https://yandex.ru") + item.set("replaced_url", url) + ydl_options = {'outtmpl': os.path.join(self.tmp_dir, f'%(id)s.%(ext)s'), 'quiet': False, 'noplaylist': not self.allow_playlist , @@ -275,7 +280,7 @@ class GenericExtractor(Extractor): # set up auth auth = self.auth_for_site(url, extract_cookies=False) - # order of importance: username/pasword -> api_key -> cookie -> cookie_from_browser -> cookies_file + # order of importance: username/pasword -> api_key -> cookie -> cookies_from_browser -> cookies_file if auth: if 'username' in auth and 'password' in auth: logger.debug(f'Using provided auth username and password for {url}') @@ -284,7 +289,7 @@ class GenericExtractor(Extractor): elif 'cookie' in auth: logger.debug(f'Using provided auth cookie for {url}') yt_dlp.utils.std_headers['cookie'] = auth['cookie'] - elif 'cookie_from_browser' in auth: + elif 'cookies_from_browser' in auth: logger.debug(f'Using extracted cookies from browser {self.cookies_from_browser} for {url}') ydl_options['cookiesfrombrowser'] = auth['cookies_from_browser'] elif 'cookies_file' in auth: diff --git a/src/auto_archiver/modules/gsheet_feeder/__manifest__.py b/src/auto_archiver/modules/gsheet_feeder/__manifest__.py index 7b74072..77026ea 100644 --- a/src/auto_archiver/modules/gsheet_feeder/__manifest__.py +++ b/src/auto_archiver/modules/gsheet_feeder/__manifest__.py @@ -10,7 +10,7 @@ "sheet": {"default": None, "help": "name of the sheet to archive"}, "sheet_id": { "default": None, - "help": "(alternative to sheet name) the id of the sheet to archive", + "help": "the id of the sheet to archive (alternative to 'sheet' config)", }, "header": {"default": 1, "help": "index of the header row (starts at 1)", "type": "int"}, "service_account": { diff --git a/src/auto_archiver/modules/html_formatter/html_formatter.py b/src/auto_archiver/modules/html_formatter/html_formatter.py index 3691735..deb4b44 100644 --- a/src/auto_archiver/modules/html_formatter/html_formatter.py +++ b/src/auto_archiver/modules/html_formatter/html_formatter.py @@ -9,9 +9,7 @@ import base64 from auto_archiver.version import __version__ from auto_archiver.core import Metadata, Media from auto_archiver.core import Formatter -from auto_archiver.modules.hash_enricher import HashEnricher from auto_archiver.utils.misc import random_str -from auto_archiver.core.module import get_module class HtmlFormatter(Formatter): environment: Environment = None @@ -51,7 +49,7 @@ class HtmlFormatter(Formatter): final_media = Media(filename=html_path, _mimetype="text/html") # get the already instantiated hash_enricher module - he = get_module('hash_enricher', self.config) + he = self.module_factory.get_module('hash_enricher', self.config) if len(hd := he.calculate_hash(final_media.filename)): final_media.set("hash", f"{he.algorithm}:{hd}") diff --git a/src/auto_archiver/modules/html_formatter/templates/html_template.html b/src/auto_archiver/modules/html_formatter/templates/html_template.html index 8bdf5ef..62d6b0b 100644 --- a/src/auto_archiver/modules/html_formatter/templates/html_template.html +++ b/src/auto_archiver/modules/html_formatter/templates/html_template.html @@ -200,7 +200,7 @@ el.innerHTML = decodeCertificate(certificate); let cyberChefUrl = - `https://gchq.github.io/CyberChef/#recipe=Parse_X.509_certificate('PEM')&input=${btoa(certificate)}`; + `https://gchq.github.io/CyberChef/#recipe=Parse_X.509_certificate('PEM')&input=${btoa(certificate).replace(/=+$/, '')}`; // create a new anchor with this url and append after the code let a = document.createElement("a"); a.href = cyberChefUrl; diff --git a/src/auto_archiver/modules/instagram_tbot_extractor/instagram_tbot_extractor.py b/src/auto_archiver/modules/instagram_tbot_extractor/instagram_tbot_extractor.py index d4b7a8e..4404d07 100644 --- a/src/auto_archiver/modules/instagram_tbot_extractor/instagram_tbot_extractor.py +++ b/src/auto_archiver/modules/instagram_tbot_extractor/instagram_tbot_extractor.py @@ -77,13 +77,14 @@ class InstagramTbotExtractor(Extractor): chat, since_id = self._send_url_to_bot(url) message = self._process_messages(chat, since_id, tmp_dir, result) + # This may be outdated and replaced by the below message, but keeping until confirmed if "You must enter a URL to a post" in message: logger.debug(f"invalid link {url=} for {self.name}: {message}") return False - # # TODO: It currently returns this as a success - is that intentional? - # if "Media not found or unavailable" in message: - # logger.debug(f"invalid link {url=} for {self.name}: {message}") - # return False + + if "Media not found or unavailable" in message: + logger.debug(f"No media found for link {url=} for {self.name}: {message}") + return False if message: result.set_content(message).set_title(message[:128]) diff --git a/src/auto_archiver/modules/screenshot_enricher/__manifest__.py b/src/auto_archiver/modules/screenshot_enricher/__manifest__.py index 52842c9..9829844 100644 --- a/src/auto_archiver/modules/screenshot_enricher/__manifest__.py +++ b/src/auto_archiver/modules/screenshot_enricher/__manifest__.py @@ -4,7 +4,6 @@ "requires_setup": True, "dependencies": { "python": ["loguru", "selenium"], - "bin": ["chromedriver"] }, "configs": { "width": {"default": 1280, "help": "width of the screenshots"}, diff --git a/src/auto_archiver/modules/screenshot_enricher/screenshot_enricher.py b/src/auto_archiver/modules/screenshot_enricher/screenshot_enricher.py index e1da99d..832d0f8 100644 --- a/src/auto_archiver/modules/screenshot_enricher/screenshot_enricher.py +++ b/src/auto_archiver/modules/screenshot_enricher/screenshot_enricher.py @@ -11,6 +11,10 @@ from auto_archiver.core import Media, Metadata class ScreenshotEnricher(Enricher): + def __init__(self, webdriver_factory=None): + super().__init__() + self.webdriver_factory = webdriver_factory or Webdriver + def enrich(self, to_enrich: Metadata) -> None: url = to_enrich.get_url() @@ -20,7 +24,8 @@ class ScreenshotEnricher(Enricher): logger.debug(f"Enriching screenshot for {url=}") auth = self.auth_for_site(url) - with Webdriver(self.width, self.height, self.timeout, facebook_accept_cookies='facebook.com' in url, + with self.webdriver_factory( + self.width, self.height, self.timeout, facebook_accept_cookies='facebook.com' in url, http_proxy=self.http_proxy, print_options=self.print_options, auth=auth) as driver: try: driver.get(url) @@ -38,3 +43,4 @@ class ScreenshotEnricher(Enricher): logger.info("TimeoutException loading page for screenshot") except Exception as e: logger.error(f"Got error while loading webdriver for screenshot enricher: {e}") + diff --git a/src/auto_archiver/modules/telegram_extractor/__manifest__.py b/src/auto_archiver/modules/telegram_extractor/__manifest__.py index cb0ee1e..0b94582 100644 --- a/src/auto_archiver/modules/telegram_extractor/__manifest__.py +++ b/src/auto_archiver/modules/telegram_extractor/__manifest__.py @@ -20,5 +20,6 @@ - Processes HTML content of messages to retrieve embedded media. - Sets structured metadata, including timestamps, content, and media details. - Does not require user authentication for Telegram. + """, } diff --git a/src/auto_archiver/modules/telethon_extractor/__manifest__.py b/src/auto_archiver/modules/telethon_extractor/__manifest__.py index 6b37654..e16d9db 100644 --- a/src/auto_archiver/modules/telethon_extractor/__manifest__.py +++ b/src/auto_archiver/modules/telethon_extractor/__manifest__.py @@ -1,5 +1,5 @@ { - "name": "telethon_extractor", + "name": "Telethon Extractor", "type": ["extractor"], "requires_setup": True, "dependencies": { @@ -40,5 +40,9 @@ To use the `TelethonExtractor`, you must configure the following: - **Bot Token**: Optional, allows access to additional content (e.g., large videos) but limits private channel archiving. - **Channel Invites**: Optional, specify a JSON string of invite links to join channels during setup. +### First Time Login +The first time you run, you will be prompted to do a authentication with the phone number associated, alternatively you can put your `anon.session` in the root. + + """ } \ No newline at end of file diff --git a/src/auto_archiver/modules/thumbnail_enricher/__manifest__.py b/src/auto_archiver/modules/thumbnail_enricher/__manifest__.py index e47397f..1bd23b5 100644 --- a/src/auto_archiver/modules/thumbnail_enricher/__manifest__.py +++ b/src/auto_archiver/modules/thumbnail_enricher/__manifest__.py @@ -7,8 +7,12 @@ "bin": ["ffmpeg"] }, "configs": { - "thumbnails_per_minute": {"default": 60, "help": "how many thumbnails to generate per minute of video, can be limited by max_thumbnails"}, - "max_thumbnails": {"default": 16, "help": "limit the number of thumbnails to generate per video, 0 means no limit"}, + "thumbnails_per_minute": {"default": 60, + "type": "int", + "help": "how many thumbnails to generate per minute of video, can be limited by max_thumbnails"}, + "max_thumbnails": {"default": 16, + "type": "int", + "help": "limit the number of thumbnails to generate per video, 0 means no limit"}, }, "description": """ Generates thumbnails for video files to provide visual previews. diff --git a/src/auto_archiver/modules/thumbnail_enricher/thumbnail_enricher.py b/src/auto_archiver/modules/thumbnail_enricher/thumbnail_enricher.py index e0ac937..8178cd8 100644 --- a/src/auto_archiver/modules/thumbnail_enricher/thumbnail_enricher.py +++ b/src/auto_archiver/modules/thumbnail_enricher/thumbnail_enricher.py @@ -42,7 +42,7 @@ class ThumbnailEnricher(Enricher): logger.error(f"error getting duration of video {m.filename}: {e}") return - num_thumbs = int(min(max(1, duration * self.thumbnails_per_minute), self.max_thumbnails)) + num_thumbs = int(min(max(1, (duration / 60) * self.thumbnails_per_minute), self.max_thumbnails)) timestamps = [duration / (num_thumbs + 1) * i for i in range(1, num_thumbs + 1)] thumbnails_media = [] diff --git a/src/auto_archiver/modules/wacz_enricher/__manifest__.py b/src/auto_archiver/modules/wacz_enricher/__manifest__.py index 46ce05e..bebfc9e 100644 --- a/src/auto_archiver/modules/wacz_enricher/__manifest__.py +++ b/src/auto_archiver/modules/wacz_enricher/__manifest__.py @@ -1,6 +1,6 @@ { "name": "WACZ Enricher", - "type": ["enricher", "archiver"], + "type": ["enricher", "extractor"], "entry_point": "wacz_enricher::WaczExtractorEnricher", "requires_setup": True, "dependencies": { diff --git a/src/auto_archiver/modules/wacz_enricher/wacz_enricher.py b/src/auto_archiver/modules/wacz_enricher/wacz_enricher.py index c324c62..ff7314a 100644 --- a/src/auto_archiver/modules/wacz_enricher/wacz_enricher.py +++ b/src/auto_archiver/modules/wacz_enricher/wacz_enricher.py @@ -221,4 +221,4 @@ class WaczExtractorEnricher(Enricher, Extractor): to_enrich.add_media(m, warc_fn) counter += 1 seen_urls.add(record_url) - logger.info(f"WACZ extract_media/extract_screenshot finished, found {counter} relevant media file(s)") + logger.info(f"WACZ extract_media/extract_screenshot finished, found {counter} relevant media file(s)") \ No newline at end of file diff --git a/src/auto_archiver/modules/wayback_extractor_enricher/__manifest__.py b/src/auto_archiver/modules/wayback_extractor_enricher/__manifest__.py index baecc14..4832265 100644 --- a/src/auto_archiver/modules/wayback_extractor_enricher/__manifest__.py +++ b/src/auto_archiver/modules/wayback_extractor_enricher/__manifest__.py @@ -1,6 +1,6 @@ { "name": "Wayback Machine Enricher", - "type": ["enricher", "archiver"], + "type": ["enricher", "extractor"], "entry_point": "wayback_extractor_enricher::WaybackExtractorEnricher", "requires_setup": True, "dependencies": { diff --git a/src/auto_archiver/modules/whisper_enricher/whisper_enricher.py b/src/auto_archiver/modules/whisper_enricher/whisper_enricher.py index 89579f9..d63d2ed 100644 --- a/src/auto_archiver/modules/whisper_enricher/whisper_enricher.py +++ b/src/auto_archiver/modules/whisper_enricher/whisper_enricher.py @@ -4,7 +4,6 @@ from loguru import logger from auto_archiver.core import Enricher from auto_archiver.core import Metadata, Media -from auto_archiver.core.module import get_module class WhisperEnricher(Enricher): """ @@ -15,7 +14,7 @@ class WhisperEnricher(Enricher): def setup(self) -> None: self.stores = self.config['steps']['storages'] - self.s3 = get_module("s3_storage", self.config) + self.s3 = self.module_factory.get_module("s3_storage", self.config) if not "s3_storage" in self.stores: logger.error("WhisperEnricher: To use the WhisperEnricher you need to use S3Storage so files are accessible publicly to the whisper service being called.") return @@ -29,8 +28,7 @@ class WhisperEnricher(Enricher): job_results = {} for i, m in enumerate(to_enrich.media): if m.is_video() or m.is_audio(): - # TODO: this used to pass all storage items to store now - # Now only passing S3, the rest will get added later in the usual order (?) + # Only storing S3, the rest will get added later in the usual order (?) m.store(url=url, metadata=to_enrich, storages=[self.s3]) try: job_id = self.submit_job(m) diff --git a/src/auto_archiver/utils/__init__.py b/src/auto_archiver/utils/__init__.py index ed2d3bb..46ca191 100644 --- a/src/auto_archiver/utils/__init__.py +++ b/src/auto_archiver/utils/__init__.py @@ -2,7 +2,6 @@ # we need to explicitly expose the available imports here from .misc import * from .webdriver import Webdriver -from .atlos import get_atlos_config_options # handy utils from ytdlp from yt_dlp.utils import (clean_html, traverse_obj, strip_or_none, url_or_none) \ No newline at end of file diff --git a/src/auto_archiver/utils/atlos.py b/src/auto_archiver/utils/atlos.py deleted file mode 100644 index c47c711..0000000 --- a/src/auto_archiver/utils/atlos.py +++ /dev/null @@ -1,13 +0,0 @@ -def get_atlos_config_options(): - return { - "api_token": { - "default": None, - "help": "An Atlos API token. For more information, see https://docs.atlos.org/technical/api/", - "cli_set": lambda cli_val, _: cli_val - }, - "atlos_url": { - "default": "https://platform.atlos.org", - "help": "The URL of your Atlos instance (e.g., https://platform.atlos.org), without a trailing slash.", - "cli_set": lambda cli_val, _: cli_val - }, - } \ No newline at end of file diff --git a/src/auto_archiver/utils/gsheet.py b/src/auto_archiver/utils/gsheet.py deleted file mode 100644 index e69de29..0000000 diff --git a/src/auto_archiver/utils/misc.py b/src/auto_archiver/utils/misc.py index cd03b49..108deae 100644 --- a/src/auto_archiver/utils/misc.py +++ b/src/auto_archiver/utils/misc.py @@ -46,7 +46,7 @@ def dump_payload(p): def update_nested_dict(dictionary, update_dict): - # takes 2 dicts and overwrites the first with the second only on the changed balues + # takes 2 dicts and overwrites the first with the second only on the changed values for key, value in update_dict.items(): if key in dictionary and isinstance(value, dict) and isinstance(dictionary[key], dict): update_nested_dict(dictionary[key], value) diff --git a/tests/conftest.py b/tests/conftest.py index 8675fbc..a94abcd 100644 --- a/tests/conftest.py +++ b/tests/conftest.py @@ -3,12 +3,14 @@ pytest conftest file, for shared fixtures and configuration """ import os import pickle +from datetime import datetime, timezone from tempfile import TemporaryDirectory from typing import Dict, Tuple import hashlib + import pytest from auto_archiver.core.metadata import Metadata -from auto_archiver.core.module import get_module, _LAZY_LOADED_MODULES +from auto_archiver.core.module import ModuleFactory # Test names inserted into this list will be run last. This is useful for expensive/costly tests # that you only want to run if everything else succeeds (e.g. API calls). The order here is important @@ -20,19 +22,19 @@ TESTS_TO_RUN_LAST = ['test_twitter_api_archiver'] def setup_module(request): def _setup_module(module_name, config={}): + module_factory = ModuleFactory() + if isinstance(module_name, type): # get the module name: # if the class does not have a .name, use the name of the parent folder module_name = module_name.