update repo badges

Only return success for instagram_tbot_extractor.py with content.

.github/dependabot.yml

@@ -0,0 +1,40 @@
+# To get started with Dependabot version updates, you'll need to specify which
+# package ecosystems to update and where the package manifests are located.
+# Please see the documentation for all configuration options:
+# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
+
+version: 2
+updates:
+  - package-ecosystem: "pip"
+    directory: "/"
+    groups:
+      python:
+        patterns:
+          - "*"
+    schedule:
+      interval: "weekly"
+  
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    groups:
+      actions:
+        patterns:
+          - "*"
+    schedule:
+      interval: "weekly"
+
+  - package-ecosystem: "npm"
+    directory: "/scripts/settings/"
+    groups:
+      actions:
+        patterns:
+          - "*"
+    schedule:
+      interval: "weekly"
+
+  - package-ecosystem: "docker"
+    # Look for a `Dockerfile` in the `root` directory
+    directory: "/"
+    # Check for updates once a week
+    schedule:
+      interval: "weekly"

.github/workflows/docker-publish.yaml

@@ -22,7 +22,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Check out the repo
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
         
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v3
@@ -33,14 +33,14 @@ jobs:
         uses: docker/setup-buildx-action@v3
 
       - name: Log in to Docker Hub
-        uses: docker/login-action@9780b0c442fbb1117ed29e0efdff1e18412f7567
+        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
 
       - name: Extract metadata (tags, labels) for Docker
         id: meta
-        uses: docker/metadata-action@369eb591f429131d6889c46b94e711f089e6ca96
+        uses: docker/metadata-action@902fa8ec7d6ecbf8d84d538b9b233a880e428804
         with:
           images: bellingcat/auto-archiver
       

.github/workflows/ruff.yaml

@@ -0,0 +1,34 @@
+name: Ruff Formatting & Linting
+
+on:
+  push:
+    branches: [ main ]
+    paths-ignore:
+      - "README.md"
+      - ".github"
+      - "poetry.lock"
+      - "scripts/settings"
+  pull_request:
+    branches: [ main ]
+    paths-ignore:
+      - "README.md"
+      - ".github"
+      - "poetry.lock"
+      - "scripts/settings"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install ruff
+
+      - name: Run Ruff
+        run: ruff check --output-format=github . && ruff format --check

.github/workflows/tests-core.yaml

@@ -20,8 +20,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: ["3.10", "3.11", "3.12"]
-        os: [ubuntu-22.04]
-        #TODO: re-enable ubuntu-latest, this is disabled as oscrypto cannot be pinned to github commit and pushed to pypi
+        os: [ubuntu-22.04, ubuntu-latest]
     defaults:
       run:
         working-directory: ./
@@ -29,16 +28,23 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      - name: Install Poetry
-        run: pipx install poetry
-
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          cache: 'poetry'
 
-      - name: Install dependencies
+      - name: Install latest Poetry
+        run: pipx install poetry
+
+      - name: Cache Poetry and pip artifacts
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.cache/pip
+          key: poetry-${{ matrix.os }}-${{ matrix.python-version }}-${{ hashFiles('**/poetry.lock') }}
+
+      - name: Install dependencies from source only
         run: poetry install --no-interaction --with dev
 
       - name: Run Core Tests

.github/workflows/tests-download.yaml

@@ -22,16 +22,23 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      - name: Install poetry
-        run: pipx install poetry
-
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          cache: 'poetry'
 
-      - name: Install dependencies
+      - name: Install latest Poetry
+        run: pipx install poetry
+
+      - name: Cache Poetry and pip artifacts
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.cache/pip
+          key: poetry-${{ matrix.os }}-${{ matrix.python-version }}-${{ hashFiles('**/poetry.lock') }}
+
+      - name: Install dependencies from source only
         run: poetry install --no-interaction --with dev
 
       - name: Run Download Tests

.gitignore

@@ -4,6 +4,7 @@ temp/
 .DS_Store
 expmt/
 service_account.json
+service_account-*.json
 __pycache__/
 ._*
 anu.html
@@ -34,4 +35,5 @@ docs/_build/
 docs/source/autoapi/
 docs/source/modules/autogen/
 scripts/settings_page.html
+scripts/settings/src/schema.json 
 .vite

.pre-commit-config.yaml

@@ -0,0 +1,7 @@
+# Run Ruff formatter on commits.
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.9.10
+    hooks:
+      - id: ruff
+      - id: ruff-format

.readthedocs.yaml

@@ -21,7 +21,7 @@ build:
       # generate the config editor page. Schema then HTML
       - VIRTUAL_ENV=$READTHEDOCS_VIRTUALENV_PATH poetry run python scripts/generate_settings_schema.py
       # install node dependencies and build the settings
-      - cd scripts/settings && npm install && npm run build && yes | cp dist/index.html ../../docs/source/installation/settings_base.html && cd ../..
+      - cd scripts/settings && npm install && npm run build && yes | cp -v dist/index.html ../../docs/source/installation/settings.html && cd ../..
 
 
 sphinx:

Dockerfile

@@ -1,4 +1,4 @@
-FROM webrecorder/browsertrix-crawler:1.4.2 AS base
+FROM webrecorder/browsertrix-crawler:1.5.8 AS base
 