__module__.rsplit(".",2)[-2] - m = get_module(module_name, {module_name: config}) - + m = module_factory.get_module(module_name, {module_name: config}) # add the tmp_dir to the module tmp_dir = TemporaryDirectory() m.tmp_dir = tmp_dir.name - + def cleanup(): - _LAZY_LOADED_MODULES.pop(module_name) tmp_dir.cleanup() request.addfinalizer(cleanup) @@ -122,10 +124,36 @@ def pytest_runtest_setup(item): def unpickle(): """ Returns a helper function that unpickles a file - ** gets the file from the test_files directory: tests/data/test_files ** + ** gets the file from the test_files directory: tests/data/ ** """ def _unpickle(path): - test_data_dir = os.path.join(os.path.dirname(__file__), "data", "test_files") - with open(os.path.join(test_data_dir, path), "rb") as f: + with open(os.path.join("tests/data", path), "rb") as f: return pickle.load(f) - return _unpickle \ No newline at end of file + return _unpickle + + +@pytest.fixture +def mock_binary_dependencies(mocker): + mock_shutil_which = mocker.patch("shutil.which") + # Mock all binary dependencies as available + mock_shutil_which.return_value = "/usr/bin/fake_binary" + return mock_shutil_which + + +@pytest.fixture +def sample_datetime(): + return datetime(2023, 1, 1, 12, 0, tzinfo=timezone.utc) + + +@pytest.fixture(autouse=True) +def mock_sleep(mocker): + """Globally mock time.sleep to avoid delays.""" + return mocker.patch("time.sleep") + + +@pytest.fixture +def metadata(): + metadata = Metadata() + metadata.set("_processed_at", "2021-01-01T00:00:00") + metadata.set_url("https://example.com") + return metadata \ No newline at end of file diff --git a/tests/data/metadata_enricher_exif.pickle b/tests/data/metadata_enricher_exif.pickle new file mode 100644 index 0000000..5607a9b Binary files /dev/null and b/tests/data/metadata_enricher_exif.pickle differ diff --git a/tests/data/metadata_enricher_ytshort_expected.pickle b/tests/data/metadata_enricher_ytshort_expected.pickle new file mode 100644 index 0000000..7e54268 Binary files /dev/null and b/tests/data/metadata_enricher_ytshort_expected.pickle differ diff --git a/tests/data/metadata_enricher_ytshort_input.pickle b/tests/data/metadata_enricher_ytshort_input.pickle new file mode 100644 index 0000000..2495c46 Binary files /dev/null and b/tests/data/metadata_enricher_ytshort_input.pickle differ diff --git a/tests/data/test_modules/example_module/__manifest__.py b/tests/data/test_modules/example_module/__manifest__.py index f2ebdbf..e3a26bb 100644 --- a/tests/data/test_modules/example_module/__manifest__.py +++ b/tests/data/test_modules/example_module/__manifest__.py @@ -1,11 +1,29 @@ { + # Display Name of your module "name": "Example Module", + # The author of your module (optional) + "author": "John Doe", + # Optional version number, for your own versioning purposes + "version": 2.0, + # The type of the module, must be one (or more) of the built in module types "type": ["extractor", "feeder", "formatter", "storage", "enricher", "database"], + # a boolean indicating whether or not a module requires additional user setup before it can be used + # for example: adding API keys, installing additional software etc. "requires_setup": False, - "dependencies": {"python": ["loguru"] - }, + # a dictionary of dependencies for this module, that must be installed before the module is loaded. + # Can be python dependencies (external packages, or other auto-archiver modules), or you can + # provide external bin dependencies (e.g. ffmpeg, docker etc.) + "dependencies": { + "python": ["loguru"], + "bin": ["bash"], + }, + # configurations that this module takes. These are argparse-compliant dicationaries, that are + # used to create command line arguments when the programme is run. + # The full name of the config option will become: `module_name.config_name` "configs": { "csv_file": {"default": "db.csv", "help": "CSV file name"}, "required_field": {"required": True, "help": "required field in the CSV file"}, }, + # A description of the module, used for documentation + "description": "This is an example module", } \ No newline at end of file diff --git a/tests/data/test_service_account.json b/tests/data/test_service_account.json new file mode 100644 index 0000000..5aae894 --- /dev/null +++ b/tests/data/test_service_account.json @@ -0,0 +1,14 @@ +{ + "type": "service_account", + "project_id": "some-project-id", + "private_key_id": "some-private-key-id", + "private_key": "-----BEGIN PRIVATE KEY-----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\njUpppYDumg3oM7wSJ6sTQA==\n-----END PRIVATE KEY-----", + "client_email": "some-email", + "client_id": "some-client-email", + "auth_uri": "https://example.com/o/oauth2/auth", + "token_uri": "https://oauth2.example.com/token", + "auth_provider_x509_cert_url": "https://www.example.com/oauth2/v1/certs", + "client_x509_cert_url": "https://www.example.com/robot/v1/metadata/x509/some-email", + "universe_domain": "example.com" + } + \ No newline at end of file diff --git a/tests/databases/test_api_db.py b/tests/databases/test_api_db.py new file mode 100644 index 0000000..5d1ea84 --- /dev/null +++ b/tests/databases/test_api_db.py @@ -0,0 +1,59 @@ +import pytest + +from auto_archiver.core import Metadata +from auto_archiver.modules.api_db import AAApiDb + + +@pytest.fixture +def api_db(setup_module): + configs: dict = { + "api_endpoint": "https://api.example.com", + "api_token": "test-token", + "public": False, + "author_id": "Someone", + "group_id": "123", + "use_api_cache": True, + "store_results": True, + "tags": "[]", + } + return setup_module(AAApiDb, configs) + + +def test_fetch_no_cache(api_db, metadata): + # Test fetch + api_db.use_api_cache = False + assert api_db.fetch(metadata) is None + + +def test_fetch_fail_status(api_db, metadata, mocker): + # Test response fail in fetch method + mock_get = mocker.patch("auto_archiver.modules.api_db.api_db.requests.get") + mock_get.return_value.status_code = 400 + mock_get.return_value.json.return_value = {} + mock_error = mocker.patch("loguru.logger.error") + assert api_db.fetch(metadata) is False + mock_error.assert_called_once_with("AA API FAIL (400): {}") + + +def test_fetch(api_db, metadata, mocker): + # Test successful fetch method + mock_get = mocker.patch("auto_archiver.modules.api_db.api_db.requests.get") + mock_datetime = mocker.patch("auto_archiver.core.metadata.datetime.datetime") + mock_datetime.now.return_value = "2021-01-01T00:00:00" + mock_get.return_value.status_code = 200 + mock_get.return_value.json.return_value = [{"result": {}}, {"result": + {'media': [], 'metadata': {'_processed_at': '2021-01-01T00:00:00', 'url': 'https://example.com'}, + 'status': 'no archiver'}}] + assert api_db.fetch(metadata) == metadata + + +def test_done_success(api_db, metadata, mocker): + mock_post = mocker.patch("auto_archiver.modules.api_db.api_db.requests.post") + mock_post.return_value.status_code = 201 + api_db.done(metadata) + mock_post.assert_called_once() + mock_post.assert_called_once_with("https://api.example.com/interop/submit-archive", + json={'author_id': 'Someone', 'url': 'https://example.com', + 'public': False, 'group_id': '123', 'tags': ['[', ']'], 'result': '{"status": "no archiver", "metadata": {"_processed_at": "2021-01-01T00:00:00", "url": "https://example.com"}, "media": []}'}, + headers={'Authorization': 'Bearer test-token'}) + diff --git a/tests/databases/test_atlos_db.py b/tests/databases/test_atlos_db.py new file mode 100644 index 0000000..82c07ef --- /dev/null +++ b/tests/databases/test_atlos_db.py @@ -0,0 +1,110 @@ +import pytest +from datetime import datetime + +from auto_archiver.core import Metadata +from auto_archiver.modules.atlos_db import AtlosDb + + +class FakeAPIResponse: + """Simulate a response object.""" + + def __init__(self, data: dict, raise_error: bool = False) -> None: + self._data = data + self.raise_error = raise_error + + def raise_for_status(self) -> None: + if self.raise_error: + raise Exception("HTTP error") + + +@pytest.fixture +def atlos_db(setup_module) -> AtlosDb: + """Fixture for AtlosDb.""" + configs: dict = { + "api_token": "abc123", + "atlos_url": "https://platform.atlos.org", + } + return setup_module("atlos_db", configs) + + +def test_failed_no_atlos_id(atlos_db, metadata, mocker): + """Test failed() skips posting when no atlos_id present.""" + post_mock = mocker.patch("requests.post") + atlos_db.failed(metadata, "failure reason") + post_mock.assert_not_called() + + +def test_failed_with_atlos_id(atlos_db, metadata, mocker): + """Test failed() posts failure when atlos_id is present.""" + metadata.set("atlos_id", 42) + fake_resp = FakeAPIResponse({}, raise_error=False) + post_mock = mocker.patch("requests.post", return_value=fake_resp) + atlos_db.failed(metadata, "failure reason") + expected_url = ( + f"{atlos_db.atlos_url}/api/v2/source_material/metadata/42/auto_archiver" + ) + expected_headers = {"Authorization": f"Bearer {atlos_db.api_token}"} + expected_json = { + "metadata": {"processed": True, "status": "error", "error": "failure reason"} + } + post_mock.assert_called_once_with( + expected_url, headers=expected_headers, json=expected_json + ) + + +def test_failed_http_error(atlos_db, metadata, mocker): + """Test failed() raises exception on HTTP error.""" + metadata.set("atlos_id", 42) + fake_resp = FakeAPIResponse({}, raise_error=True) + mocker.patch("requests.post", return_value=fake_resp) + with pytest.raises(Exception, match="HTTP error"): + atlos_db.failed(metadata, "failure reason") + + +def test_fetch_returns_false(atlos_db): + """Test fetch() always returns False.""" + item = Metadata() + assert atlos_db.fetch(item) is False + + +def test_done_no_atlos_id(atlos_db, mocker): + """Test done() skips posting when no atlos_id present.""" + item = Metadata().set_url("http://example.com") + post_mock = mocker.patch("requests.post") + atlos_db.done(item) + post_mock.assert_not_called() + + +def test_done_with_atlos_id(atlos_db, metadata, mocker): + """Test done() posts success when atlos_id is present.""" + metadata.set("atlos_id", 99) + now = datetime.now() + metadata.set("timestamp", now) + fake_resp = FakeAPIResponse({}, raise_error=False) + post_mock = mocker.patch("requests.post", return_value=fake_resp) + atlos_db.done(metadata) + expected_url = ( + f"{atlos_db.atlos_url}/api/v2/source_material/metadata/99/auto_archiver" + ) + expected_headers = {"Authorization": f"Bearer {atlos_db.api_token}"} + expected_results = metadata.metadata.copy() + expected_results["timestamp"] = now.isoformat() + expected_json = { + "metadata": { + "processed": True, + "status": "success", + "results": expected_results, + } + } + post_mock.assert_called_once_with( + expected_url, headers=expected_headers, json=expected_json + ) + + +def test_done_http_error(atlos_db, metadata, mocker): + """Test done() raises exception on HTTP error.""" + metadata.set("atlos_id", 123) + fake_resp = FakeAPIResponse({}, raise_error=True) + mocker.patch("requests.post", return_value=fake_resp) + with pytest.raises(Exception, match="HTTP error"): + atlos_db.done(metadata) diff --git a/tests/databases/test_gsheet_db.py b/tests/databases/test_gsheet_db.py index 18a22f1..42a21b2 100644 --- a/tests/databases/test_gsheet_db.py +++ b/tests/databases/test_gsheet_db.py @@ -1,6 +1,4 @@ from datetime import datetime, timezone -from unittest.mock import MagicMock, patch - import pytest from auto_archiver.core import Metadata, Media @@ -9,8 +7,8 @@ from auto_archiver.modules.gsheet_feeder import GWorksheet @pytest.fixture -def mock_gworksheet(): - mock_gworksheet = MagicMock(spec=GWorksheet) +def mock_gworksheet(mocker): + mock_gworksheet = mocker.MagicMock(spec=GWorksheet) mock_gworksheet.col_exists.return_value = True mock_gworksheet.get_cell.return_value = "" mock_gworksheet.get_row.return_value = {} @@ -18,14 +16,14 @@ def mock_gworksheet(): @pytest.fixture -def mock_metadata(): - metadata: Metadata = MagicMock(spec=Metadata) +def mock_metadata(mocker): + metadata: Metadata = mocker.MagicMock(spec=Metadata) metadata.get_url.return_value = "http://example.com" metadata.status = "done" metadata.get_title.return_value = "Example Title" metadata.get.return_value = "Example Content" metadata.get_timestamp.return_value = "2025-01-01T00:00:00" - metadata.get_final_media.return_value = MagicMock(spec=Media) + metadata.get_final_media.return_value = mocker.MagicMock(spec=Media) metadata.get_all_media.return_value = [] metadata.get_media_by_id.return_value = None metadata.get_first_image.return_value = None @@ -47,21 +45,21 @@ def metadata(): @pytest.fixture -def mock_media(): +def mock_media(mocker): """Fixture for a mock Media object.""" - mock_media = MagicMock(spec=Media) + mock_media = mocker.MagicMock(spec=Media) mock_media.urls = ["http://example.com/media"] mock_media.get.return_value = "not-calculated" return mock_media @pytest.fixture -def gsheets_db(mock_gworksheet, setup_module): +def gsheets_db(mock_gworksheet, setup_module, mocker): db = setup_module("gsheet_db", { "allow_worksheets": "set()", "block_worksheets": "set()", "use_sheet_names_in_stored_paths": "True", }) - db._retrieve_gsheet = MagicMock(return_value=(mock_gworksheet, 1)) + db._retrieve_gsheet = mocker.MagicMock(return_value=(mock_gworksheet, 1)) return db @@ -109,27 +107,26 @@ def test_aborted(gsheets_db, mock_metadata, mock_gworksheet): mock_gworksheet.set_cell.assert_called_once_with(1, 'status', '') -def test_done(gsheets_db, metadata, mock_gworksheet, expected_calls): - with patch("auto_archiver.modules.gsheet_db.gsheet_db.get_current_timestamp", return_value='2025-02-01T00:00:00+00:00'): - gsheets_db.done(metadata) +def test_done(gsheets_db, metadata, mock_gworksheet, expected_calls, mocker): + mocker.patch("auto_archiver.modules.gsheet_db.gsheet_db.get_current_timestamp", return_value='2025-02-01T00:00:00+00:00') + gsheets_db.done(metadata) mock_gworksheet.batch_set_cell.assert_called_once_with(expected_calls) -def test_done_cached(gsheets_db, metadata, mock_gworksheet): - with patch("auto_archiver.modules.gsheet_db.gsheet_db.get_current_timestamp", return_value='2025-02-01T00:00:00+00:00'): - gsheets_db.done(metadata, cached=True) +def test_done_cached(gsheets_db, metadata, mock_gworksheet, mocker): + mocker.patch("auto_archiver.modules.gsheet_db.gsheet_db.get_current_timestamp", return_value='2025-02-01T00:00:00+00:00') + gsheets_db.done(metadata, cached=True) # Verify the status message includes "[cached]" call_args = mock_gworksheet.batch_set_cell.call_args[0][0] assert any(call[2].startswith("[cached]") for call in call_args) -def test_done_missing_media(gsheets_db, metadata, mock_gworksheet): +def test_done_missing_media(gsheets_db, metadata, mock_gworksheet, mocker): # clear media from metadata metadata.media = [] - with patch("auto_archiver.modules.gsheet_db.gsheet_db.get_current_timestamp", - return_value='2025-02-01T00:00:00+00:00'): - gsheets_db.done(metadata) + mocker.patch("auto_archiver.modules.gsheet_db.gsheet_db.get_current_timestamp", return_value='2025-02-01T00:00:00+00:00') + gsheets_db.done(metadata) # Verify nothing media-related gets updated call_args = mock_gworksheet.batch_set_cell.call_args[0][0] media_fields = {'archive', 'screenshot', 'thumbnail', 'wacz', 'replaywebpage'} diff --git a/tests/enrichers/test_hash_enricher.py b/tests/enrichers/test_hash_enricher.py index 4b61fc2..c2fe67a 100644 --- a/tests/enrichers/test_hash_enricher.py +++ b/tests/enrichers/test_hash_enricher.py @@ -2,7 +2,7 @@ import pytest from auto_archiver.modules.hash_enricher import HashEnricher from auto_archiver.core import Metadata, Media -from auto_archiver.core.module import get_module_lazy +from auto_archiver.core.module import ModuleFactory @pytest.mark.parametrize("algorithm, filename, expected_hash", [ ("SHA-256", "tests/data/testfile_1.txt", "1b4f0e9851971998e732078544c96b36c3d01cedf7caa332359d6f1d83567014"), @@ -22,7 +22,7 @@ def test_default_config_values(setup_module): def test_config(): # test default config - c = get_module_lazy('hash_enricher').configs + c = ModuleFactory().get_module_lazy('hash_enricher').configs assert c["algorithm"]["default"] == "SHA-256" assert c["chunksize"]["default"] == 16000000 assert c["algorithm"]["choices"] == ["SHA-256", "SHA3-512"] diff --git a/tests/enrichers/test_meta_enricher.py b/tests/enrichers/test_meta_enricher.py index a09aaa9..476e25b 100644 --- a/tests/enrichers/test_meta_enricher.py +++ b/tests/enrichers/test_meta_enricher.py @@ -1,6 +1,5 @@ import datetime from datetime import datetime, timedelta, timezone -from unittest.mock import MagicMock, patch import pytest @@ -9,29 +8,21 @@ from auto_archiver.modules.meta_enricher import MetaEnricher @pytest.fixture -def mock_metadata(): +def mock_metadata(mocker): """Creates a mock Metadata object.""" - mock: Metadata = MagicMock(spec=Metadata) + mock: Metadata = mocker.MagicMock(spec=Metadata) mock.get_url.return_value = "https://example.com" mock.is_empty.return_value = False # Default to not empty mock.get_all_media.return_value = [] return mock @pytest.fixture -def mock_media(): +def mock_media(mocker): """Creates a mock Media object.""" - mock: Media = MagicMock(spec=Media) + mock: Media = mocker.MagicMock(spec=Media) mock.filename = "mock_file.txt" return mock -@pytest.fixture -def metadata(): - m = Metadata() - m.set_url("https://example.com") - m.set_title("Test Title") - m.set_content("Test Content") - return m - @pytest.fixture(autouse=True) def meta_enricher(setup_module): @@ -90,14 +81,14 @@ def test_enrich_file_sizes_no_media(meta_enricher, metadata): assert metadata.get("total_size") == "0.0 bytes" -def test_enrich_archive_duration(meta_enricher, metadata): +def test_enrich_archive_duration(meta_enricher, metadata, mocker): # Set fixed "processed at" time in the past processed_at = datetime.now(timezone.utc) - timedelta(minutes=10, seconds=30) metadata.set("_processed_at", processed_at) # patch datetime - with patch("datetime.datetime") as mock_datetime: - mock_now = datetime.now(timezone.utc) - mock_datetime.now.return_value = mock_now - meta_enricher.enrich_archive_duration(metadata) + mock_datetime = mocker.patch("datetime.datetime") + mock_now = datetime.now(timezone.utc) + mock_datetime.now.return_value = mock_now + meta_enricher.enrich_archive_duration(metadata) assert metadata.get("archive_duration_seconds") == 630 \ No newline at end of file diff --git a/tests/enrichers/test_metadata_enricher.py b/tests/enrichers/test_metadata_enricher.py new file mode 100644 index 0000000..888837d --- /dev/null +++ b/tests/enrichers/test_metadata_enricher.py @@ -0,0 +1,88 @@ + +import pytest + +from auto_archiver.core import Media + + +@pytest.fixture +def mock_media(mocker): + """Creates a mock Media object.""" + mock: Media = mocker.MagicMock(spec=Media) + mock.filename = "mock_file.txt" + return mock + + +@pytest.fixture +def enricher(setup_module, mock_binary_dependencies): + return setup_module("metadata_enricher", {}) + + +@pytest.mark.parametrize( + "output,expected", + [ + ("Key1: Value1\nKey2: Value2", {"Key1": "Value1", "Key2": "Value2"}), + ("InvalidLine", {}), + ("", {}), + ], +) +def test_get_metadata(enricher, output, expected, mocker): + mock_run = mocker.patch("subprocess.run") + mock_run.return_value.stdout = output + mock_run.return_value.stderr = "" + mock_run.return_value.returncode = 0 + + result = enricher.get_metadata("test.jpg") + assert result == expected + mock_run.assert_called_once_with( + ["exiftool", "test.jpg"], capture_output=True, text=True + ) + + +def test_get_metadata_exiftool_not_found(enricher, mocker): + mock_run = mocker.patch("subprocess.run") + mock_run.side_effect = FileNotFoundError + result = enricher.get_metadata("test.jpg") + assert result == {} + + +def test_enrich_sets_metadata(enricher, mocker): + media1 = mocker.Mock(filename="img1.jpg") + media2 = mocker.Mock(filename="img2.jpg") + metadata = mocker.Mock() + metadata.media = [media1, media2] + enricher.get_metadata = lambda f: {"key": "value"} if f == "img1.jpg" else {} + + enricher.enrich(metadata) + + media1.set.assert_called_once_with("metadata", {"key": "value"}) + media2.set.assert_not_called() + assert metadata.media == [media1, media2] + + +def test_enrich_empty_media(enricher, mocker): + metadata = mocker.Mock() + metadata.media = [] + # Should not raise errors + enricher.enrich(metadata) + + +def test_get_metadata_error_handling(enricher, mocker): + mocker.patch("subprocess.run", side_effect=Exception("Test error")) + mock_log = mocker.patch("loguru.logger.error") + result = enricher.get_metadata("test.jpg") + assert result == {} + assert "Error occurred: " in mock_log.call_args[0][0] + + +def test_metadata_pickle(enricher, unpickle, mocker): + mock_run = mocker.patch("subprocess.run") + # Uses pickled values + mock_run.return_value = unpickle("metadata_enricher_exif.pickle") + metadata = unpickle("metadata_enricher_ytshort_input.pickle") + expected = unpickle("metadata_enricher_ytshort_expected.pickle") + enricher.enrich(metadata) + expected_media = expected.media + actual_media = metadata.media + assert len(expected_media) == len(actual_media) + assert actual_media[0].properties.get("metadata") == expected_media[0].properties.get("metadata") + diff --git a/tests/enrichers/test_pdq_hash_enricher.py b/tests/enrichers/test_pdq_hash_enricher.py new file mode 100644 index 0000000..9653734 --- /dev/null +++ b/tests/enrichers/test_pdq_hash_enricher.py @@ -0,0 +1,78 @@ +import pytest +from PIL import UnidentifiedImageError + +from auto_archiver.core import Metadata, Media +from auto_archiver.modules.pdq_hash_enricher import PdqHashEnricher + + +@pytest.fixture +def enricher(setup_module): + return setup_module("pdq_hash_enricher", {}) + + +@pytest.fixture +def metadata_with_images(): + m = Metadata() + m.set_url("https://example.com") + m.add_media(Media(filename="image1.jpg", key="image1")) + m.add_media(Media(filename="image2.jpg", key="image2")) + return m + + +def test_successful_enrich(metadata_with_images, mocker): + with ( + mocker.patch("pdqhash.compute", return_value=([1, 0, 1, 0] * 64, 100)), + mocker.patch("PIL.Image.open"), + mocker.patch.object(Media, "is_image", return_value=True) as mock_is_image, + ): + enricher = PdqHashEnricher() + enricher.enrich(metadata_with_images) + + # Ensure the hash is set for image media + for media in metadata_with_images.media: + assert media.get("pdq_hash") is not None + + +def test_enrich_skip_non_image(metadata_with_images, mocker): + mocker.patch.object(Media, "is_image", return_value=False) + mock_pdq = mocker.patch("pdqhash.compute") + + enricher = PdqHashEnricher() + enricher.enrich(metadata_with_images) + mock_pdq.assert_not_called() + + +def test_enrich_handles_corrupted_image(metadata_with_images, mocker): + mocker.patch("PIL.Image.open", side_effect=UnidentifiedImageError("Corrupted image")) + mock_pdq = mocker.patch("pdqhash.compute") + mock_logger = mocker.patch("loguru.logger.error") + enricher = PdqHashEnricher() + enricher.enrich(metadata_with_images) + + assert mock_logger.call_count == len(metadata_with_images.media) + mock_pdq.assert_not_called() + + +@pytest.mark.parametrize( + "media_id, should_have_hash", + [ + ("screenshot", False), + ("warc-file-123", False), + ("regular-image", True), + ] +) +def test_enrich_excludes_by_filetype(media_id, should_have_hash, mocker): + metadata = Metadata() + metadata.set_url("https://example.com") + metadata.add_media(Media(filename="image.jpg").set("id", media_id)) + + mocker.patch("pdqhash.compute", return_value=([1, 0, 1, 0] * 64, 100)) + mocker.patch("PIL.Image.open") + mocker.patch.object(Media, "is_image", return_value=True) + + enricher = PdqHashEnricher() + enricher.enrich(metadata) + + media_item = metadata.media[0] + assert (media_item.get("pdq_hash") is not None) == should_have_hash + diff --git a/tests/enrichers/test_screenshot_enricher.py b/tests/enrichers/test_screenshot_enricher.py new file mode 100644 index 0000000..25ca51d --- /dev/null +++ b/tests/enrichers/test_screenshot_enricher.py @@ -0,0 +1,195 @@ +import base64 + +import pytest +from selenium.common.exceptions import TimeoutException + +from auto_archiver.core import Metadata, Media +from auto_archiver.modules.screenshot_enricher import ScreenshotEnricher + + +@pytest.fixture +def mock_selenium_env(mocker): + """Patches Selenium calls and driver checks in one place.""" + + # Patch external dependencies + mock_which = mocker.patch("shutil.which") + mock_driver_class = mocker.patch("auto_archiver.utils.webdriver.CookieSettingDriver") + mock_binary_paths = mocker.patch("selenium.webdriver.common.selenium_manager.SeleniumManager.binary_paths") + mock_is_file = mocker.patch("pathlib.Path.is_file", return_value=True) + mock_popen = mocker.patch("subprocess.Popen") + mock_is_connectable = mocker.patch("selenium.webdriver.common.service.Service.is_connectable", return_value=True) + mock_firefox_options = mocker.patch("selenium.webdriver.FirefoxOptions") + # Define side effect for `shutil.which` + def mock_which_side_effect(dep): + return "/mock/geckodriver" if dep == "geckodriver" else None + mock_which.side_effect = mock_which_side_effect + + # Mock binary paths + mock_binary_paths.return_value = { + "driver_path": "/mock/driver", + "browser_path": "/mock/browser", + } + # Mock `subprocess.Popen` + mock_proc = mocker.MagicMock() + mock_proc.poll.return_value = None + mock_popen.return_value = mock_proc + # Mock `CookieSettingDriver` + mock_driver = mocker.MagicMock() + mock_driver_class.return_value = mock_driver + # Mock `FirefoxOptions` + mock_options_instance = mocker.MagicMock() + mock_firefox_options.return_value = mock_options_instance + yield mock_driver, mock_driver_class, mock_options_instance + + +@pytest.fixture +def common_patches(tmp_path, mocker): + """Patches common utilities used across multiple tests.""" + mocker.patch("auto_archiver.utils.url.is_auth_wall", return_value=False) + mocker.patch("os.path.join", return_value=str(tmp_path / "test.png")) + mocker.patch("time.sleep") + yield + + +@pytest.fixture +def screenshot_enricher(setup_module, mock_binary_dependencies) -> ScreenshotEnricher: + configs: dict = { + "width": 1280, + "height": 720, + "timeout": 60, + "sleep_before_screenshot": 4, + "http_proxy": "", + "save_to_pdf": "False", + "print_options": {}, + } + return setup_module("screenshot_enricher", configs) + + +@pytest.fixture +def metadata_with_video(): + m = Metadata() + m.set_url("https://example.com") + m.add_media(Media(filename="video.mp4").set("id", "video1")) + return m + + +def test_enrich_adds_screenshot( + screenshot_enricher, + metadata_with_video, + mock_selenium_env, + common_patches, + tmp_path, +): + mock_driver, mock_driver_class, mock_options_instance = mock_selenium_env + screenshot_enricher.enrich(metadata_with_video) + mock_driver_class.assert_called_once_with( + cookies=None, + cookiejar=None, + facebook_accept_cookies=False, + options=mock_options_instance, + ) + # Verify the actual calls on the returned mock_driver + mock_driver.get.assert_called_once_with("https://example.com") + mock_driver.save_screenshot.assert_called_once_with(str(tmp_path / "test.png")) + # Check that the media was added (2 = original video + screenshot) + assert len(metadata_with_video.media) == 2 + assert metadata_with_video.media[1].properties.get("id") == "screenshot" + + +@pytest.mark.parametrize( + "url,is_auth", + [ + ("https://example.com", False), + ("https://private.com", True), + ], +) +def test_enrich_auth_wall( + screenshot_enricher, + metadata_with_video, + mock_selenium_env, + common_patches, + url, + is_auth, + mocker +): + # Testing with and without is_auth_wall + mock_driver, mock_driver_class, _ = mock_selenium_env + mocker.patch("auto_archiver.utils.url.is_auth_wall", return_value=is_auth) + metadata_with_video.set_url(url) + screenshot_enricher.enrich(metadata_with_video) + + if is_auth: + mock_driver.get.assert_not_called() + assert len(metadata_with_video.media) == 1 + assert metadata_with_video.media[0].properties.get("id") == "video1" + else: + mock_driver.get.assert_called_once_with(url) + assert len(metadata_with_video.media) == 2 + assert metadata_with_video.media[1].properties.get("id") == "screenshot" + + +def test_handle_timeout_exception( + screenshot_enricher, metadata_with_video, mock_selenium_env, mocker +): + mock_driver, mock_driver_class, mock_options_instance = mock_selenium_env + + mock_driver.get.side_effect = TimeoutException + mock_log = mocker.patch("loguru.logger.info") + screenshot_enricher.enrich(metadata_with_video) + mock_log.assert_called_once_with("TimeoutException loading page for screenshot") + assert len(metadata_with_video.media) == 1 + + +def test_handle_general_exception( + screenshot_enricher, metadata_with_video, mock_selenium_env, mocker +): + """Test proper handling of unexpected general exceptions""" + mock_driver, mock_driver_class, mock_options_instance = mock_selenium_env + # Simulate a generic exception when save_screenshot is called + mock_driver.get.return_value = None + mock_driver.save_screenshot.side_effect = Exception("Unexpected Error") + + mock_log = mocker.patch("loguru.logger.error") + screenshot_enricher.enrich(metadata_with_video) + # Verify that the exception was logged with the log + mock_log.assert_called_once_with( + "Got error while loading webdriver for screenshot enricher: Unexpected Error" + ) + # And no new media was added due to the error + assert len(metadata_with_video.media) == 1 + + +def test_pdf_creation(mocker, screenshot_enricher, metadata_with_video, mock_selenium_env): + """Test PDF creation when save_to_pdf is enabled""" + mock_driver, mock_driver_class, mock_options_instance = mock_selenium_env + # Override the save_to_pdf option + screenshot_enricher.save_to_pdf = True + # Mock the print_page method to return base64-encoded content + mock_driver.print_page.return_value = base64.b64encode(b"fake_pdf_content").decode("utf-8") + # Patch functions with mocker + mock_os_path_join = mocker.patch("os.path.join", side_effect=lambda *args: f"{args[-1]}") + mock_random_str = mocker.patch( + "auto_archiver.modules.screenshot_enricher.screenshot_enricher.random_str", + return_value="fixed123", + ) + mock_open = mocker.patch("builtins.open", new_callable=mocker.mock_open) + mock_log_error = mocker.patch("loguru.logger.error") + + screenshot_enricher.enrich(metadata_with_video) + # Verify screenshot and PDF creation + mock_driver.save_screenshot.assert_called_once() + mock_driver.print_page.assert_called_once_with(mock_driver.print_options) + # Check that PDF file was opened and written + mock_open.assert_any_call("pdf_fixed123.pdf", "wb") + + # Ensure both screenshot and PDF were added as media + assert len(metadata_with_video.media) == 3 + assert metadata_with_video.media[1].properties.get("id") == "screenshot" + assert metadata_with_video.media[2].properties.get("id") == "pdf" + + +@pytest.fixture(autouse=True) +def cleanup_files(tmp_path): + yield + for file in tmp_path.iterdir(): + file.unlink() diff --git a/tests/enrichers/test_ssl_enricher.py b/tests/enrichers/test_ssl_enricher.py new file mode 100644 index 0000000..eb7ba6b --- /dev/null +++ b/tests/enrichers/test_ssl_enricher.py @@ -0,0 +1,54 @@ +import ssl +import pytest + +from auto_archiver.core import Metadata, Media + + +@pytest.fixture +def enricher(setup_module): + configs: dict = { + "skip_when_nothing_archived": "True", + } + return setup_module("ssl_enricher", configs) + + +@pytest.fixture +def metadata(): + m = Metadata() + m.set_url("https://example.com") + m.add_media(Media("tests/data/testfile_1.txt")) + m.add_media(Media("tests/data/testfile_2.txt")) + return m + + +def test_http_raises(metadata, enricher): + metadata.set_url("http://example.com") + with pytest.raises(AssertionError) as exc_info: + enricher.enrich(metadata) + assert "Invalid URL scheme" in str(exc_info.value) + + +def test_empty_metadata(metadata, enricher): + metadata.media = [] + assert enricher.enrich(metadata) is None + + +def test_ssl_enrich(metadata, enricher, mocker): + mocker.patch("ssl.get_server_certificate", return_value="TEST_CERT") + mock_file = mocker.patch("builtins.open", mocker.mock_open()) + media_len_before = len(metadata.media) + enricher.enrich(metadata) + + ssl.get_server_certificate.assert_called_once_with(("example.com", 443)) + mock_file.assert_called_once_with(f"{enricher.tmp_dir}/example-com.pem", "w") + mock_file().write.assert_called_once_with("TEST_CERT") + assert len(metadata.media) == media_len_before + 1 + # Ensure the certificate is added to metadata + assert