 ENV RUNNING_IN_DOCKER=1 \
     LANG=C.UTF-8 \

Makefile

@@ -0,0 +1,79 @@
+# Variables
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = docs/source
+BUILDDIR      = docs/_build
+
+.PHONY: help
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+	@echo "Additional Commands:"
+	@echo "  make test         - Run all tests in 'tests/' with pytest"
+	@echo "  make ruff-check   - Run Ruff linting and formatting checks (safe)"
+	@echo "  make ruff-clean   - Auto-fix Ruff linting and formatting issues"
+	@echo "  make docs         - Generate documentation (same as 'make html')"
+	@echo "  make clean-docs   - Remove generated docs"
+	@echo "  make docker-build - Build the Auto Archiver Docker image"
+	@echo "  make docker-compose - Run Auto Archiver with Docker Compose"
+	@echo "  make docker-compose-rebuild - Rebuild and run Auto Archiver with Docker Compose"
+	@echo "  make show-docs    - Build and open the documentation in a browser"
+
+
+
+.PHONY: test
+test:
+	@echo "Running tests..."
+	@pytest tests --disable-warnings
+
+
+.PHONY: ruff-check
+ruff-check:
+	@echo "Checking code style with Ruff (safe)..."
+	@ruff check .
+
+
+.PHONY: ruff-clean
+ruff-clean:
+	@echo "Fixing lint and formatting issues with Ruff..."
+	@ruff check . --fix
+	@ruff format .
+
+
+.PHONY: docs
+docs:
+	@echo "Building documentation..."
+	@$(SPHINXBUILD) -M html "$(SOURCEDIR)" "$(BUILDDIR)"
+
+
+.PHONY: clean-docs
+clean-docs:
+	@echo "Cleaning up generated documentation files..."
+	@$(SPHINXBUILD) -M clean "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+	@rm -rf "$(SOURCEDIR)/autoapi/" "$(SOURCEDIR)/modules/autogen/"
+	@echo "Cleanup complete."
+
+
+.PHONY: show-docs
+show-docs:
+	@echo "Opening documentation in browser..."
+	@open "$(BUILDDIR)/html/index.html"
+
+.PHONY: docker-build
+docker-build:
+	@echo "Building local Auto Archiver Docker image..."
+	@docker compose build  # Uses the same build context as docker-compose.yml
+
+.PHONY: docker-compose
+docker-compose:
+	@echo "Running Auto Archiver with Docker Compose..."
+	@docker compose up
+
+.PHONY: docker-compose-rebuild
+docker-compose-rebuild:
+	@echo "Rebuilding and running Auto Archiver with Docker Compose..."
+	@docker compose up --build
+
+# Catch-all for Sphinx commands
+.PHONY: Makefile
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

README.md

@@ -1,16 +1,17 @@
 <h1 align="center">Auto Archiver</h1>
 
+[![Documentation Status](https://readthedocs.org/projects/auto-archiver/badge/?version=latest)](https://auto-archiver.readthedocs.io/en/latest/?badge=latest)
 [![PyPI version](https://badge.fury.io/py/auto-archiver.svg)](https://badge.fury.io/py/auto-archiver)
-[![Docker Image Version (latest by date)](https://img.shields.io/docker/v/bellingcat/auto-archiver?label=version&logo=docker)](https://hub.docker.com/r/bellingcat/auto-archiver)
+[![Docker Image Version (latest by date)](https://img.shields.io/docker/v/bellingcat/auto-archiver?sort=semver&logo=docker&color=#69F0AE)](https://hub.docker.com/r/bellingcat/auto-archiver)
 [![Core Test Status](https://github.com/bellingcat/auto-archiver/workflows/Core%20Tests/badge.svg)](https://github.com/bellingcat/auto-archiver/actions/workflows/tests-core.yaml)
-[![Download Test Status](https://github.com/bellingcat/auto-archiver/workflows/Download%20Tests/badge.svg)](https://github.com/bellingcat/auto-archiver/actions/workflows/tests-download.yaml)
+<!-- [![Download Test Status](https://github.com/bellingcat/auto-archiver/workflows/Download%20Tests/badge.svg)](https://github.com/bellingcat/auto-archiver/actions/workflows/tests-download.yaml) -->
+
 <!-- ![Docker Pulls](https://img.shields.io/docker/pulls/bellingcat/auto-archiver) -->
 <!-- [![PyPI download month](https://img.shields.io/pypi/dm/auto-archiver.svg)](https://pypi.python.org/pypi/auto-archiver/) -->
-<!-- [![Documentation Status](https://readthedocs.org/projects/vk-url-scraper/badge/?version=latest)](https://vk-url-scraper.readthedocs.io/en/latest/?badge=latest) -->
 
 
 
-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.
+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 be 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.
 
 <div class="hidden_rtd">
   
@@ -29,7 +30,7 @@ View the [Installation Guide](https://auto-archiver.readthedocs.io/en/latest/ins
 
 To get started quickly using Docker:
 
-`docker pull bellingcat/auto-archiver && docker run --rm -v secrets:/app/secrets bellingcat/auto-archiver --config secrets/orchestration.yaml`
+`docker pull bellingcat/auto-archiver && docker run -it --rm -v secrets:/app/secrets bellingcat/auto-archiver --config secrets/orchestration.yaml`
 
 Or pip:
 

docker-compose.yaml

@@ -1,4 +1,3 @@
-version: '3.8'
 
 services:
   auto-archiver:
@@ -10,7 +9,4 @@ services:
     volumes:
       - ./secrets:/app/secrets
       - ./local_archive:/app/local_archive
-    environment:
-      - WACZ_ENABLE_DOCKER=true
-      - RUNNING_IN_DOCKER=true
     command: --config secrets/orchestration.yaml

docs/Makefile

@@ -1,20 +0,0 @@
-# Minimal makefile for Sphinx documentation
-#
-
-# You can set these variables from the command line, and also
-# from the environment for the first two.
-SPHINXOPTS    ?=
-SPHINXBUILD   ?= sphinx-build
-SOURCEDIR     = source
-BUILDDIR      = _build
-
-# Put it first so that "make" without argument is like "make help".
-help:
-	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
-
-.PHONY: help Makefile
-
-# Catch-all target: route all unknown targets to Sphinx using the new
-# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
-%: Makefile
-	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/scripts/__init__.py

@@ -1 +1 @@
-from scripts import generate_module_docs
+from scripts import generate_module_docs

docs/scripts/scripts.py

@@ -10,12 +10,12 @@ MODULES_FOLDER = Path(__file__).parent.parent.parent.parent / "src" / "auto_arch
 SAVE_FOLDER = Path(__file__).parent.parent / "source" / "modules" / "autogen"
 
 type_color = {
-    'feeder': "<span style='color: #FFA500'>[feeder](/core_modules.md#feeder-modules)</a></span>",
-    'extractor': "<span style='color: #00FF00'>[extractor](/core_modules.md#extractor-modules)</a></span>",
-    'enricher': "<span style='color: #0000FF'>[enricher](/core_modules.md#enricher-modules)</a></span>",
-    'database': "<span style='color: #FF00FF'>[database](/core_modules.md#database-modules)</a></span>",
-    'storage': "<span style='color: #FFFF00'>[storage](/core_modules.md#storage-modules)</a></span>",
-    'formatter': "<span style='color: #00FFFF'>[formatter](/core_modules.md#formatter-modules)</a></span>",
+    "feeder": "<span style='color: #FFA500'>[feeder](/core_modules.md#feeder-modules)</a></span>",
+    "extractor": "<span style='color: #00FF00'>[extractor](/core_modules.md#extractor-modules)</a></span>",
+    "enricher": "<span style='color: #0000FF'>[enricher](/core_modules.md#enricher-modules)</a></span>",
+    "database": "<span style='color: #FF00FF'>[database](/core_modules.md#database-modules)</a></span>",
+    "storage": "<span style='color: #FFFF00'>[storage](/core_modules.md#storage-modules)</a></span>",
+    "formatter": "<span style='color: #00FFFF'>[formatter](/core_modules.md#formatter-modules)</a></span>",
 }
 