any(media.filename.endswith("example-com.pem") for media in metadata.media) + + +def test_ssl_error_handling(enricher, metadata, mocker): + mocker.patch("ssl.get_server_certificate", side_effect=ssl.SSLError("SSL error")) + with pytest.raises(ssl.SSLError, match="SSL error"): + enricher.enrich(metadata) + diff --git a/tests/enrichers/test_thumbnail_enricher.py b/tests/enrichers/test_thumbnail_enricher.py new file mode 100644 index 0000000..effc25e --- /dev/null +++ b/tests/enrichers/test_thumbnail_enricher.py @@ -0,0 +1,148 @@ +import pytest +from auto_archiver.core import Metadata, Media +from auto_archiver.modules.thumbnail_enricher import ThumbnailEnricher + + +@pytest.fixture +def thumbnail_enricher(setup_module, mock_binary_dependencies) -> ThumbnailEnricher: + config: dict = { + "thumbnails_per_minute": 60, + "max_thumbnails": 4, + } + return setup_module("thumbnail_enricher", config) + + +@pytest.fixture +def metadata_with_video(): + m = Metadata() + m.set_url("https://example.com") + m.add_media(Media(filename="video.mp4").set("id", "video1")) + return m + + +@pytest.fixture +def mock_ffmpeg_environment(mocker): + # Mocking all the ffmpeg calls in one place + mock_ffmpeg_input = mocker.patch("ffmpeg.input") + mock_makedirs = mocker.patch("os.makedirs") + mocker.patch.object(Media, "is_video", return_value=True), + mock_probe = mocker.patch( + "ffmpeg.probe", + return_value={ + "streams": [ + {"codec_type": "video", "duration": "120"} + ] # Default 2-minute duration, but can override in tests + }, + ) + mock_output = mocker.MagicMock() + mock_ffmpeg_input.return_value.filter.return_value.output.return_value = ( + mock_output + ) + + return { + "mock_ffmpeg_input": mock_ffmpeg_input, + "mock_makedirs": mock_makedirs, + "mock_output": mock_output, + "mock_probe": mock_probe, + } + + +@pytest.mark.parametrize("thumbnails_per_minute, max_thumbnails, expected_count", [ + (10, 5, 5), # Capped at max_thumbnails + (1, 10, 2), # Less than max_thumbnails + (60, 7, 7), # Matches exactly +]) +def test_enrich_thumbnail_limits( + thumbnail_enricher, metadata_with_video, mock_ffmpeg_environment, + thumbnails_per_minute, max_thumbnails, expected_count +): + thumbnail_enricher.thumbnails_per_minute = thumbnails_per_minute + thumbnail_enricher.max_thumbnails = max_thumbnails + + thumbnail_enricher.enrich(metadata_with_video) + + assert mock_ffmpeg_environment["mock_output"].run.call_count == expected_count + thumbnails = metadata_with_video.media[0].get("thumbnails") + assert len(thumbnails) == expected_count + +def test_enrich_handles_probe_failure(thumbnail_enricher, metadata_with_video, mocker): + + mocker.patch("ffmpeg.probe", side_effect=Exception("Probe error")) + mocker.patch("os.makedirs") + mock_logger = mocker.patch("loguru.logger.error") + mocker.patch.object(Media, "is_video", return_value=True) + + thumbnail_enricher.enrich(metadata_with_video) + # Ensure error was logged + mock_logger.assert_called_with( + f"error getting duration of video video.mp4: Probe error" + ) + # Ensure no thumbnails were created + thumbnails = metadata_with_video.media[0].get("thumbnails") + assert thumbnails is None + + +def test_enrich_skips_non_video_files(thumbnail_enricher, metadata_with_video, mocker): + mocker.patch.object(Media, "is_video", return_value=False) + mock_ffmpeg = mocker.patch("ffmpeg.input") + thumbnail_enricher.enrich(metadata_with_video) + mock_ffmpeg.assert_not_called() + + +@pytest.mark.parametrize("thumbnails_per_minute,max_thumbnails,expected_count", [ + (60, 5, 5), # caught by max + (60, 20, 10), # caught by t/min + (0, 20, 1), # test min caught (1) + (11, 20, 1), # test min caught (1) + (12, 20, 2), # test caught by t/min +]) +def test_enrich_handles_short_video( + thumbnail_enricher, metadata_with_video, mock_ffmpeg_environment, thumbnails_per_minute, max_thumbnails, expected_count, mocker +): + # override mock duration + fake_duration = 10 + mocker.patch( + "ffmpeg.probe", + return_value={ "streams": [{"codec_type": "video", "duration": str(fake_duration)}]}, + ) + thumbnail_enricher.thumbnails_per_minute = thumbnails_per_minute + thumbnail_enricher.max_thumbnails = max_thumbnails + + thumbnail_enricher.enrich(metadata_with_video) + assert mock_ffmpeg_environment["mock_output"].run.call_count == expected_count + thumbnails = metadata_with_video.media[0].get("thumbnails") + assert len(thumbnails) == expected_count + + +def test_uses_existing_duration( + thumbnail_enricher, metadata_with_video, mock_ffmpeg_environment +): + metadata_with_video.media[0].set("duration", 60) + thumbnail_enricher.enrich(metadata_with_video) + mock_ffmpeg_environment["mock_probe"].assert_not_called() + assert mock_ffmpeg_environment["mock_output"].run.call_count == 4 + + +def test_enrich_metadata_structure(thumbnail_enricher, metadata_with_video, mock_ffmpeg_environment, mocker): + fake_duration = 120 + mocker.patch("ffmpeg.probe", return_value={'streams': [{'codec_type': 'video', 'duration': str(fake_duration)}]}) + thumbnail_enricher.thumbnails_per_minute = 2 + thumbnail_enricher.max_thumbnails = 4 + + thumbnail_enricher.enrich(metadata_with_video) + + media_item = metadata_with_video.media[0] + thumbnails = media_item.get("thumbnails") + + # Assert normal metadata + assert media_item.get("id") == "video1" + assert media_item.get("duration") == fake_duration + # Evenly spaced timestamps + expected_timestamps = ["24.000s", "48.000s", "72.000s", "96.000s"] + assert thumbnails is not None + assert len(thumbnails) == 4 + + for index, thumbnail in enumerate(thumbnails): + assert thumbnail.filename is not None + assert thumbnail.properties.get("id") == f"thumbnail_{index}" + assert thumbnail.properties.get("timestamp") == expected_timestamps[index] diff --git a/tests/enrichers/test_wacz_enricher.py b/tests/enrichers/test_wacz_enricher.py new file mode 100644 index 0000000..d55733d --- /dev/null +++ b/tests/enrichers/test_wacz_enricher.py @@ -0,0 +1,112 @@ +import os +from zipfile import ZipFile + +import pytest + +from auto_archiver.core import Metadata, Media + + +@pytest.fixture +def wacz_enricher(setup_module, mock_binary_dependencies): + configs: dict = { + "profile": None, + "docker_commands": None, + "timeout": 120, + "extract_media": False, + "extract_screenshot": True, + "socks_proxy_host": None, + "socks_proxy_port": None, + "proxy_server": None, + } + wacz = setup_module("wacz_enricher", configs) + return wacz + + +def test_setup_without_docker(wacz_enricher, mocker): + mocker.patch.dict(os.environ, {"RUNNING_IN_DOCKER": "1"}, clear=True) + wacz_enricher.setup() + assert not wacz_enricher.docker_in_docker + + +def test_setup_with_docker(wacz_enricher, mocker): + mocker.patch.dict(os.environ, {"WACZ_ENABLE_DOCKER": "1"}, clear=True) + wacz_enricher.setup() + assert wacz_enricher.use_docker + + +def test_already_ran(wacz_enricher, metadata, mocker): + metadata.add_media(Media("test.wacz"), id="browsertrix") + mock_log = mocker.patch("loguru.logger.info") + assert wacz_enricher.enrich(metadata) is True + assert "WACZ enricher had already been executed" in mock_log.call_args[0][0] + + +def test_basic_call_execution(wacz_enricher, mocker): + mock_run = mocker.patch("subprocess.run") + mock_run.return_value = mocker.Mock(returncode=0) + metadata = Metadata().set_url("https://example.com") + wacz_enricher.enrich(metadata) + assert mock_run.called + # Checks that the url is passed to the cmd + assert "--url https://example.com" in " ".join(mock_run.call_args[0][0]) + + +def test_download_success(wacz_enricher, mocker) -> None: + """Test download returns metadata on successful enrichment.""" + basic_metadata = Metadata().set_url("https://example.com") + mocker.patch.object(wacz_enricher, "enrich", return_value=True) + result = wacz_enricher.download(basic_metadata) + assert result is not None + assert isinstance(result, Metadata) + assert result.status == "wacz: success" + + +def test_enrich_already_executed(wacz_enricher, mocker) -> None: + """Test enrich if already executed.""" + mock_log = mocker.patch("loguru.logger.info") + metadata = Metadata().set_url("https://example.com") + media = Media(filename="some_file.wacz") + metadata.add_media(media, id="browsertrix") + result = wacz_enricher.enrich(metadata) + assert result is True + assert "WACZ enricher had already been executed:" in mock_log.call_args[0][0] + + +def test_enrich_subprocess_exception(wacz_enricher, mocker, tmp_path) -> None: + """Test enrich returns False when subprocess fails.""" + wacz_enricher.tmp_dir = str(tmp_path) + wacz_enricher.extract_media = False + wacz_enricher.extract_screenshot = True + mocker.patch("auto_archiver.utils.misc.random_str", return_value="TESTCOL") + mocker.patch("subprocess.run", side_effect=Exception("fail")) + basic_metadata = Metadata().set_url("https://example.com") + result = wacz_enricher.enrich(basic_metadata) + assert result is False + + +def test_extract_media(wacz_enricher, metadata, tmp_path, mocker) -> None: + """Test extract_media_from_wacz extracts screenshot media.""" + wacz_enricher.tmp_dir = str(tmp_path) + + # Create a *real* zip file so ZipFile won't fail. + wacz_file = tmp_path / "dummy.wacz" + with ZipFile(wacz_file, "w") as zf: + zf.writestr("dummy.txt", "test content") + + mocker.patch("os.listdir", return_value=[]) + warc_data = ( + b"WARC/1.0\r\n" + b"WARC-Type: resource\r\n" + b"Content-Type: image/png\r\n" + b"WARC-Target-URI: http://example.com/image.png\r\n" + b"Content-Length: 12\r\n" + b"\r\n" + b"image-bytes" + b"\r\n\r\nWARC/1.0\r\n\r\n" + ) + mock_file = mocker.mock_open(read_data=warc_data) + mocker.patch("builtins.open", mock_file) + metadata.add_media(Media("something.wacz"), "browsertrix") + wacz_enricher.extract_media_from_wacz(metadata, str(wacz_file)) + assert len(metadata.media) == 2 + assert metadata.media[1].properties.get("id") == "browsertrix-screenshot" diff --git a/tests/enrichers/test_wayback_enricher.py b/tests/enrichers/test_wayback_enricher.py new file mode 100644 index 0000000..88f4662 --- /dev/null +++ b/tests/enrichers/test_wayback_enricher.py @@ -0,0 +1,168 @@ +import json +import requests +import pytest +from auto_archiver.modules.wayback_extractor_enricher import WaybackExtractorEnricher +from auto_archiver.core import Metadata + + +@pytest.fixture +def mock_is_auth_wall(mocker): + """Fixture to mock is_auth_wall behavior.""" + def _mock_is_auth_wall(return_value: bool): + return mocker.patch("auto_archiver.utils.url.is_auth_wall", return_value=return_value) + return _mock_is_auth_wall + +@pytest.fixture +def mock_post_success(mocker): + """Fixture to mock POST requests with a successful response.""" + def _mock_post(json_data: dict = None, status_code: int = 200): + json_data = json_data or {"job_id": "job123"} + resp = mocker.Mock(status_code=status_code) + resp.json.return_value = json_data + return mocker.patch("requests.post", return_value=resp) + return _mock_post + +@pytest.fixture +def mock_get_success(mocker): + """Fixture to mock GET requests returning a completed archive status.""" + def _mock_get(json_data: dict = None, status_code: int = 200): + json_data = json_data or { + "status": "success", + "timestamp": "20250101010101", + "original_url": "https://example.com" + } + resp = mocker.Mock(status_code=status_code) + resp.json.return_value = json_data + return mocker.patch("requests.get", return_value=resp) + return _mock_get + +@pytest.fixture +def wayback_extractor_enricher(setup_module) -> WaybackExtractorEnricher: + configs: dict = { + "timeout": 5, + "if_not_archived_within": None, + "key": "somekey", + "secret": "secret", + "proxy_http": None, + "proxy_https": None, + } + return setup_module("wayback_extractor_enricher", configs) + + +def test_download_success( + wayback_extractor_enricher, + mock_is_auth_wall, + mock_post_success, + mock_get_success +): + mock_is_auth_wall(False) + mock_post_success() + mock_get_success() + # Basic metadata to allow merge + metadata = Metadata().set_url("https://example.com") + result = wayback_extractor_enricher.download(metadata) + assert result.get("wayback") == "https://web.archive.org/web/20250101010101/https://example.com" + +def test_enrich_auth_wall(wayback_extractor_enricher, metadata, mock_is_auth_wall): + mock_is_auth_wall(True) + result = wayback_extractor_enricher.enrich(metadata) + assert result is None + +def test_enrich_already_enriched(wayback_extractor_enricher, metadata): + metadata.set("wayback", "existing") + result = wayback_extractor_enricher.enrich(metadata) + assert result is True + +def test_enrich_post_failure( + wayback_extractor_enricher, + metadata, + mock_is_auth_wall, + mock_post_success +): + mock_is_auth_wall(False) + mock_post_success(json_data={"error": "server error"}, status_code=500) + result = wayback_extractor_enricher.enrich(metadata) + assert result is False + assert "Internet archive failed with status of 500" in metadata.get("wayback") + +def test_enrich_post_json_decode_error( + wayback_extractor_enricher, + metadata, + mock_is_auth_wall, + mocker +): + mock_is_auth_wall(False) + resp = mocker.Mock(status_code=200) + resp.json.side_effect = json.decoder.JSONDecodeError("msg", "doc", 0) + resp.text = "invalid json" + mocker.patch("requests.post", return_value=resp) + assert wayback_extractor_enricher.enrich(metadata) is False + +def test_enrich_no_job_id( + wayback_extractor_enricher, + metadata, + mock_is_auth_wall, + mock_post_success +): + mock_is_auth_wall(False) + mock_post_success(json_data={}) + assert wayback_extractor_enricher.enrich(metadata) is False + +def test_enrich_get_success( + wayback_extractor_enricher, + metadata, + mock_is_auth_wall, + mock_post_success, + mock_get_success +): + mock_is_auth_wall(False) + mock_post_success() + mock_get_success() + assert wayback_extractor_enricher.enrich(metadata) is True + assert metadata.get("wayback") == "https://web.archive.org/web/20250101010101/https://example.com" + assert metadata.get("check wayback") == "https://web.archive.org/web/*/https://example.com" + +def test_enrich_get_failure( + wayback_extractor_enricher, + metadata, + mock_is_auth_wall, + mock_post_success, + mock_get_success +): + mock_is_auth_wall(False) + mock_post_success() + mock_get_success(json_data={"status": "failed"}, status_code=400) + assert wayback_extractor_enricher.enrich(metadata) is False + +def test_enrich_get_request_exception( + wayback_extractor_enricher, + metadata, + mock_is_auth_wall, + mock_post_success, + mocker +): + mock_is_auth_wall(False) + mock_post_success() + mocker.patch("requests.get", side_effect=requests.exceptions.RequestException("error")) + mocker.patch("time.sleep", return_value=None) + # check it still enriches the job_id information + assert wayback_extractor_enricher.enrich(metadata) is True + assert metadata.get("wayback").get("job_id") == "job123" + +def test_enrich_get_json_decode_error( + wayback_extractor_enricher, + metadata, + mock_is_auth_wall, + mock_post_success, + mocker +): + mock_is_auth_wall(False) + mock_post_success() + resp = mocker.Mock() + resp.json.side_effect = json.decoder.JSONDecodeError("msg", "doc", 0) + resp.text = "invalid json" + mocker.patch("requests.get", return_value=resp) + mocker.patch("time.sleep", return_value=None) + # check it still enriches the job_id information + assert wayback_extractor_enricher.enrich(metadata) is True + assert metadata.get("wayback").get("job_id") == "job123" diff --git a/tests/enrichers/test_whisper_enricher.py b/tests/enrichers/test_whisper_enricher.py new file mode 100644 index 0000000..ee1844a --- /dev/null +++ b/tests/enrichers/test_whisper_enricher.py @@ -0,0 +1,133 @@ +import pytest + +from auto_archiver.core import Metadata, Media +from auto_archiver.modules.s3_storage import S3Storage +from auto_archiver.modules.whisper_enricher import WhisperEnricher + +TEST_S3_URL = "http://cdn.example.com/test.mp4" + + +@pytest.fixture +def enricher(mocker): + """Fixture with mocked S3 and API dependencies""" + config = { + "api_endpoint": "http://testapi", + "api_key": "whisper-key", + "include_srt": False, + "timeout": 5, + "action": "translate", + "steps": {"storages": ["s3_storage"]} + } + mock_s3 = mocker.MagicMock(spec=S3Storage) + mock_s3.get_cdn_url.return_value = TEST_S3_URL + instance = WhisperEnricher() + instance.name = "whisper_enricher" + instance.display_name = "Whisper Enricher" + instance.config_setup({instance.name: config}) + # bypassing the setup method and mocking S3 setup + instance.stores = config['steps']['storages'] + instance.s3 = mock_s3 + yield instance, mock_s3 + + +@pytest.fixture +def metadata(): + metadata = Metadata() + metadata.set_url("http://test.url") + metadata.set_title("test title") + return metadata + + +@pytest.fixture +def mock_requests(mocker): + mock_requests = mocker.patch("auto_archiver.modules.whisper_enricher.whisper_enricher.requests") + mock_response = mocker.MagicMock() + mock_response.status_code = 201 + mock_response.json.return_value = {"id": "job123"} + mock_requests.post.return_value = mock_response + yield mock_requests + + +def test_successful_job_submission(enricher, metadata, mock_requests, mocker): + """Test successful media processing with S3 configured""" + whisper, mock_s3 = enricher + # Configure mock S3 URL to match test expectation + mock_s3.get_cdn_url.return_value = TEST_S3_URL + + # Create test media with matching CDN URL + m = Media("test.mp4") + m.mimetype = "video/mp4" + m.add_url(mock_s3.get_cdn_url.return_value) + metadata.media = [m] + + # Mock the complete API interaction chain + mock_status_response = mocker.MagicMock() + mock_status_response.status_code = 200 + mock_status_response.json.return_value = { + "status": "success", + "meta": {} + } + mock_artifacts_response = mocker.MagicMock() + mock_artifacts_response.status_code = 200 + mock_artifacts_response.json.return_value = [{ + "data": [{"start": 0, "end": 5, "text": "test transcript"}] + }] + # Set up mock response sequence + mock_requests.get.side_effect = [ + mock_status_response, # First call: status check + mock_artifacts_response # Second call: artifacts check + ] + + # Run enrichment (without opening file) + whisper.enrich(metadata) + # Check API interactions + mock_requests.post.assert_called_once_with( + "http://testapi/jobs", + json={"url": "http://cdn.example.com/test.mp4", "type": "translate"}, + headers={"Authorization": "Bearer whisper-key"} + ) + # Verify job status checks + assert mock_requests.get.call_count == 2 + assert "artifact_0_text" in metadata.media[0].get("whisper_model") + assert metadata.media[0].get("whisper_model") == {'artifact_0_text': 'test transcript', + 'job_artifacts_check': 'http://testapi/jobs/job123/artifacts', + 'job_id': 'job123', + 'job_status_check': 'http://testapi/jobs/job123'} + + +def test_submit_job(enricher, mocker): + """Test job submission method""" + whisper, _ = enricher + m = Media("test.mp4") + m.add_url(TEST_S3_URL) + mock_requests = mocker.patch("auto_archiver.modules.whisper_enricher.whisper_enricher.requests") + mock_response = mocker.MagicMock() + mock_response.status_code = 201 + mock_response.json.return_value = {"id": "job123"} + mock_requests.post.return_value = mock_response + job_id = whisper.submit_job(m) + assert job_id == "job123" + + +def test_submit_raises_status(enricher, mocker): + whisper, _ = enricher + m = Media("test.mp4") + m.add_url(TEST_S3_URL) + mock_requests = mocker.patch("auto_archiver.modules.whisper_enricher.whisper_enricher.requests") + mock_response = mocker.MagicMock() + mock_response.status_code = 400 + mock_response.json.return_value = {"id": "job123"} + mock_requests.post.return_value = mock_response + with pytest.raises(AssertionError) as exc_info: + whisper.submit_job(m) + assert str(exc_info.value) == "calling the whisper api http://testapi returned a non-success code: 400" + + +# @pytest.mark.parametrize("test_url, status", ["http://cdn.example.com/test.mp4",]) +def test_submit_job_fails(enricher): + """Test assertion fails with non-S3 URL""" + whisper, mock_s3 = enricher + m = Media("test.mp4") + m.add_url("http://cdn.wrongurl.com/test.mp4") + with pytest.raises(AssertionError): + whisper.submit_job(m) diff --git a/tests/extractors/test_generic_extractor.py b/tests/extractors/test_generic_extractor.py index c70a51f..54f4d9c 100644 --- a/tests/extractors/test_generic_extractor.py +++ b/tests/extractors/test_generic_extractor.py @@ -9,6 +9,7 @@ import pytest from auto_archiver.modules.generic_extractor.generic_extractor import GenericExtractor from .test_extractor_base import TestExtractorBase +CI=os.getenv("GITHUB_ACTIONS", '') == 'true' class TestGenericExtractor(TestExtractorBase): """Tests Generic Extractor """ @@ -77,10 +78,11 @@ class TestGenericExtractor(TestExtractorBase): result = self.extractor.download(item) assert not result - + @pytest.mark.skipif(CI, reason="Currently no way to authenticate when on CI. Youtube (yt-dlp) doesn't support logging in with username/password.") @pytest.mark.download def test_youtube_download(self, make_item): # url https://www.youtube.com/watch?v=5qap5aO4i9A + item = make_item("https://www.youtube.com/watch?v=J---aiyznGQ") result = self.extractor.download(item) assert result.get_url() == "https://www.youtube.com/watch?v=J---aiyznGQ" @@ -114,6 +116,7 @@ class TestGenericExtractor(TestExtractorBase): result = self.extractor.download(item) assert result is not False + @pytest.mark.skipif(CI, reason="Truth social blocks GH actions.") @pytest.mark.download def test_truthsocial_download_video(self, make_item): item = make_item("https://truthsocial.com/@DaynaTrueman/posts/110602446619561579") @@ -121,18 +124,21 @@ class TestGenericExtractor(TestExtractorBase): assert len(result.media) == 1 assert result is not False + @pytest.mark.skipif(CI, reason="Truth social blocks GH actions.") @pytest.mark.download def test_truthsocial_download_no_media(self, make_item): item = make_item("https://truthsocial.com/@bbcnewa/posts/109598702184774628") result = self.extractor.download(item) assert result is not False + @pytest.mark.skipif(CI, reason="Truth social blocks GH actions.") @pytest.mark.download def test_truthsocial_download_poll(self, make_item): item = make_item("https://truthsocial.com/@CNN_US/posts/113724326568555098") result = self.extractor.download(item) assert result is not False + @pytest.mark.skipif(CI, reason="Truth social blocks GH actions.") @pytest.mark.download def test_truthsocial_download_single_image(self, make_item): item = make_item("https://truthsocial.com/@mariabartiromo/posts/113861116433335006") @@ -140,6 +146,7 @@ class TestGenericExtractor(TestExtractorBase): assert len(result.media) == 1 assert result is not False + @pytest.mark.skipif(CI, reason="Truth social blocks GH actions.") @pytest.mark.download def test_truthsocial_download_multiple_images(self, make_item): item = make_item("https://truthsocial.com/@trrth/posts/113861302149349135") diff --git a/tests/extractors/test_instagram_api_extractor.py b/tests/extractors/test_instagram_api_extractor.py index c119e3f..7eba8e9 100644 --- a/tests/extractors/test_instagram_api_extractor.py +++ b/tests/extractors/test_instagram_api_extractor.py @@ -1,15 +1,12 @@ from datetime import datetime -from typing import Type import pytest -from unittest.mock import patch, MagicMock from auto_archiver.core import Metadata from auto_archiver.modules.instagram_api_extractor.instagram_api_extractor import InstagramAPIExtractor from .test_extractor_base import TestExtractorBase - @pytest.fixture def mock_user_response(): return { @@ -115,74 +112,74 @@ class TestInstagramAPIExtractor(TestExtractorBase): # test gets text (metadata title) pass - def test_download_profile_basic(self, metadata, mock_user_response): + def test_download_profile_basic(self, metadata, mock_user_response, mocker): """Test basic profile download without full_profile""" - with patch.object(self.extractor, 'call_api') as mock_call, \ - patch.object(self.extractor, 'download_from_url') as mock_download: - # Mock API responses - mock_call.return_value = mock_user_response - mock_download.return_value = "profile.jpg" + mock_call = mocker.patch.object(self.extractor, 'call_api') + mock_download = mocker.patch.object(self.extractor, 'download_from_url') + # Mock API responses + mock_call.return_value = mock_user_response + mock_download.return_value = "profile.jpg" - result = self.extractor.download_profile(metadata, "test_user") - assert result.status == "insta profile: success" - assert result.get_title() == "Test User" - assert result.get("data") == self.extractor.cleanup_dict(mock_user_response["user"]) - # Verify profile picture download - mock_call.assert_called_once_with("v2/user/by/username", {"username": "test_user"}) - mock_download.assert_called_once_with("http://example.com/profile.jpg") - assert len(result.media) == 1 - assert result.media[0].filename == "profile.jpg" + result = self.extractor.download_profile(metadata, "test_user") + assert result.status == "insta profile: success" + assert result.get_title() == "Test User" + assert result.get("data") == self.extractor.cleanup_dict(mock_user_response["user"]) + # Verify profile picture download + mock_call.assert_called_once_with("v2/user/by/username", {"username": "test_user"}) + mock_download.assert_called_once_with("http://example.com/profile.jpg") + assert len(result.media) == 1 + assert result.media[0].filename == "profile.jpg" - def test_download_profile_full(self, metadata, mock_user_response, mock_story_response): + def test_download_profile_full(self, metadata, mock_user_response, mock_story_response, mocker): """Test full profile download with stories/posts""" - with patch.object(self.extractor, 'call_api') as mock_call, \ - patch.object(self.extractor, 'download_all_posts') as mock_posts, \ - patch.object(self.extractor, 'download_all_highlights') as mock_highlights, \ - patch.object(self.extractor, 'download_all_tagged') as mock_tagged, \ - patch.object(self.extractor, '_download_stories_reusable') as mock_stories: + mock_call = mocker.patch.object(self.extractor, 'call_api') + mock_posts = mocker.patch.object(self.extractor, 'download_all_posts') + mock_highlights = mocker.patch.object(self.extractor, 'download_all_highlights') + mock_tagged = mocker.patch.object(self.extractor, 'download_all_tagged') + mock_stories = mocker.patch.object(self.extractor, '_download_stories_reusable') - self.extractor.full_profile = True - mock_call.side_effect = [ - mock_user_response, - mock_story_response - ] - mock_highlights.return_value = None - mock_stories.return_value = mock_story_response - mock_posts.return_value = None - mock_tagged.return_value = None + self.extractor.full_profile = True + mock_call.side_effect = [ + mock_user_response, + mock_story_response + ] + mock_highlights.return_value = None + mock_stories.return_value = mock_story_response + mock_posts.return_value = None + mock_tagged.return_value = None - result = self.extractor.download_profile(metadata, "test_user") - assert result.get("#stories") == len(mock_story_response) - mock_posts.assert_called_once_with(result, "123") - assert "errors" not in result.metadata + result = self.extractor.download_profile(metadata, "test_user") + assert result.get("#stories") == len(mock_story_response) + mock_posts.assert_called_once_with(result, "123") + assert "errors" not in result.metadata - def test_download_profile_not_found(self, metadata): + def test_download_profile_not_found(self, metadata, mocker): """Test profile not found error""" - with patch.object(self.extractor, 'call_api') as mock_call: - mock_call.return_value = {"user": None} - with pytest.raises(AssertionError) as exc_info: - self.extractor.download_profile(metadata, "invalid_user") - assert "User invalid_user not found" in str(exc_info.value) + mock_call = mocker.patch.object(self.extractor, 'call_api') + mock_call.return_value = {"user": None} + with pytest.raises(AssertionError) as exc_info: + self.extractor.download_profile(metadata, "invalid_user") + assert "User invalid_user not found" in str(exc_info.value) - def test_download_profile_error_handling(self, metadata, mock_user_response): + def test_download_profile_error_handling(self, metadata, mock_user_response, mocker): """Test error handling in full profile mode""" - with (patch.object(self.extractor, 'call_api') as mock_call, \ - patch.object(self.extractor, 'download_all_highlights') as mock_highlights, \ - patch.object(self.extractor, 'download_all_tagged') as mock_tagged, \ - patch.object(self.extractor, '_download_stories_reusable') as stories_tagged, \ - patch.object(self.extractor, 'download_all_posts') as mock_posts - ): - self.extractor.full_profile = True - mock_call.side_effect = [ - mock_user_response, - Exception("Stories API failed"), - Exception("Posts API failed") - ] - mock_highlights.return_value = None - mock_tagged.return_value = None - stories_tagged.return_value = None - mock_posts.return_value = None - result = self.extractor.download_profile(metadata, "test_user") + mock_call = mocker.patch.object(self.extractor, 'call_api') + mock_highlights = mocker.patch.object(self.extractor, 'download_all_highlights') + mock_tagged = mocker.patch.object(self.extractor, 'download_all_tagged') + stories_tagged = mocker.patch.object(self.extractor, '_download_stories_reusable') + mock_posts = mocker.patch.object(self.extractor, 'download_all_posts') - assert result.is_success() - assert "Error downloading stories for test_user" in result.metadata["errors"] \ No newline at end of file + self.extractor.full_profile = True + mock_call.side_effect = [ + mock_user_response, + Exception("Stories API failed"), + Exception("Posts API failed") + ] + mock_highlights.return_value = None + mock_tagged.return_value = None + stories_tagged.return_value = None + mock_posts.return_value = None + result = self.extractor.download_profile(metadata, "test_user") + + assert result.is_success() + assert "Error downloading stories for test_user" in result.metadata["errors"] \ No newline at end of file diff --git a/tests/extractors/test_instagram_tbot_extractor.py b/tests/extractors/test_instagram_tbot_extractor.py index d7a1e53..f274728 100644 --- a/tests/extractors/test_instagram_tbot_extractor.py +++ b/tests/extractors/test_instagram_tbot_extractor.py @@ -1,94 +1,108 @@ import os -from typing import Type -from unittest.mock import patch, MagicMock import pytest from auto_archiver.core import Metadata -from auto_archiver.core.extractor import Extractor from auto_archiver.modules.instagram_tbot_extractor import InstagramTbotExtractor from tests.extractors.test_extractor_base import TestExtractorBase -TESTFILES = os.path.join(os.path.dirname(__file__), "testfiles") - @pytest.fixture -def session_file(tmpdir): - """Fixture to create a test session file.""" - session_file = os.path.join(tmpdir, "test_session.session") - with open(session_file, "w") as f: - f.write("mock_session_data") - return session_file.replace(".session", "") +def patch_extractor_methods(request, setup_module, mocker): + mocker.patch.object(InstagramTbotExtractor, '_prepare_session_file', return_value=None) + mocker.patch.object(InstagramTbotExtractor, '_initialize_telegram_client', return_value=None) + yield -@pytest.fixture(autouse=True) -def patch_extractor_methods(request, setup_module): - with patch.object(InstagramTbotExtractor, '_prepare_session_file', return_value=None), \ - patch.object(InstagramTbotExtractor, '_initialize_telegram_client', return_value=None): - if hasattr(request, 'cls') and hasattr(request.cls, 'config'): - request.cls.extractor = setup_module("instagram_tbot_extractor", request.cls.config) - - yield - @pytest.fixture def metadata_sample(): m = Metadata() m.set_title("Test Title") - m.set_timestamp("2021-01-01T00:00:00Z") + m.set_timestamp("2021-01-01T00:00:00") m.set_url("https://www.instagram.com/p/1234567890") return m -class TestInstagramTbotExtractor: +@pytest.fixture +def mock_telegram_client(mocker): + """Fixture to mock TelegramClient interactions.""" + mock_client = mocker.patch("auto_archiver.modules.instagram_tbot_extractor.client") + instance = mocker.MagicMock() + mock_client.return_value = instance + return instance + +@pytest.fixture +def extractor(setup_module, patch_extractor_methods, mocker): extractor_module = "instagram_tbot_extractor" - extractor: InstagramTbotExtractor config = { "api_id": 12345, "api_hash": "test_api_hash", "session_file": "test_session", + "timeout": 4 + } + extractor = setup_module(extractor_module, config) + extractor.client = mocker.MagicMock() + extractor.session_file = "test_session" + return extractor + + +def test_non_instagram_url(extractor, metadata_sample): + metadata_sample.set_url("https://www.youtube.com") + assert extractor.download(metadata_sample) is False + + +def test_download_success(extractor, metadata_sample, mocker): + mocker.patch.object(extractor, "_send_url_to_bot", return_value=(mocker.MagicMock(), 101)) + mocker.patch.object(extractor, "_process_messages", return_value="Sample Instagram post caption") + result = extractor.download(metadata_sample) + assert result.is_success() + assert result.status == "insta-via-bot: success" + assert result.metadata.get("title") == "Sample Instagram post caption" + + +def test_download_invalid(extractor, metadata_sample, mocker): + mocker.patch.object(extractor, "_send_url_to_bot", return_value=(mocker.MagicMock(), 101)) + mocker.patch.object(extractor, "_process_messages", return_value="You must enter a URL to a post") + assert extractor.download(metadata_sample) is False + + +@pytest.mark.skip(reason="Requires authentication.") +class TestInstagramTbotExtractorReal(TestExtractorBase): + # To run these tests set the TELEGRAM_API_ID and TELEGRAM_API_HASH environment variables, and ensure the session file exists. + # Note these are true at this point in time, but changes to source media could be reason for failure. + extractor_module = "instagram_tbot_extractor" + extractor: InstagramTbotExtractor + config = { + "api_id": os.environ.get("TELEGRAM_API_ID"), + "api_hash": os.environ.get("TELEGRAM_API_HASH"), + "session_file": "secrets/anon-insta", } - @pytest.fixture - def mock_telegram_client(self): - """Fixture to mock TelegramClient interactions.""" - with patch("auto_archiver.modules.instagram_tbot_extractor._initialize_telegram_client") as mock_client: - instance = MagicMock() - mock_client.return_value = instance - yield instance - - def test_extractor_is_initialized(self): - assert self.extractor is not None - - - @patch("time.sleep") - @pytest.mark.parametrize("url, expected_status, bot_responses", [ - ("https://www.instagram.com/p/C4QgLbrIKXG", "insta-via-bot: success", [MagicMock(id=101, media=None, message="Are you new to Bellingcat? - The way we share our investigations is different. 💭\nWe want you to read our story but also learn ou")]), - ("https://www.instagram.com/reel/DEVLK8qoIbg/", "insta-via-bot: success", [MagicMock(id=101, media=None, message="Our volunteer community is at the centre of many incredible Bellingcat investigations and tools. Stephanie Ladel is one such vol")]), - # todo tbot not working for stories :( - ("https://www.instagram.com/stories/bellingcatofficial/3556336382743057476/", False, [MagicMock(id=101, media=None, message="Media not found or unavailable")]), - ("https://www.youtube.com/watch?v=ymCMy8OffHM", False, []), - ("https://www.instagram.com/p/INVALID", False, [MagicMock(id=101, media=None, message="You must enter a URL to a post")]), + @pytest.mark.parametrize("url, expected_status, message, len_media", [ + ("https://www.instagram.com/p/C4QgLbrIKXG", "insta-via-bot: success", + "Are you new to Bellingcat? - The way we share our investigations is different. 💭\nWe want you to read our story but also learn ou", + 6), + ("https://www.instagram.com/reel/DEVLK8qoIbg/", "insta-via-bot: success", + "Our volunteer community is at the centre of many incredible Bellingcat investigations and tools. Stephanie Ladel is one such vol", + 3), + # instagram tbot not working (potentially intermittently?) for stories - replace with a live story to retest + # ("https://www.instagram.com/stories/bellingcatofficial/3556336382743057476/", False, "Media not found or unavailable"), + # Seems to be working intermittently for highlights + # ("https://www.instagram.com/stories/highlights/17868810693068139/", "insta-via-bot: success", None, 50), + # Marking invalid url as success + ("https://www.instagram.com/p/INVALID", "insta-via-bot: success", "Media not found or unavailable", 0), + ("https://www.youtube.com/watch?v=ymCMy8OffHM", False, None, 0), ]) - def test_download(self, mock_sleep, url, expected_status, bot_responses, metadata_sample): + def test_download(self, url, expected_status, message, len_media, metadata_sample): """Test the `download()` method with various Instagram URLs.""" metadata_sample.set_url(url) - self.extractor.client = MagicMock() + result = self.extractor.download(metadata_sample) - pass - # TODO fully mock or use as authenticated test - # if expected_status: - # assert result.is_success() - # assert result.status == expected_status - # assert result.metadata.get("title") in [msg.message[:128] for msg in bot_responses if msg.message] - # else: - # assert result is False - - - - - # Test story -# Test expired story -# Test requires login/ access (?) -# Test post -# Test multiple images? \ No newline at end of file + if expected_status: + assert result.is_success() + assert result.status == expected_status + assert result.metadata.get("title") == message + assert len(result.media) == len_media + else: + assert result is False diff --git a/tests/extractors/test_twitter_api_extractor.py b/tests/extractors/test_twitter_api_extractor.py index d9a8eb0..26394ac 100644 --- a/tests/extractors/test_twitter_api_extractor.py +++ b/tests/extractors/test_twitter_api_extractor.py @@ -23,7 +23,6 @@ class TestTwitterApiExtractor(TestExtractorBase): } @pytest.mark.parametrize("url, expected", [ - ("https://t.co/yl3oOJatFp", "https://www.bellingcat.com/category/resources/"), # t.co URL ("https://x.com/bellingcat/status/1874097816571961839", "https://x.com/bellingcat/status/1874097816571961839"), # x.com urls unchanged ("https://twitter.com/bellingcat/status/1874097816571961839", "https://twitter.com/bellingcat/status/1874097816571961839"), # twitter urls unchanged ("https://twitter.com/bellingcat/status/1874097816571961839?s=20&t=3d0g4ZQis7dCbSDg-mE7-w", "https://twitter.com/bellingcat/status/1874097816571961839?s=20&t=3d0g4ZQis7dCbSDg-mE7-w"), # don't strip params from twitter urls (changed Jan 2025) @@ -32,7 +31,11 @@ class TestTwitterApiExtractor(TestExtractorBase): ]) def test_sanitize_url(self, url, expected): assert expected == self.extractor.sanitize_url(url) - + + @pytest.mark.download + def test_sanitize_url_download(self): + assert "https://www.bellingcat.com/category/resources/" == self.extractor.sanitize_url("https://t.co/yl3oOJatFp") + @pytest.mark.parametrize("url, exptected_username, exptected_tweetid", [ ("https://twitter.com/bellingcat/status/1874097816571961839", "bellingcat", "1874097816571961839"), ("https://x.com/bellingcat/status/1874097816571961839", "bellingcat", "1874097816571961839"), diff --git a/tests/feeders/test_atlos_feeder.py b/tests/feeders/test_atlos_feeder.py new file mode 100644 index 0000000..f26bdc9 --- /dev/null +++ b/tests/feeders/test_atlos_feeder.py @@ -0,0 +1,108 @@ +import pytest +from auto_archiver.modules.atlos_feeder import AtlosFeeder + + +class FakeAPIResponse: + """Simulate a response object.""" + + def __init__(self, data: dict, raise_error: bool = False) -> None: + self._data = data + self.raise_error = raise_error + + def json(self) -> dict: + return self._data + + def raise_for_status(self) -> None: + if self.raise_error: + raise Exception("HTTP error") + + +@pytest.fixture +def atlos_feeder(setup_module) -> AtlosFeeder: + """Fixture for AtlosFeeder.""" + configs: dict = { + "api_token": "abc123", + "atlos_url": "https://platform.atlos.org", + } + return setup_module("atlos_feeder", configs) + + +@pytest.fixture +def mock_atlos_api(mocker): + """Fixture to mock requests to Atlos API.""" + def _mock_responses(responses): + mocker.patch( + "requests.get", + side_effect=[FakeAPIResponse(data) for data in responses], + ) + return _mock_responses + + +def test_atlos_feeder_iter_yields_valid_metadata(atlos_feeder, mock_atlos_api): + """Test valid items are yielded and invalid ones ignored.""" + mock_atlos_api([ + { + "next": None, + "results": [ + {"source_url": "http://example.com", "id": 1, + "metadata": {"auto_archiver": {"processed": False}}, + "visibility": "visible", "status": "complete"}, + {"source_url": "", "id": 2, + "metadata": {"auto_archiver": {"processed": False}}, + "visibility": "visible", "status": "complete"}, + {"source_url": "http://example.org", "id": 3, + "metadata": {"auto_archiver": {"processed": True}}, + "visibility": "visible", "status": "complete"}, + ], + } + ]) + + items = list(atlos_feeder) + assert len(items) == 1 + assert items[0].get_url() == "http://example.com" + assert items[0].get("atlos_id") == 1 + + +def test_atlos_feeder_multiple_pages(atlos_feeder, mock_atlos_api): + """Test iteration over multiple pages with valid items.""" + mock_atlos_api([ + { + "next": "cursor2", + "results": [ + {"source_url": "http://example1.com", "id": 10, + "metadata": {"auto_archiver": {"processed": False}}, + "visibility": "visible", "status": "complete"}, + ], + }, + { + "next": None, + "results": [ + {"source_url": "http://example2.com", "id": 20, + "metadata": {"auto_archiver": {"processed": False}}, + "visibility": "visible", "status": "complete"}, + ], + }, + ]) + + items = list(atlos_feeder) + assert len(items) == 2 + assert items[0].get_url() == "http://example1.com" + assert items[0].get("atlos_id") == 10 + assert items[1].get_url() == "http://example2.com" + assert items[1].get("atlos_id") == 20 + + +def test_atlos_feeder_no_results(atlos_feeder, mock_atlos_api): + """Test iteration stops when no results are returned.""" + mock_atlos_api([{"next": None, "results": []}]) + assert list(atlos_feeder) == [] + + +def test_atlos_feeder_http_error(atlos_feeder, mocker): + """Test raises an exception on HTTP error.""" + mocker.patch( + "requests.get", + return_value=FakeAPIResponse({"next": None, "results": []}, raise_error=True), + ) + with pytest.raises(Exception, match="HTTP error"): + list(atlos_feeder) diff --git a/tests/feeders/test_gsheet_feeder.py b/tests/feeders/test_gsheet_feeder.py index b86e329..7c5f501 100644 --- a/tests/feeders/test_gsheet_feeder.py +++ b/tests/feeders/test_gsheet_feeder.py @@ -2,27 +2,23 @@ from typing import Type import gspread import pytest -from unittest.mock import patch, MagicMock from auto_archiver.modules.gsheet_feeder import GsheetsFeeder from auto_archiver.core import Metadata, Feeder -def test_setup_without_sheet_and_sheet_id(setup_module): +def test_setup_without_sheet_and_sheet_id(setup_module, mocker): # Ensure setup() raises AssertionError if neither sheet nor sheet_id is set. - with patch("gspread.service_account"): - with pytest.raises(AssertionError): - setup_module( - "gsheet_feeder", - {"service_account": "dummy.json", "sheet": None, "sheet_id": None}, - ) + mocker.patch("gspread.service_account") + with pytest.raises(AssertionError): + setup_module( + "gsheet_feeder", + {"service_account": "dummy.json", "sheet": None, "sheet_id": None}, + ) @pytest.fixture -def gsheet_feeder(setup_module) -> GsheetsFeeder: - with patch("gspread.service_account"): - feeder = setup_module( - "gsheet_feeder", - { +def gsheet_feeder(setup_module, mocker) -> GsheetsFeeder: + config: dict = { "service_account": "dummy.json", "sheet": "test-auto-archiver", "sheet_id": None, @@ -46,9 +42,13 @@ def gsheet_feeder(setup_module) -> GsheetsFeeder: "allow_worksheets": set(), "block_worksheets": set(), "use_sheet_names_in_stored_paths": True, - }, - ) - feeder.gsheets_client = MagicMock() + } + mocker.patch("gspread.service_account") + feeder = setup_module( + "gsheet_feeder", + config + ) + feeder.gsheets_client = mocker.MagicMock() return feeder @@ -129,56 +129,56 @@ def test__set_metadata_with_folder(gsheet_feeder: GsheetsFeeder): ], ) def test_open_sheet_with_name_or_id( - setup_module, sheet, sheet_id, expected_method, expected_arg, description + setup_module, sheet, sheet_id, expected_method, expected_arg, description, mocker ): """Ensure open_sheet() correctly opens by name or ID based on configuration.""" - with patch("gspread.service_account") as mock_service_account: - mock_client = MagicMock() - mock_service_account.return_value = mock_client - mock_client.open.return_value = "MockSheet" - mock_client.open_by_key.return_value = "MockSheet" + mock_service_account = mocker.patch("gspread.service_account") + mock_client = mocker.MagicMock() + mock_service_account.return_value = mock_client + mock_client.open.return_value = "MockSheet" + mock_client.open_by_key.return_value = "MockSheet" - # Setup module with parameterized values - feeder = setup_module( - "gsheet_feeder", - {"service_account": "dummy.json", "sheet": sheet, "sheet_id": sheet_id}, - ) - sheet_result = feeder.open_sheet() - # Validate the correct method was called - getattr(mock_client, expected_method).assert_called_once_with( - expected_arg - ), f"Failed: {description}" - assert sheet_result == "MockSheet", f"Failed: {description}" + # Setup module with parameterized values + feeder = setup_module( + "gsheet_feeder", + {"service_account": "dummy.json", "sheet": sheet, "sheet_id": sheet_id}, + ) + sheet_result = feeder.open_sheet() + # Validate the correct method was called + getattr(mock_client, expected_method).assert_called_once_with( + expected_arg + ), f"Failed: {description}" + assert sheet_result == "MockSheet", f"Failed: {description}" @pytest.mark.usefixtures("setup_module") -def test_open_sheet_with_sheet_id(setup_module): +def test_open_sheet_with_sheet_id(setup_module, mocker): """Ensure open_sheet() correctly opens a sheet by ID.""" - with patch("gspread.service_account") as mock_service_account: - mock_client = MagicMock() - mock_service_account.return_value = mock_client - mock_client.open_by_key.return_value = "MockSheet" - feeder = setup_module( - "gsheet_feeder", - {"service_account": "dummy.json", "sheet": None, "sheet_id": "ABC123"}, - ) - sheet = feeder.open_sheet() - mock_client.open_by_key.assert_called_once_with("ABC123") - assert sheet == "MockSheet" + mock_service_account = mocker.patch("gspread.service_account") + mock_client = mocker.MagicMock() + mock_service_account.return_value = mock_client + mock_client.open_by_key.return_value = "MockSheet" + feeder = setup_module( + "gsheet_feeder", + {"service_account": "dummy.json", "sheet": None, "sheet_id": "ABC123"}, + ) + sheet = feeder.open_sheet() + mock_client.open_by_key.assert_called_once_with("ABC123") + assert sheet == "MockSheet" -def test_should_process_sheet(setup_module): - with patch("gspread.service_account"): - gdb = setup_module( - "gsheet_feeder", - { - "service_account": "dummy.json", - "sheet": "TestSheet", - "sheet_id": None, - "allow_worksheets": {"TestSheet", "Sheet2"}, - "block_worksheets": {"Sheet3"}, - }, - ) +def test_should_process_sheet(setup_module, mocker): + mocker.patch("gspread.service_account") + gdb = setup_module( + "gsheet_feeder", + { + "service_account": "dummy.json", + "sheet": "TestSheet", + "sheet_id": None, + "allow_worksheets": {"TestSheet", "Sheet2"}, + "block_worksheets": {"Sheet3"}, + }, + ) assert gdb.should_process_sheet("TestSheet") == True assert gdb.should_process_sheet("Sheet3") == False # False if allow_worksheets is set diff --git a/tests/feeders/test_gworksheet.py b/tests/feeders/test_gworksheet.py index e6f5cc6..2b05504 100644 --- a/tests/feeders/test_gworksheet.py +++ b/tests/feeders/test_gworksheet.py @@ -1,13 +1,13 @@ +# Note this isn't a feeder, but contained as utility of the gsheet feeder module import pytest -from unittest.mock import MagicMock from auto_archiver.modules.gsheet_feeder import GWorksheet class TestGWorksheet: @pytest.fixture - def mock_worksheet(self): - mock_ws = MagicMock() + def mock_worksheet(self, mocker): + mock_ws = mocker.MagicMock() mock_ws.get_values.return_value = [ ["Link", "Archive Status", "Archive Location", "Archive Date"], ["url1", "archived", "filepath1", "2023-01-01"], @@ -136,8 +136,8 @@ class TestGWorksheet: assert gworksheet.to_a1(row, col) == expected # Test empty worksheet - def