 TABLE_HEADER = ("Option", "Description", "Default", "Type")
@@ -34,6 +34,7 @@ steps:
 
 """
 
+
 def generate_module_docs():
     yaml = YAML()
     SAVE_FOLDER.mkdir(exist_ok=True)
@@ -48,49 +49,49 @@ def generate_module_docs():
         # generate the markdown file from the __manifest__.py file.
 
         manifest = module.manifest
-        for type in manifest['type']:
+        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'])
+        description = "\n".join(line.lstrip() for line in manifest["description"].split("\n"))
+        types = ", ".join(type_color[t] for t in manifest["type"])
         readme_str = f"""
-# {manifest['name']}
+# {manifest["name"]}
 ```{{admonition}} Module type
 
 {types}
 ```
 {description}
-"""     
-        steps_str = "\n".join(f"  {t}s:\n  - {module.name}" for t in manifest['type'])
+"""
+        steps_str = "\n".join(f"  {t}s:\n  - {module.name}" for t in manifest["type"])
 
-        if not manifest['configs']:
+        if not manifest["configs"]:
             config_string = f"# No configuration options for {module.name}.*\n"
         else:
-
             config_table = header_row
             config_yaml = {}
 
             global_yaml[module.name] = CommentedMap()
-            global_yaml.yaml_set_comment_before_after_key(module.name, f"\n\n{module.display_name} configuration options")
+            global_yaml.yaml_set_comment_before_after_key(
+                module.name, f"\n\n{module.display_name} configuration options"
+            )
 
-
-            for key, value in manifest['configs'].items():
-                type = value.get('type', 'string')
-                if type == 'json_loader':
-                    value['type'] = 'json'
-                elif type == 'str':
+            for key, value in manifest["configs"].items():
+                type = value.get("type", "string")
+                if type == "json_loader":
+                    value["type"] = "json"
+                elif type == "str":
                     type = "string"
-                
-                default = value.get('default', '')
+
+                default = value.get("default", "")
                 config_yaml[key] = default
 
                 global_yaml[module.name][key] = default
 
-                if value.get('help', ''):
-                    global_yaml[module.name].yaml_add_eol_comment(value.get('help', ''), key)
+                if value.get("help", ""):
+                    global_yaml[module.name].yaml_add_eol_comment(value.get("help", ""), key)
 
-                help = "**Required**. " if value.get('required', False) else "Optional. "
-                help += value.get('help', '')
+                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"
                 global_table += f"| `{module.name}.{key}` | {help} | {default} | {type} |\n"
             readme_str += "\n## Configuration Options\n"
@@ -98,18 +99,18 @@ def generate_module_docs():
 
             config_string = io.BytesIO()
             yaml.dump({module.name: config_yaml}, config_string)
-            config_string = config_string.getvalue().decode('utf-8')
+            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']:
+        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']:
+        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:
@@ -117,10 +118,10 @@ def generate_module_docs():
                 f.write(readme_str)
         generate_index(modules_by_type)
 
-    del global_yaml['placeholder']
+    del global_yaml["placeholder"]
     global_string = io.BytesIO()
     global_yaml = yaml.dump(global_yaml, global_string)
-    global_string = global_string.getvalue().decode('utf-8')
+    global_string = global_string.getvalue().decode("utf-8")
     global_yaml = f"```yaml\n{global_string}\n```"
     with open(SAVE_FOLDER / "configs_cheatsheet.md", "w") as f:
         f.write("### Configuration File\n" + global_yaml + "\n### Command Line\n" + global_table)
@@ -144,4 +145,4 @@ def generate_index(modules_by_type):
 
 
 if __name__ == "__main__":
-    generate_module_docs()
+    generate_module_docs()

docs/source/conf.py

@@ -5,7 +5,7 @@ import os
 from importlib.metadata import metadata
 from datetime import datetime
 
-sys.path.append(os.path.abspath('../scripts'))
+sys.path.append(os.path.abspath("../scripts"))
 from scripts import generate_module_docs
 from auto_archiver.version import __version__
 
@@ -20,33 +20,35 @@ project = package_metadata["name"]
 copyright = str(datetime.now().year)
 author = "Bellingcat"
 release = package_metadata["version"]
-language = 'en'
+language = "en"
 
 # -- General configuration ---------------------------------------------------
 extensions = [
-    "myst_parser",                  # Markdown support
-    "autoapi.extension",            # Generate API documentation from docstrings
-    "sphinxcontrib.mermaid",        # Mermaid diagrams
-    "sphinx.ext.viewcode",          # Source code links
+    "myst_parser",  # Markdown support
+    "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.napoleon",  # Google-style and NumPy-style docstrings
     "sphinx.ext.autosectionlabel",
     # 'sphinx.ext.autosummary',       # Summarize module/class/function docs
 ]
 
-templates_path = ['_templates']
+templates_path = ["_templates"]
 exclude_patterns = ["_build", "Thumbs.db", ".DS_Store", ""]
 
 
 # -- AutoAPI Configuration ---------------------------------------------------
-autoapi_type = 'python'
+autoapi_type = "python"
 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 = ["*/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
+autodoc_typehints = "signature"  # Include type hints in the signature
+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_python_use_implicit_namespaces = True
 autoapi_template_dir = "../_templates/autoapi"
 autoapi_options = [
@@ -59,13 +61,13 @@ autoapi_options = [
 