test_empty_worksheet_initialization(self): - mock_ws = MagicMock() + def test_empty_worksheet_initialization(self, mocker): + mock_ws = mocker.MagicMock() mock_ws.get_values.return_value = [] g = GWorksheet(mock_ws) assert g.headers == [] diff --git a/tests/storages/test_S3_storage.py b/tests/storages/test_S3_storage.py index 2a5d026..fe60329 100644 --- a/tests/storages/test_S3_storage.py +++ b/tests/storages/test_S3_storage.py @@ -1,6 +1,5 @@ from typing import Type import pytest -from unittest.mock import MagicMock, patch from auto_archiver.core import Media from auto_archiver.modules.s3_storage import S3Storage @@ -11,7 +10,6 @@ class TestS3Storage: """ module_name: str = "s3_storage" storage: Type[S3Storage] - s3: MagicMock config: dict = { "path_generator": "flat", "filename_generator": "static", @@ -25,13 +23,14 @@ class TestS3Storage: "private": False, } - @patch('boto3.client') @pytest.fixture(autouse=True) - def setup_storage(self, setup_module): + def setup_storage(self, setup_module, mocker): + self.s3 = S3Storage() self.storage = setup_module(self.module_name, self.config) def test_client_initialization(self): """Test that S3 client is initialized with correct parameters""" + assert self.storage.s3 is not None assert self.storage.s3.meta.region_name == 'test-region' @@ -44,81 +43,63 @@ class TestS3Storage: media.key = "another/path.jpg" assert self.storage.get_cdn_url(media) == "https://cdn.example.com/another/path.jpg" - def test_uploadf_sets_acl_public(self): + def test_uploadf_sets_acl_public(self, mocker): media = Media("test.txt") - mock_file = MagicMock() - with patch.object(self.storage.s3, 'upload_fileobj') as mock_s3_upload, \ - patch.object(self.storage, 'is_upload_needed', return_value=True): - self.storage.uploadf(mock_file, media) - mock_s3_upload.assert_called_once_with( - mock_file, - Bucket='test-bucket', - Key=media.key, - ExtraArgs={'ACL': 'public-read', 'ContentType': 'text/plain'} - ) + mock_file = mocker.MagicMock() + mock_s3_upload = mocker.patch.object(self.storage.s3, 'upload_fileobj') + mocker.patch.object(self.storage, 'is_upload_needed', return_value=True) + self.storage.uploadf(mock_file, media) + mock_s3_upload.assert_called_once_with( + mock_file, + Bucket='test-bucket', + Key=media.key, + ExtraArgs={'ACL': 'public-read', 'ContentType': 'text/plain'} + ) - def test_upload_decision_logic(self): + def test_upload_decision_logic(self, mocker): """Test is_upload_needed under different conditions""" media = Media("test.txt") - # Test default state (random_no_duplicate=False) assert self.storage.is_upload_needed(media) is True - # Set duplicate checking config to true: - self.storage.random_no_duplicate = True - with patch('auto_archiver.modules.s3_storage.s3_storage.calculate_file_hash') as mock_calc_hash, \ - patch.object(self.storage, 'file_in_folder') as mock_file_in_folder: - mock_calc_hash.return_value = 'beepboop123beepboop123beepboop123' - mock_file_in_folder.return_value = 'existing_key.txt' - # Test duplicate result - assert self.storage.is_upload_needed(media) is False - assert media.key == 'existing_key.txt' - mock_file_in_folder.assert_called_with( - # (first 24 chars of hash) - 'no-dups/beepboop123beepboop123be' - ) + mock_calc_hash = mocker.patch('auto_archiver.modules.s3_storage.s3_storage.calculate_file_hash', return_value='beepboop123beepboop123beepboop123') + mock_file_in_folder = mocker.patch.object(self.storage, 'file_in_folder', return_value='existing_key.txt') + assert self.storage.is_upload_needed(media) is False + assert media.key == 'existing_key.txt' + mock_file_in_folder.assert_called_with('no-dups/beepboop123beepboop123be') - - @patch.object(S3Storage, 'file_in_folder') - def test_skips_upload_when_duplicate_exists(self, mock_file_in_folder): + def test_skips_upload_when_duplicate_exists(self, mocker): """Test that upload skips when file_in_folder finds existing object""" self.storage.random_no_duplicate = True - mock_file_in_folder.return_value = "existing_folder/existing_file.txt" - # Create test media with calculated hash + mock_file_in_folder = mocker.patch.object(S3Storage, 'file_in_folder', return_value="existing_folder/existing_file.txt") media = Media("test.txt") media.key = "original_path.txt" - with patch('auto_archiver.modules.s3_storage.s3_storage.calculate_file_hash') as mock_calculate_hash: - mock_calculate_hash.return_value = "beepboop123beepboop123beepboop123" - # Verify upload - assert self.storage.is_upload_needed(media) is False - assert media.key == "existing_folder/existing_file.txt" - assert media.get("previously archived") is True - with patch.object(self.storage.s3, 'upload_fileobj') as mock_upload: - result = self.storage.uploadf(None, media) - mock_upload.assert_not_called() - assert result is True + mock_calculate_hash = mocker.patch('auto_archiver.modules.s3_storage.s3_storage.calculate_file_hash', return_value="beepboop123beepboop123beepboop123") + assert self.storage.is_upload_needed(media) is False + assert media.key == "existing_folder/existing_file.txt" + assert media.get("previously archived") is True + mock_upload = mocker.patch.object(self.storage.s3, 'upload_fileobj') + result = self.storage.uploadf(None, media) + mock_upload.assert_not_called() + assert result is True - @patch.object(S3Storage, 'is_upload_needed') - def test_uploads_with_correct_parameters(self, mock_upload_needed): + def test_uploads_with_correct_parameters(self, mocker): media = Media("test.txt") media.key = "original_key.txt" - mock_upload_needed.return_value = True + mocker.patch.object(S3Storage, 'is_upload_needed', return_value=True) media.mimetype = 'image/png' - mock_file = MagicMock() + mock_file = mocker.MagicMock() + mock_upload = mocker.patch.object(self.storage.s3, 'upload_fileobj') + self.storage.uploadf(mock_file, media) + mock_upload.assert_called_once_with( + mock_file, + Bucket='test-bucket', + Key='original_key.txt', + ExtraArgs={ + 'ACL': 'public-read', + 'ContentType': 'image/png' + } + ) - with patch.object(self.storage.s3, 'upload_fileobj') as mock_upload: - self.storage.uploadf(mock_file, media) - # verify call occured with these params - mock_upload.assert_called_once_with( - mock_file, - Bucket='test-bucket', - Key='original_key.txt', - ExtraArgs={ - 'ACL': 'public-read', - 'ContentType': 'image/png' - } - ) - - def test_file_in_folder_exists(self): - with patch.object(self.storage.s3, 'list_objects') as mock_list_objects: - mock_list_objects.return_value = {'Contents': [{'Key': 'path/to/file.txt'}]} - assert self.storage.file_in_folder('path/to/') == 'path/to/file.txt' \ No newline at end of file + def test_file_in_folder_exists(self, mocker): + mock_list_objects = mocker.patch.object(self.storage.s3, 'list_objects', return_value={'Contents': [{'Key': 'path/to/file.txt'}]}) + assert self.storage.file_in_folder('path/to/') == 'path/to/file.txt' diff --git a/tests/storages/test_atlos_storage.py b/tests/storages/test_atlos_storage.py new file mode 100644 index 0000000..7528456 --- /dev/null +++ b/tests/storages/test_atlos_storage.py @@ -0,0 +1,142 @@ +import os +import hashlib +import pytest +from auto_archiver.core import Media, Metadata +from auto_archiver.modules.atlos_storage import AtlosStorage + + +class FakeAPIResponse: + """Simulate a response object.""" + + def __init__(self, data: dict, raise_error: bool = False) -> None: + self._data = data + self.raise_error = raise_error + + def json(self) -> dict: + return self._data + + def raise_for_status(self) -> None: + if self.raise_error: + raise Exception("HTTP error") + + +@pytest.fixture +def atlos_storage(setup_module) -> AtlosStorage: + """Fixture for AtlosStorage.""" + configs: dict = { + "api_token": "abc123", + "atlos_url": "https://platform.atlos.org", + } + return setup_module("atlos_storage", configs) + + +@pytest.fixture +def media(tmp_path) -> Media: + """Fixture for Media.""" + content = b"media content" + file_path = tmp_path / "media.txt" + file_path.write_bytes(content) + media = Media(filename=str(file_path)) + media.properties = {"something": "Title"} + media.key = "key" + return media + + +def test_get_cdn_url(atlos_storage: AtlosStorage) -> None: + """Test get_cdn_url returns the configured atlos_url.""" + media = Media(filename="dummy.mp4") + url = atlos_storage.get_cdn_url(media) + assert url == atlos_storage.atlos_url + + +def test_hash(tmp_path, atlos_storage: AtlosStorage) -> None: + """Test _hash() computes the correct SHA-256 hash of a file.""" + content = b"hello world" + file_path = tmp_path / "test.txt" + file_path.write_bytes(content) + media = Media(filename="dummy.mp4") + media.filename = str(file_path) + expected_hash = hashlib.sha256(content).hexdigest() + assert atlos_storage._hash(media) == expected_hash + + +def test_upload_no_atlos_id(tmp_path, atlos_storage: AtlosStorage, media: Media, mocker) -> None: + """Test upload() returns False when metadata lacks atlos_id.""" + metadata = Metadata() # atlos_id not set + post_mock = mocker.patch("requests.post") + result = atlos_storage.upload(media, metadata) + assert result is False + post_mock.assert_not_called() + + +def test_upload_already_uploaded(atlos_storage: AtlosStorage, + metadata: Metadata, + media: Media, + tmp_path, + mocker) -> None: + """Test upload() returns True if media hash already exists.""" + content = b"media content" + metadata.set("atlos_id", 101) + media_hash = hashlib.sha256(content).hexdigest() + fake_get = FakeAPIResponse({ + "result": {"artifacts": [{"file_hash_sha256": media_hash}]} + }) + get_mock = mocker.patch("requests.get", return_value=fake_get) + post_mock = mocker.patch("requests.post") + result = atlos_storage.upload(media, metadata) + assert result is True + get_mock.assert_called_once() + post_mock.assert_not_called() + + +def test_upload_not_uploaded(tmp_path, atlos_storage: AtlosStorage, + metadata: Metadata, + media: Media, + mocker) -> None: + """Test upload() uploads media when not already present.""" + metadata.set("atlos_id", 202) + fake_get = FakeAPIResponse({ + "result": {"artifacts": [{"file_hash_sha256": "different_hash"}]} + }) + get_mock = mocker.patch("requests.get", return_value=fake_get) + fake_post = FakeAPIResponse({}, raise_error=False) + post_mock = mocker.patch("requests.post", return_value=fake_post) + result = atlos_storage.upload(media, metadata) + assert result is True + get_mock.assert_called_once() + post_mock.assert_called_once() + expected_url = f"{atlos_storage.atlos_url}/api/v2/source_material/upload/202" + expected_headers = {"Authorization": f"Bearer {atlos_storage.api_token}"} + expected_params = {"title": media.properties} + call_kwargs = post_mock.call_args.kwargs + assert call_kwargs["headers"] == expected_headers + assert call_kwargs["params"] == expected_params + # Verify the URL passed to requests.post. + posted_url = call_kwargs.get("url") or post_mock.call_args.args[0] + assert posted_url == expected_url + # Verify files parameter contains the correct filename. + file_tuple = call_kwargs["files"]["file"] + assert file_tuple[0] == os.path.basename(media.filename) + + +def test_upload_post_http_error(tmp_path, + atlos_storage: AtlosStorage, + metadata: Metadata, + media: Media, + mocker) -> None: + """Test upload() propagates HTTP error during POST.""" + metadata.set("atlos_id", 303) + fake_get = FakeAPIResponse({ + "result": {"artifacts": []} + }) + mocker.patch("requests.get", return_value=fake_get) + fake_post = FakeAPIResponse({}, raise_error=True) + mocker.patch("requests.post", return_value=fake_post) + with pytest.raises(Exception, match="HTTP error"): + atlos_storage.upload(media, metadata) + + +def test_uploadf_not_implemented(atlos_storage: AtlosStorage) -> None: + """Test uploadf() returns None (not implemented).""" + result = atlos_storage.uploadf(None, "dummy") + assert result is None diff --git a/tests/storages/test_gdrive_storage.py b/tests/storages/test_gdrive_storage.py index aba0a25..f5ff87c 100644 --- a/tests/storages/test_gdrive_storage.py +++ b/tests/storages/test_gdrive_storage.py @@ -1,44 +1,57 @@ from typing import Type import pytest -from unittest.mock import MagicMock, patch +from oauth2client import service_account + from auto_archiver.core import Media from auto_archiver.modules.gdrive_storage import GDriveStorage from auto_archiver.core.metadata import Metadata from tests.storages.test_storage_base import TestStorageBase -class TestGDriveStorage: - """ - Test suite for GDriveStorage. - """ - +@pytest.fixture +def gdrive_storage(setup_module, mocker): module_name: str = "gdrive_storage" - storage: Type[GDriveStorage] + storage: GDriveStorage config: dict = {'path_generator': 'url', 'filename_generator': 'static', 'root_folder_id': "fake_root_folder_id", 'oauth_token': None, 'service_account': 'fake_service_account.json' } - - @pytest.fixture(autouse=True) - def gdrive(self, setup_module): - with patch('google.oauth2.service_account.Credentials.from_service_account_file') as mock_creds: - self.storage = setup_module(self.module_name, self.config) - - def test_initialize_fails_with_non_existent_creds(self): - """ - Test that the Google Drive service raises a FileNotFoundError when the service account file does not exist. - """ - # Act and Assert - with pytest.raises(FileNotFoundError) as exc_info: - self.storage.setup() - assert "No such file or directory" in str(exc_info.value) + mocker.patch('google.oauth2.service_account.Credentials.from_service_account_file') + return setup_module(module_name, config) - def test_path_parts(self): - media = Media(filename="test.jpg") - media.key = "folder1/folder2/test.jpg" +def test_initialize_fails_with_non_existent_creds(setup_module): + """Test that the Google Drive service raises a FileNotFoundError when the service account file does not exist. + (and isn't mocked) + """ + config: dict = {'path_generator': 'url', + 'filename_generator': 'static', + 'root_folder_id': "fake_root_folder_id", + 'oauth_token': None, + 'service_account': 'fake_service_account.json' + } + with pytest.raises(FileNotFoundError) as exc_info: + setup_module("gdrive_storage", config) + assert "No such file or directory" in str(exc_info.value) + + +def test_get_id_from_parent_and_name(gdrive_storage, mocker): + """Test _get_id_from_parent_and_name returns correct id from an API result.""" + fake_list = mocker.MagicMock() + fake_list.execute.return_value = {"files": [{"id": "123", "name": "testname"}]} + fake_service = mocker.MagicMock() + # mock the files.list return value + fake_service.files.return_value.list.return_value = fake_list + gdrive_storage.service = fake_service + result = gdrive_storage._get_id_from_parent_and_name("parent", "mock", retries=1, use_mime_type=False) + assert result == "123" + +def test_path_parts(): + media = Media(filename="test.jpg") + media.key = "folder1/folder2/test.jpg" + @pytest.mark.skip(reason="Requires real credentials") diff --git a/tests/storages/test_local_storage.py b/tests/storages/test_local_storage.py new file mode 100644 index 0000000..85f97c6 --- /dev/null +++ b/tests/storages/test_local_storage.py @@ -0,0 +1,54 @@ + +import os +from pathlib import Path + +import pytest + +from auto_archiver.core import Media +from auto_archiver.modules.local_storage import LocalStorage + + +@pytest.fixture +def local_storage(setup_module) -> LocalStorage: + configs: dict = { + "path_generator": "flat", + "filename_generator": "static", + "save_to": "./local_archive", + "save_absolute": False, + } + return setup_module("local_storage", configs) + + +@pytest.fixture +def sample_media(tmp_path) -> Media: + """Fixture creating a Media object with temporary source file""" + src_file = tmp_path / "source.txt" + src_file.write_text("test content") + return Media(key="subdir/test.txt", filename=str(src_file)) + + +def test_get_cdn_url_relative(local_storage): + media = Media(key="test.txt", filename="dummy.txt") + expected = os.path.join(local_storage.save_to, media.key) + assert local_storage.get_cdn_url(media) == expected + + + +def test_get_cdn_url_absolute(local_storage): + media = Media(key="test.txt", filename="dummy.txt") + local_storage.save_absolute = True + expected = os.path.abspath(os.path.join(local_storage.save_to, media.key)) + assert local_storage.get_cdn_url(media) == expected + +def test_upload_file_contents_and_metadata(local_storage, sample_media): + dest = os.path.join(local_storage.save_to, sample_media.key) + assert local_storage.upload(sample_media) is True + assert Path(sample_media.filename).read_text() == Path(dest).read_text() + + +def test_upload_nonexistent_source(local_storage): + media = Media(key="missing.txt", filename="nonexistent.txt") + with pytest.raises(FileNotFoundError): + local_storage.upload(media) + + diff --git a/tests/test_implementation.py b/tests/test_implementation.py index 7e33651..85fc448 100644 --- a/tests/test_implementation.py +++ b/tests/test_implementation.py @@ -60,3 +60,15 @@ def test_run_auto_archiver_empty_file(caplog, autoarchiver, orchestration_file): # should treat an empty file as if there is no file at all assert " No URLs provided. Please provide at least one URL via the com" in caplog.text + +def test_call_autoarchiver_main(caplog, monkeypatch, tmp_path): + from auto_archiver.__main__ import main + + # monkey patch to change the current working directory, so that we don't use the user's real config file + monkeypatch.chdir(tmp_path) + with monkeypatch.context() as m: + m.setattr(sys, "argv", ["auto-archiver"]) + with pytest.raises(SystemExit): + main() + + assert "No URLs provided. Please provide at least one" in caplog.text \ No newline at end of file diff --git a/tests/test_metadata.py b/tests/test_metadata.py index b07e107..e1f7797 100644 --- a/tests/test_metadata.py +++ b/tests/test_metadata.py @@ -162,4 +162,25 @@ def test_get_context(): def test_choose_most_complete(): - pass \ No newline at end of file + m_more = Metadata() + m_more.set_title("Title 1") + m_more.set_content("Content 1") + m_more.set_url("https://example.com") + + m_less = Metadata() + m_less.set_title("Title 2") + m_less.set_content("Content 2") + m_less.set_url("https://example.com") + m_less.set_context("key", "value") + + res = Metadata.choose_most_complete([m_more, m_less]) + assert res.metadata.get("title") == "Title 1" + +def test_choose_most_complete_from_pickles(unpickle): + # test most complete from pickles before and after an enricher has run + # Only compares length of media, not the actual media + m_before_enriching = unpickle("metadata_enricher_ytshort_input.pickle") + m_after_enriching = unpickle("metadata_enricher_ytshort_expected.pickle") + # Iterates `for r in results[1:]:` + res = Metadata.choose_most_complete([Metadata(), m_after_enriching, m_before_enriching]) + assert res.media == m_after_enriching.media diff --git a/tests/test_modules.py b/tests/test_modules.py index 854edb5..7a2b14d 100644 --- a/tests/test_modules.py +++ b/tests/test_modules.py @@ -1,24 +1,18 @@ import sys import pytest -from auto_archiver.core.module import get_module_lazy, BaseModule, LazyBaseModule, _LAZY_LOADED_MODULES +from auto_archiver.core.module import ModuleFactory, LazyBaseModule +from auto_archiver.core.base_module import BaseModule @pytest.fixture def example_module(): import auto_archiver + module_factory = ModuleFactory() + previous_path = auto_archiver.modules.__path__ auto_archiver.modules.__path__.append("tests/data/test_modules/") - module = get_module_lazy("example_module") - yield module - # cleanup - try: - del module._manifest - except AttributeError: - pass - del _LAZY_LOADED_MODULES["example_module"] - sys.modules.pop("auto_archiver.modules.example_module.example_module", None) - auto_archiver.modules.__path__ = previous_path + return module_factory.get_module_lazy("example_module") def test_get_module_lazy(example_module): assert example_module.name == "example_module" @@ -46,12 +40,14 @@ def test_module_dependency_check_loads_module(example_module): # monkey patch the manifest to include a nonexistnet dependency example_module.manifest["dependencies"]["python"] = ["hash_enricher"] + module_factory = example_module.module_factory + loaded_module = example_module.load({}) assert loaded_module is not None # check the dependency is loaded - assert _LAZY_LOADED_MODULES["hash_enricher"] is not None - assert _LAZY_LOADED_MODULES["hash_enricher"]._instance is not None + assert module_factory._lazy_modules["hash_enricher"] is not None + assert module_factory._lazy_modules["hash_enricher"]._instance is not None def test_load_module(example_module): @@ -69,7 +65,7 @@ def test_load_module(example_module): @pytest.mark.parametrize("module_name", ["local_storage", "generic_extractor", "html_formatter", "csv_db"]) def test_load_modules(module_name): # test that specific modules can be loaded - module = get_module_lazy(module_name) + module = ModuleFactory().get_module_lazy(module_name) assert module is not None assert isinstance(module, LazyBaseModule) assert module.name == module_name @@ -86,7 +82,7 @@ def test_load_modules(module_name): @pytest.mark.parametrize("module_name", ["local_storage", "generic_extractor", "html_formatter", "csv_db"]) def test_lazy_base_module(module_name): - lazy_module = get_module_lazy(module_name) + lazy_module = ModuleFactory().get_module_lazy(module_name) assert lazy_module is not None assert isinstance(lazy_module, LazyBaseModule) diff --git a/tests/test_orchestrator.py b/tests/test_orchestrator.py index 5ba57d0..301e4d9 100644 --- a/tests/test_orchestrator.py +++ b/tests/test_orchestrator.py @@ -4,7 +4,7 @@ from argparse import ArgumentParser, ArgumentTypeError from auto_archiver.core.orchestrator import ArchivingOrchestrator from auto_archiver.version import __version__ from auto_archiver.core.config import read_yaml, store_yaml -from auto_archiver.core.module import _LAZY_LOADED_MODULES + TEST_ORCHESTRATION = "tests/data/test_orchestration.yaml" TEST_MODULES = "tests/data/test_modules/" @@ -17,22 +17,7 @@ def test_args(): @pytest.fixture def orchestrator(): - yield ArchivingOrchestrator() - # hack - the loguru logger starts with one logger, but if orchestrator has run before - # it'll remove the default logger, add it back in: - - from loguru import logger - - if not logger._core.handlers.get(0): - logger._core.handlers_count = 0 - logger.add(sys.stderr) - # and remove the custom logger - if logger._core.handlers.get(1): - logger.remove(1) - - # delete out any loaded modules - _LAZY_LOADED_MODULES.clear() - + return ArchivingOrchestrator() @pytest.fixture def basic_parser(orchestrator) -> ArgumentParser: @@ -75,18 +60,36 @@ def test_help(orchestrator, basic_parser, capsys): orchestrator.show_help(args) assert exit_error.value.code == 0 - assert "Usage: auto-archiver [--help] [--version] [--config CONFIG_FILE]" in capsys.readouterr().out + + logs = capsys.readouterr().out + assert "Usage: auto-archiver [--help] [--version] [--config CONFIG_FILE]" in logs + + # basic config options + assert "--version" in logs + + # setting modules options + assert "--feeders" in logs + assert "--extractors" in logs + + # authentication options + assert "--authentication" in logs + + # logging options + assert "--logging.level" in logs + + # individual module configs + assert "--gsheet_feeder.sheet_id" in logs def test_add_custom_modules_path(orchestrator, test_args): - orchestrator.run(test_args) + orchestrator.setup_config(test_args) import auto_archiver assert "tests/data/test_modules/" in auto_archiver.modules.__path__ def test_add_custom_modules_path_invalid(orchestrator, caplog, test_args): - orchestrator.run(test_args + # we still need to load the real path to get the example_module + orchestrator.setup_config(test_args + # we still need to load the real path to get the example_module ["--module_paths", "tests/data/invalid_test_modules/"]) assert caplog.records[0].message == "Path 'tests/data/invalid_test_modules/' does not exist. Skipping..." @@ -97,7 +100,7 @@ def test_check_required_values(orchestrator, caplog, test_args): test_args = test_args[:-2] with pytest.raises(SystemExit) as exit_error: - orchestrator.run(test_args) + config = orchestrator.setup_config(test_args) assert caplog.records[1].message == "the following arguments are required: --example_module.required_field" @@ -111,24 +114,50 @@ def test_get_required_values_from_config(orchestrator, test_args, tmp_path): store_yaml(test_yaml, tmp_file) # run the orchestrator - orchestrator.run(["--config", tmp_file, "--module_paths", TEST_MODULES]) - assert orchestrator.config is not None + config = orchestrator.setup_config(["--config", tmp_file, "--module_paths", TEST_MODULES]) + assert config is not None def test_load_authentication_string(orchestrator, test_args): - orchestrator.run(test_args + ["--authentication", '{"facebook.com": {"username": "my_username", "password": "my_password"}}']) - assert orchestrator.config['authentication'] == {"facebook.com": {"username": "my_username", "password": "my_password"}} + config = orchestrator.setup_config(test_args + ["--authentication", '{"facebook.com": {"username": "my_username", "password": "my_password"}}']) + assert config['authentication'] == {"facebook.com": {"username": "my_username", "password": "my_password"}} def test_load_authentication_string_concat_site(orchestrator, test_args): - orchestrator.run(test_args + ["--authentication", '{"x.com,twitter.com": {"api_key": "my_key"}}']) - assert orchestrator.config['authentication'] == {"x.com": {"api_key": "my_key"}, + config = orchestrator.setup_config(test_args + ["--authentication", '{"x.com,twitter.com": {"api_key": "my_key"}}']) + assert config['authentication'] == {"x.com": {"api_key": "my_key"}, "twitter.com": {"api_key": "my_key"}} def test_load_invalid_authentication_string(orchestrator, test_args): with pytest.raises(ArgumentTypeError): - orchestrator.run(test_args + ["--authentication", "{\''invalid_json"]) + orchestrator.setup_config(test_args + ["--authentication", "{\''invalid_json"]) def test_load_authentication_invalid_dict(orchestrator, test_args): with pytest.raises(ArgumentTypeError): - orchestrator.run(test_args + ["--authentication", "[true, false]"]) \ No newline at end of file + orchestrator.setup_config(test_args + ["--authentication", "[true, false]"]) + +def test_load_modules_from_commandline(orchestrator, test_args): + args = test_args + ["--feeders", "example_module", "--extractors", "example_module", "--databases", "example_module", "--enrichers", "example_module", "--formatters", "example_module"] + + orchestrator.setup(args) + + assert len(orchestrator.feeders) == 1 + assert len(orchestrator.extractors) == 1 + assert len(orchestrator.databases) == 1 + assert len(orchestrator.enrichers) == 1 + assert len(orchestrator.formatters) == 1 + + assert orchestrator.feeders[0].name == "example_module" + assert orchestrator.extractors[0].name == "example_module" + assert orchestrator.databases[0].name == "example_module" + assert orchestrator.enrichers[0].name == "example_module" + assert orchestrator.formatters[0].name == "example_module" + +def test_load_settings_for_module_from_commandline(orchestrator, test_args): + args = test_args + ["--feeders", "gsheet_feeder", "--gsheet_feeder.sheet_id", "123", "--gsheet_feeder.service_account", "tests/data/test_service_account.json"] + + orchestrator.setup(args) + + assert len(orchestrator.feeders) == 1 + assert orchestrator.feeders[0].name == "gsheet_feeder" + assert orchestrator.config['gsheet_feeder']['sheet_id'] == "123" \ No newline at end of file diff --git a/tests/utils/test_misc.py b/tests/utils/test_misc.py new file mode 100644 index 0000000..0023077 --- /dev/null +++ b/tests/utils/test_misc.py @@ -0,0 +1,144 @@ +import hashlib +import json +from datetime import datetime, timezone + +import pytest + +from auto_archiver.utils.misc import ( + mkdir_if_not_exists, + expand_url, + getattr_or, + DateTimeEncoder, + dump_payload, + get_datetime_from_str, + update_nested_dict, + calculate_file_hash, + random_str, + get_timestamp +) + + +@pytest.fixture +def sample_file(tmp_path): + file_path = tmp_path / "test.txt" + file_path.write_text("test content") + return file_path + + +class TestDirectoryUtils: + def test_mkdir_creates_new_directory(self, tmp_path): + new_dir = tmp_path / "new_folder" + mkdir_if_not_exists(new_dir) + assert new_dir.exists() + assert new_dir.is_dir() + + def test_mkdir_exists_quietly(self, tmp_path): + existing_dir = tmp_path / "existing" + existing_dir.mkdir() + mkdir_if_not_exists(existing_dir) + assert existing_dir.exists() + +class TestURLExpansion: + @pytest.mark.parametrize("input_url,expected", [ + ("https://example.com", "https://example.com"), + ("https://t.co/test", "https://expanded.url") + ]) + def test_expand_url(self, input_url, expected, mocker): + mock_response = mocker.Mock() + mock_response.url = "https://expanded.url" + mocker.patch('requests.get', return_value=mock_response) + result = expand_url(input_url) + assert result == expected + + def test_expand_url_handles_errors(self, caplog, mocker): + mocker.patch('requests.get', side_effect=Exception("Connection error")) + url = "https://t.co/error" + result = expand_url(url) + assert result == url + assert f"Failed to expand url {url}" in caplog.text + +class TestAttributeHandling: + class Sample: + exists = "value" + none = None + + @pytest.mark.parametrize("obj,attr,default,expected", [ + (Sample(), "exists", "default", "value"), + (Sample(), "none", "default", "default"), + (Sample(), "missing", "default", "default"), + (None, "anything", "fallback", "fallback"), + ]) + def test_getattr_or(self, obj, attr, default, expected): + # Test gets attribute or returns a default value + assert getattr_or(obj, attr, default) == expected + +class TestDateTimeHandling: + def test_datetime_encoder(self, sample_datetime): + result = json.dumps({"dt": sample_datetime}, cls=DateTimeEncoder) + loaded = json.loads(result) + assert loaded["dt"] == str(sample_datetime) + + def test_dump_payload(self, sample_datetime): + payload = {"timestamp": sample_datetime} + result = dump_payload(payload) + assert str(sample_datetime) in result + + @pytest.mark.parametrize("dt_str,fmt,expected", [ + ("2023-01-01 12:00:00+00:00", None, datetime(2023, 1, 1, 12, 0, tzinfo=timezone.utc)), + ("20230101 120000", "%Y%m%d %H%M%S", datetime(2023, 1, 1, 12, 0)), + ("invalid", None, None), + ]) + def test_datetime_from_string(self, dt_str, fmt, expected): + result = get_datetime_from_str(dt_str, fmt) + if expected is None: + assert result is None + else: + assert result == expected.replace(tzinfo=result.tzinfo) + +class TestDictUtils: + @pytest.mark.parametrize("original,update,expected", [ + ({"a": 1}, {"b": 2}, {"a": 1, "b": 2}), + ({"nested": {"a": 1}}, {"nested": {"b": 2}}, {"nested": {"a": 1, "b": 2}}), + ({"a": {"b": {"c": 1}}}, {"a": {"b": {"c": 2}}}, {"a": {"b": {"c": 2}}}), + ]) + def test_update_nested_dict(self, original, update, expected): + update_nested_dict(original, update) + assert original == expected + +class TestHashingUtils: + def test_file_hashing(self, sample_file): + expected = hashlib.sha256(b"test content").hexdigest() + assert calculate_file_hash(str(sample_file)) == expected + + def test_large_file_hashing(self, tmp_path): + file_path = tmp_path / "large.bin" + content = b"0" * 16_000_000 * 2 # 32MB + file_path.write_bytes(content) + + expected = hashlib.sha256(content).hexdigest() + assert calculate_file_hash(str(file_path)) == expected + +class TestMiscUtils: + def test_random_str_length(self): + for length in [8, 16, 32]: + assert len(random_str(length)) == length + + def test_random_str_raises_too_long(self): + with pytest.raises(AssertionError) as exc_info: + random_str(64) + assert "length must be less than 32 as UUID4 is used" == str(exc_info.value) + + def test_random_str_uniqueness(self): + assert random_str() != random_str() + + @pytest.mark.parametrize("ts_input,utc,iso,expected_type", [ + (datetime.now(), True, True, str), + ("2023-01-01T12:00:00+00:00", False, False, datetime), + (1672574400, True, True, str), + ]) + def test_timestamp_parsing(self, ts_input, utc, iso, expected_type): + result = get_timestamp(ts_input, utc=utc, iso=iso) + assert isinstance(result, expected_type) + + def test_invalid_timestamp_returns_none(self): + assert get_timestamp("invalid-date") is None \ No newline at end of file