 # -- Markdown Support --------------------------------------------------------
 myst_enable_extensions = [
-    "deflist",              # Definition lists
-    "html_admonition",      # HTML-style admonitions
-    "html_image",           # Inline HTML images
-    "replacements",         # Substitutions like (C)
-    "smartquotes",          # Smart quotes
-    "linkify",              # Auto-detect links
-    "substitution",         # Text substitutions
+    "deflist",  # Definition lists
+    "html_admonition",  # HTML-style admonitions
+    "html_image",  # Inline HTML images
+    "replacements",  # Substitutions like (C)
+    "smartquotes",  # Smart quotes
+    "linkify",  # Auto-detect links
+    "substitution",  # Text substitutions
 ]
 myst_heading_anchors = 2
 myst_fence_as_directive = ["mermaid"]
@@ -76,7 +78,7 @@ source_suffix = {
 }
 
 # -- Options for HTML output -------------------------------------------------
-html_theme = 'sphinx_book_theme'
+html_theme = "sphinx_book_theme"
 html_static_path = ["../_static"]
 html_css_files = ["custom.css"]
 html_title = f"Auto Archiver v{__version__}"
@@ -87,7 +89,6 @@ html_theme_options = {
 }
 
 
-
 copybutton_prompt_text = r">>> |\.\.\."
 copybutton_prompt_is_regexp = True
-copybutton_only_copy_prompt_lines = False
+copybutton_only_copy_prompt_lines = False

docs/source/development/developer_guidelines.md

@@ -32,4 +32,5 @@ testing
 docs
 release
 settings_page
+style_guide
 ```

docs/source/development/docs.md

@@ -36,3 +36,12 @@ open docs/_build/html/index.html
 sphinx-autobuild docs/source docs/_build/html
 ```
 
+
+### Managing Readthedocs (RTD) Versions
+
+Version management is done at [https://app.readthedocs.org/projects/auto-archiver/](https://app.readthedocs.org/projects/auto-archiver/)
+(login required). Once logged in, you can create new versions, delete old versions or change visibility of versions. More info on
+[RTD](https://docs.readthedocs.com/platform/stable/versions.html).
+
+Currently, the Auto Archiver project is set up to automatically create a new docs version for each `vX.Y.Z` release. For more on this,
+see the RTD [instructions on automation](https://docs.readthedocs.com/platform/stable/guides/automation-rules.html) or edit the existing automation rule in the project settings.

docs/source/development/style_guide.md

@@ -0,0 +1,70 @@
+# Style Guide
+
+
+The project uses [Ruff](https://docs.astral.sh/ruff/) for linting and  formatting.
+Our style configurations are set in the `pyproject.toml` file. If needed, you can modify them there.
+
+
+### **Formatting (Auto-Run Before Commit) 🛠️**  
+
+We have a pre-commit hook to run the formatter before you commit.
+This requires you to set it up once locally, then it will run automatically when you commit changes.
+
+```shell
+poetry run pre-commit install
+```
+
+Ruff can also be to run automatically.
+Alternative: Ruff can also be [integrated with most editors](https://docs.astral.sh/ruff/editors/setup/)  for real-time formatting.
+
+If you wish to disable the pre-commit hook (for example, if you want to commit some WIP code) you can use the `--no-verify` flag when you commit.
+For example: `git commit -m "WIP Code" --no-verify`
+
+### **Linting (Check Before Pushing) 🔍**
+
+We recommend you also run the linter before pushing code. 
+
+We have [Makefile](../../../Makefile) commands to run common tasks. 
+
+Tip: if you're on Windows you might need to install `make` first, or alternatively you can use ruff commands directly.
+
+
+**Lint Check:** This outputs a report of any issues found, without attempting to fix them: 
+```shell
+make ruff-check
+```
+
+Tip: To see a more detailed linting report, you can remove the following line from the `pyproject.toml` file:
+```toml
+[tool.ruff]
+
+# Remove this for a more detailed lint report
+output-format = "concise"
+```
+
+**Lint Fix:** This command will attempt to fix some of the issues it picked up with the lint check.
+
+Note not all warnings can be fixed automatically.
+
+⚠️ Warning: This can cause breaking changes. ⚠️
+
+Most fixes are safe, but some non-standard practices such as dynamic loading are not picked up by linters. Ensure you check any modifications by this before committing them.
+```shell
+make ruff-fix
+```
+
+**Changing Configurations ⚙️**
+
+
+Our rules are quite lenient for general usage, but if you want to run more rigorous checks you can then run checks with additional rules to see more nuanced errors which you can review manually.
+Check out the [ruff documentation](https://docs.astral.sh/ruff/configuration/) for the full list of rules.
+One example is to extend the selected rules for linting the `pyproject.toml` file:
+
+```toml 
+[tool.ruff.lint]
+# Extend the rules to check for by adding them to this option:
+# See documentation for more details: https://docs.astral.sh/ruff/rules/
+extend-select = ["B"]
+```
+
+Then re-run the `make ruff-check` command to see the new rules in action.

docs/source/how_to/authentication_how_to.md

@@ -106,5 +106,117 @@ Finally,Some important things to remember:
 
 ## Authenticating on XXXX site with username/password
 
-```{note} This section is still under construction 🚧
+```{note} 
+This section is still under construction 🚧
 ```
+
+
+# Proof of Origin Tokens
+
+YouTube uses **Proof of Origin Tokens (POT)** as part of its bot detection system to verify that requests originate from valid clients. If a token is missing or invalid, some videos may return errors like "Sign in to confirm you're not a bot."
+
+yt-dlp provides [a detailed guide to POTs](https://github.com/yt-dlp/yt-dlp/wiki/PO-Token-Guide).
+
+### How Auto Archiver Uses POT
+This feature is enabled for the Generic Archiver via two yt-dlp plugins:
+
+- **Client-side plugin**: [yt-dlp-get-pot](https://github.com/coletdjnz/yt-dlp-get-pot)  
+  Detects when a token is required and requests one from a provider.
+
+- **Provider plugin**: [bgutil-ytdlp-pot-provider](https://github.com/Brainicism/bgutil-ytdlp-pot-provider)  
+  Includes both a Python plugin and a **Node.js server or script** to generate the token.
+
+These are installed in our Poetry environment.
+
+### Integration Methods
+
+**Docker (Recommended)**:
+
+When running the Auto Archiver using the Docker image, we use the [Node.js token generation script](https://github.com/Brainicism/bgutil-ytdlp-pot-provider/tree/master/server).
+This is to avoid managing a separate server process, and is handled automatically inside the Docker container when needed.
+
+This is already included in the Docker image, however if you need to disable this you can set the config option `bguils_po_token_method` under the `generic_extractor` section of your `orchestration.yaml` config file to "disabled".
+```yaml
+generic_extractor:
+  bguils_po_token_method: "disabled"
+```
+
+**PyPi/ Local**:
+
+When using the Auto Archiver PyPI package, or running locally, you will need additional system requirements to run the token generation script, namely either Docker, or Node.js and Yarn.
+
+See the [bgutil-ytdlp-pot-provider](https://github.com/Brainicism/bgutil-ytdlp-pot-provider?tab=readme-ov-file#a-http-server-option) documentation for more details.
+
+⚠️WARNING⚠️: This will add the server scripts to the home directory of wherever this is running.
+
+- You can set the config option `bguils_po_token_method` under the `generic_extractor` section of your `orchestration.yaml` config file to "script" to enable the token generation script process locally.
+- Alternatively you can run the bgutil-ytdlp-pot-provider server separately using their Docker image or Node.js server.
+
+### Notes
+
+- The token generation script is only triggered when needed by yt-dlp, so it should have no effect unless YouTube requests a POT.
+- If you're running the Auto Archiver in Docker, this is set up automatically.
+- If you're running locally, you'll need to run the setup script manually or enable the feature in your config.
+- You can set up both the server and the script, and the plugin will fallback on each other if needed. This is recommended for robustness!
+
+### Configurations: 
+
+## Configurations Summary
+
+| Option     | Behavior                                                                                                                                   | Docker Default? |
+|------------| ------------------------------------------------------------------------------------------------------------------------------------------ | --------------- |
+| `auto`     | Docker: Automatically downloads and uses the token generation script. Local: Does nothing; assumes a separate server is running externally. | ✅ Yes           |
+| `script`   | Explicitly downloads and uses the token generation script, even locally.                                                                   | ❌ No            |
+| `disabled` | Disables token generation completely.                                                                                                      | ❌ No            |
+
+Example configuration:
+
+ 
+```yaml
+generic_extractor:
+  # ...  
+  bguils_po_token_method: "script"
+  # For debugging add the verbose flag here:
+  ytdlp_args: "--no-abort-on-error --abort-on-error --verbose"
+
+```
+
+**Advanced Configuration:**
+
+If you change the default port of the bgutil-ytdlp-pot-provider server, you can pass the updated values using our `extractor_args` option for the gereric extractor.
+
+```yaml
+generic_extractor:
+  ytdlp_args: "--no-abort-on-error --abort-on-error --verbose"
+  ytdlp_update_interval: 5
+  bguils_po_token_method: "script"
+  extractor_args:
+    youtube:
+      getpot_bgutil_baseurl: "http://127.0.0.1:8080"
+      player_client: web,tv
+```
+For more details on this for bgutils see [here](https://github.com/Brainicism/bgutil-ytdlp-pot-provider?tab=readme-ov-file#usage)
+
+### Checking the logs
+
+To verify that the POT process working, look for the following lines in your log after adding the config option:
+
+```shell
+[GetPOT] BgUtilScript: Generating POT via script: /Users/you/bgutil-ytdlp-pot-provider/server/build/generate_once.js
+[debug] [GetPOT] BgUtilScript: Executing command to get POT via script: /Users/you/.nvm/versions/node/v20.18.0/bin/node /Users/you/bgutil-ytdlp-pot-provider/server/build/generate_once.js -v ymCMy8OflKM
+[debug] [GetPOT] BgUtilScript: stdout:
+{"poToken":"MlMxojNFhEJvUzGeHEkVRSK_luXtwcDnwSNIOgaUutqB7t99nmlNvtWgYayboopG6ZopZgmQ-6PJCWEMHv89MIiFGGlJRY25Fkwzxmia_8uYgf5AWf==","generatedAt":"2025-03-26T10:45:26.156Z","visitIdentifier":"ymCMy8OflKM"}
+[debug] [GetPOT] Fetching gvs PO Token for tv client
+```
+
+If it can't find the script or something, you'll see something like this:
+```shell
+[debug] [GetPOT] Fetching player PO Token for tv client
+WARNING: [GetPOT] BgUtilScript: Script path doesn't exist: /Users/you/bgutil-ytdlp-pot-provider/server/build/generate_once.js. Please make sure the script has been transpiled correctly.
+WARNING: [GetPOT] BgUtilHTTP: Error reaching GET http://127.0.0.1:4416/ping (caused by TransportError). Please make sure that the server is reachable at http://127.0.0.1:4416.
+[debug] [GetPOT] No player PO Token provider available for tv client
+```
+
+In this case check that the script has been transpiled correctly and is available at the path specified in the log, 
+or that the server is running and reachable.
+

docs/source/how_to/gsheets_setup.md

@@ -6,12 +6,43 @@ This guide explains how to set up Google Sheets to process URLs automatically an
 2. Setting up a service account so Auto Archiver can access the sheet
 3. Setting the Auto Archiver settings
 
-### 1. Setting up your Google Sheet
 
-Any Google sheet must have at least *one* column, with the name 'link' (you can change this name afterwards). This is the column with the URLs that you want the Auto Archiver to archive. 
-Your sheet can have many other columns that the Auto Archiver can use, and you can also include any additional columns for your own personal use. The order of the columns does not matter, the naming just needs to be correctly assigned to its corresponding value in the configuration file.
+## 1. Setting up a Google Service Account
 
-We recommend copying [this template Google Sheet](https://docs.google.com/spreadsheets/d/1NJZo_XZUBKTI1Ghlgi4nTPVvCfb0HXAs6j5tNGas72k/edit?usp=sharing) as a starting point for your project, as this matches the default column names.
+Once your Google Sheet is set up, you need to create what's called a 'service account' that will allow the Auto Archiver to access it.
+
+To do this, you can either:
+* a) follow the steps in [this guide](https://gspread.readthedocs.io/en/latest/oauth2.html) all the way up until step 8. You should have downloaded a file called `service_account.json` and should save it in the `secrets/` folder
+* b) run the following script to automatically generate the file:
+```{code} bash
+https://raw.githubusercontent.com/bellingcat/auto-archiver/refs/heads/main/scripts/generate_google_services.sh | bash -s --
+```
+This uses gcloud to create a new project, a new user and downloads the service account automatically for you. The service account file will have the name `service_account-XXXXXXX.json` where XXXXXXX is a random 16 letter/digit string for the project created.
+
+```{note}
+To save the generated file to a different folder, pass an argument as follows:
+```{code} bash
+https://raw.githubusercontent.com/bellingcat/auto-archiver/refs/heads/main/scripts/generate_google_services.sh | bash -s -- /path/to/secrets
+```
+
+----------
+
+Once you've downloaded the file, you can save it to `secrets/service_account.json` (the default name), or to another file and then change the location in the settings (see step 4).
+
+Also make sure to **note down** the email address for this service account. You'll need that for step 3.
+
+```{note}
+The email address created in this step can be found either by opening the `service_account.json` file, or if you used b) the `generate_google_services.sh` script, then the script will have printed it out for you.
+
+The email address will look something like `user@project-name.iam.gserviceaccount.com`
+```
+
+
+## 2. Setting up your Google Sheet
+
+We recommend copying [this template Google Sheet](https://docs.google.com/spreadsheets/d/1NJZo_XZUBKTI1Ghlgi4nTPVvCfb0HXAs6j5tNGas72k/edit?usp=sharing) as a starting point for your project, as this matches all the columns required.
+
+But if you like, you can also create your own custom sheet. The only columns required are 'link', 'archive status', and 'archive location'. 'link' is the column with the URLs that you want the Auto Archiver to archive, the other two record the archival status and result. 
 
 Here's an overview of all the columns, and what a complete sheet would look like.
 
@@ -46,21 +77,18 @@ In this example the Ghseet Feeder and Gsheet DB are being used, and the archive
 
 ![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)
 
-We'll change the name of the 'Destination Folder' column in step 3.
+We'll change the name of the 'Destination Folder' column in the Step 4a.
 
-## 2. Setting up your Service Account
+## 3. Share your Google Sheet with your Service Account email address
 
-Once your Google Sheet is set up, you need to create what's called a 'service account' that will allow the Auto Archiver to access it.
+Remember that email address you copied in Step 1? Now that you've set up your Google sheet, click 'Share' in the top
+right hand corner and enter the email address. Make sure to give the account **Editor** access. Here's how that looks:
 
-To do this, follow the steps in [this guide](https://gspread.readthedocs.io/en/latest/oauth2.html) all the way up until step 8. You should have downloaded a file called `service_account.json` and shared the Google Sheet with the log 'client_email' email address in this file.
+![Share sheet](share_sheet.png)
 
-Once you've downloaded the file, save it to `secrets/service_account.json`
+## 4. Setting up the configuration file
 
-## 3. Setting up the configuration file
-
-Now that you've set up your Google sheet, and you've set up the service account so Auto Archiver can access the sheet, the final step is to set your configuration.
-
-First, make sure you have `gsheet_feeder_db` set in the `steps.feeders` section of your config. If you wish to store the results of the archiving process back in your Google sheet, make sure to also set the `ghseet_db` settig in the `steps.databases` section. Here's how this might look:
+The final step is to set your configuration. First, make sure you have `gsheet_feeder_db` set in the `steps.feeders` section of your config. If you wish to store the results of the archiving process back in your Google sheet, make sure to also put `gsheet_feeder_db` setting in the `steps.databases` section. Here's how this might look:
 
 ```{code} yaml
 steps:
@@ -75,22 +103,25 @@ steps:
 Next, set up the `gsheet_feeder_db` configuration settings in the 'Configurations' part of the config `orchestration.yaml` file. Open up the file, and set the `gsheet_feeder_db.sheet` setting or the `gsheet_feeder_db.sheet_id` setting. The `sheet` should be the name of your sheet, as it shows in the top left of the sheet. 
 For example, the sheet [here](https://docs.google.com/spreadsheets/d/1NJZo_XZUBKTI1Ghlgi4nTPVvCfb0HXAs6j5tNGas72k/edit?gid=0#gid=0) is called 'Public Auto Archiver template'.
 
+If you saved your `service_account.json` file to anywhere other than the default location (`secrets/service_account.json`), then also make sure to change that now:
+
 Here's how this might look:
 
 ```{code} yaml
 ...
 gsheet_feeder_db:
     sheet: 'My Awesome Sheet'
+    service_account: secrets/service_account-XXXXX.json # or leave as secrets/service_account.json
     ...
 ```
 
 You can also pass these settings directly on the command line without having to edit the file, here'a an example of how to do that (using docker):
 
-`docker run --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive bellingcat/auto-archiver:dockerize --gsheet_feeder_db.sheet "My Awesome Sheet 2"`. 
+`docker run -it --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive bellingcat/auto-archiver:dockerize --gsheet_feeder_db.sheet "My Awesome Sheet 2"`. 
 
 Here, the sheet name has been overridden/specified in the command line invocation.
 
-### 3a. (Optional) Changing the column names
+### 4a. (Optional) Changing the column names
 
 In step 1, we said we would change the name of the 'Destination Folder'. Perhaps you don't like this name, or already have a sheet with a different name. In our example here, we want to name this column 'Save Folder'. To do this, we need to edit the `ghseet_feeder_db.column` setting in the configuration file. 
 For more information on this setting, see the [Gsheet Feeder Database docs](../modules/autogen/feeder/gsheet_feeder_db.md#configuration-options). We will first copy the default settings from the Gsheet Feeder docs for the 'column' settings, and then edit the 'Destination Folder' section to rename it 'Save Folder'. Our final configuration section looks like:

docs/source/how_to/run_instagrapi_server.md

@@ -0,0 +1,169 @@
+# InstagrAPI Server
+
+The instagram API Extractor requires access to a running instance of the InstagrAPI server. 
+We have a lightweight script with the endpoints required for our Instagram API Extractor module which you can run locally, or via Docker.
+
+
+
+⚠️ Warning: Remember that it's best not to use your own personal account for archiving. [Here's why](../installation/authentication.md#recommendations-for-authentication).
+## Quick Start: Using Docker
+
+We've provided a convenient shell script (`run_instagrapi_server.sh`) that simplifies the process of setting up and running the Instagrapi server in Docker. This script handles building the Docker image, setting up credentials, and starting the container.
+
+### 🔧 Running the script:
+
+Run this script either from the repository root or from within the `scripts/instagrapi_server` directory:
+
+```bash
+./scripts/instagrapi_server/run_instagrapi_server.sh
+```
+
+This script will:
+- Prompt for your Instagram username and password.
+- Create the necessary `.env` file.
+- Build the Docker image.
+- Start the Docker container and authenticate with Instagram, creating a session automatically.
+
+### ⏱ To run the server again later:
+```bash
+docker start ig-instasrv
+```
+
+### 🐛 Debugging:
+View logs:
+```bash
+docker logs ig-instasrv
+```
+
+
+### Overview: How the Setup Works
+
+1. You enter your Instagram credentials in a local `.env` file
+2. You run the server **once locally** to generate a session file
+3. After that, you can choose to run the server again locally or inside Docker without needing to log in again
+
+---
+
+## Optional: Manual / Local Setup
+
+If you'd prefer to run the server manually (without Docker), you can follow these steps:
+
+
+1. **Navigate to the server folder (and stay there for the rest of this guide)**:
+   ```bash
+   cd scripts/instagrapi_server
+   ```
+
+2. **Create a `secrets/` folder** (if it doesn't already exist in `scripts/instagrapi_server`):
+   ```bash
+   mkdir -p secrets
+   ```
+
+3. **Create a `.env` file** inside `secrets/` with your Instagram credentials:
+   ```dotenv
+   INSTAGRAM_USERNAME="your_username"
+   INSTAGRAM_PASSWORD="your_password"
+   ```
+
+4. **Install dependencies** using the pyproject.toml file:
+  
+   ```bash
+   poetry install --no-root
+   ```
+
+5. **Run the server locally**:
+   ```bash
+   poetry run uvicorn src.instaserver:app --port 8000
+   ```
+
+6. **Watch for the message**:
+   ```
+   Login successful, session saved.
+   ```
+
+✅ Your session is now saved to `secrets/instagrapi_session.json`.
+
+### To run it again locally:
+```bash
+poetry run uvicorn src.instaserver:app --port 8000
+```
+
+---
+
+## Adding the API Endpoint to Auto Archiver
+
+The server should now be running within that session, and accessible at  http://127.0.0.1:8000 
+
+You can set this in the Auto Archiver orchestration.yaml file like this:
+```yaml
+instagram_api_extractor:
+  api_endpoint: http://127.0.0.1:8000
+```
+
+
+---
+
+## 2. Running the Server Again
+
+Once the session file is created, you should be able to run the server without logging in again.
+
+### To run it locally (from scripts/instagrapi_server):
+```bash
+poetry run uvicorn src.instgrapinstance.instaserver:app --port 8000
+```
+
+---
+
+## 3. Running via Docker (After Setup is Complete, either locally or via the script)
+
+Once the `instagrapi_session.json` and `.env` files are set up, you can pass them Docker and it should authenticate successfully.
+
+### 🔨 Build the Docker image manually:
+```bash
+docker build -t instagrapi-server .
+```
+
+### ▶️ Run the container:
+```bash
+docker run -d \
+  --env-file secrets/.env \
+  -v "$(pwd)/secrets:/app/secrets" \
+  -p 8000:8000 \
+  --name ig-instasrv \
+  instagrapi-server
+```
+
+This passes the /secrets/ directory to docker as well as the environment variables from the `.env` file.
+
+
+
+---
+
+## 4. Optional Cleanup
+
+- **Stop the Docker container**:
+  ```bash
+  docker stop ig-instasrv
+  ```
+
+- **Remove the container**:
+  ```bash
+  docker rm ig-instasrv
+  ```
+
+- **Remove the Docker image**:
+  ```bash
+  docker rmi instagrapi-server
+  ```
+
+### ⏱ To run again later:
+```bash
+docker start ig-instasrv
+```
+
+---
+
+##  Notes
+
+- Never share your `.env` or `instagrapi_session.json` — these contain sensitive login data. 
+- If you want to reset your session, simply delete the `secrets/instagrapi_session.json` file and re-run the local server.

docs/source/installation/authentication.md

@@ -6,6 +6,15 @@ 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 accessing the website. Adding real login information to auto-archiver can sometimes bypass this.
 
+```{note}
+
+The Authentication framework currently only works with the following modules:
+* Generic Extractor
+* Screenshot Enricher
+
+To authenticate for WACZ archiving, see the instructions on the [](../modules/autogen/enricher/wacz_extractor_enricher.md) page.
+```
+
 ## 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. Currently, auto-archiver supports the following authentication types:
@@ -27,7 +36,7 @@ You can save your authentication information directly inside your orchestration
 
 The Username & Password, and API settings only work with the Generic Extractor. Other modules (like the screenshot enricher) can only use the `cookies` options. Furthermore, many sites can still detect bots and block username/password logins. Twitter/X and YouTube are two prominent ones that block username/password logging.
 
-One of the 'Cookies' options is recommended for the most robust archiving.
+One of the 'Cookies' options is recommended for the most robust archiving, but it still isn't guaranteed to work.
 ```
 
 ```{code} yaml

docs/source/installation/faq.md

@@ -0,0 +1,60 @@
+# Frequently Asked Questions
+
+
+### Q: What websites does the Auto Archiver support?
+**A:** The Auto Archiver works for a large variety of sites. Firstly, the Auto Archiver can download
+and archive any video website supported by YT-DLP, a powerful video-downloading tool ([full list of of
+sites here](https://github.com/yt-dlp/yt-dlp/blob/master/supportedsites.md)). Aside from these sites,
+there are various different 'Extractors' for specific websites. See the full list of extractors that 
+are available on the [extractors](../modules/extractor.md) page. Some sites supported include:
+
+* Twitter
+* Instagram
+* Telegram
+* VKontact
+* Tiktok
+* Bluesky
+
+```{note} What websites the Auto Archiver can archie depends on what extractors you have enabled in
+your configuration. See [configuration](./configurations.md) for more info.
+```
+
+### Q: Does the Auto Archiver only work for social media posts ?
+**A:** No, the Auto Archiver can archive any web page on the internet, not just social media posts.
+However, for social media posts Auto Archiver can extract more relevant/useful information (such as 
+post comments, likes, author etc.) which may not be available for a generic website. If you are looking
+to more generally archive webpages, then you should make sure to enable the [](../modules/autogen/extractor/wacz_extractor_enricher.md)
+and the [](../modules/autogen/extractor/wayback_extractor_enricher.md).
+
+### Q: What kind of data is stored for each webpage that's archived?
+**A:** This depends on the website archived, but more generally, for social media posts any videos and photos in
+the post will be archived. For video sites, the video will be downloaded separately. For most of these sites, additional
+metadata such as published date, uploader/author and ratings/comments will also be saved. Additionally, further data can be
+saved depending on the enrichers that you have enabled. Some other types of data saved are timestamps if you have the 
+[](../modules/autogen/enricher/timestamping_enricher.md) or [](../modules/autogen/enricher/opentimestamps_enricher.md) enabled,
+screenshots of the web page with the [](../modules/autogen/enricher/screenshot_enricher.md), and for videos, thumbnails of the
+video with the [](../modules/autogen/enricher/thumbnail_enricher.md). You can also store things like hashes (SHA256, or pdq hashes)
+with the various hash enrichers.
+
+### Q: Where is my data stored?
+**A:** With the default configuration, data is stored on your local computer in the `local_storage` folder. You can adjust these settings by
+changing the [storage modules](../modules/storage.md) you have enabled. For example, you could choose to store your data in an S3 bucket or 
+on Google Drive. 
+
+```{note}
+You can choose to store your data in multiple places, for example your local drive **and** an S3 bucket for redundancy.
+```
+
+### Q: What should I do is something doesn't work?
+**A:** First, read through the log files to see if you can find a specific reason why something isn't working. Learn more about logging
+and how to enable debug logging in the [Logging Howto](../how_to/logging.md).
+
+If you cannot find an answer in the logs, then try searching this documentation or existing / closed issues on the [Github Issue Tracker](https://github.com/bellingcat/auto-archiver/issues?q=is%3Aissue%20). If you still cannot find an answer, then consider opening an issue on the Github Issue Tracker or asking in the Bellingcat Discord
+'Auto Archiver' group.
+
+#### Common reasons why an archiving might not work:
+
+* The website may have temporarily adjusted its settings - sometimes sites like Telegram or Twitter adjust their scraping protection settings. Often,
+waiting a day or two and then trying again can work.
+* The site requires you to be logged in - you could try using cookies or authentication to bypass any blocks. See [](../installation/authentication.md) for more information.
+* The website you're trying to archive has changed its settings/structure. Make sure you're using the latest version of Auto Archiver and try again.

docs/source/installation/installation.md

@@ -1,5 +1,11 @@
 # Installation
 
+```{toctree}
+:maxdepth: 1
+
+upgrading.md
+```
+
 There are 3 main ways to use the auto-archiver. We recommend the 'docker' method for most uses. This installs all the requirements in one command.
 
 1. Easiest (recommended): [via docker](#installing-with-docker)

docs/source/installation/setup.md

@@ -1,7 +1,6 @@
 # Getting Started
 
 ```{toctree}
-:maxdepth: 1
 :hidden:
 
 installation.md
@@ -9,6 +8,7 @@ configurations.md
 config_editor.md
 authentication.md
 requirements.md
+faq.md
 config_cheatsheet.md
 ```
 
@@ -27,17 +27,18 @@ The way you run the Auto Archiver depends on how you installed it (docker instal
 If you installed Auto Archiver using docker, open up your terminal, and copy-paste / type the following command:
 
 ```bash
-docker run --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive bellingcat/auto-archiver
+docker run -it --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive bellingcat/auto-archiver
  ```
 
 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 with settings
+   2. `-it` tells docker to run in 'interactive mode' so that we get nice colour logs
+   3. `--rm` makes sure this container is removed after execution (less garbage locally)
+   4. `-v $PWD/secrets:/app/secrets` - your secrets folder with settings
       1. `-v` is a volume flag which means a folder that you have on your computer will be connected to a folder inside the docker container
       2. `$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
+   5.  `-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 
@@ -48,13 +49,14 @@ The invocations below will run the auto-archiver Docker image using a configurat
 
 ```bash
 # Have auto-archiver run with the default settings, generating a settings file in ./secrets/orchestration.yaml
-docker run --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive bellingcat/auto-archiver
+docker run -it --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive bellingcat/auto-archiver
 
 # uses the same configuration, but with the `gsheet_feeder`, a header on row 2 and with some different column names
+# Note this expects you to have followed the [Google Sheets setup](how_to/google_sheets.md) and added your service_account.json to the `secrets/` folder
 # 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 --feeders=gsheet_feeder --gsheet_feeder.sheet="use it on another sheets doc" --gsheet_feeder.header=2 --gsheet_feeder.columns='{"url": "link"}'
+docker run -it --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive bellingcat/auto-archiver --feeders=gsheet_feeder --gsheet_feeder.sheet="use it on another sheets doc" --gsheet_feeder.header=2 --gsheet_feeder.columns='{"url": "link"}'
 # Runs auto-archiver for the first time, but in 'full' mode, enabling all modules to get a full settings file
-docker run --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive bellingcat/auto-archiver --mode full
+docker run -it --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive bellingcat/auto-archiver --mode full
 ```
 
 ------------

docs/source/installation/upgrading.md

@@ -0,0 +1,30 @@
+
+# Upgrading
+
+If an update is available, then you will see a message in the logs when you
+run Auto Archiver. Here's what those logs look like:
+
+```{code} bash
+********* IMPORTANT: UPDATE AVAILABLE ********
+A new version of auto-archiver is available (v0.13.6, you have 0.13.4)
+Make sure to update to the latest version using: `pip install --upgrade auto-archiver`
+```
+
+Upgrading Auto Archiver depends on the way you installed it.
+
+## Docker
+
+To upgrade using docker, update the docker image with:
+
+```
+docker pull bellingcat/auto-archiver:latest 
+```
+
+## Pip
+
+To upgrade the pip package, use:
+
+```
+pip install --upgrade auto-archiver
+```
+

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [project]
 name = "auto-archiver"
-version = "0.13.5"
+version = "1.0.0"
 description = "Automatically archive links to videos, images, and social media content from Google Sheets (and more)."
 
 requires-python = ">=3.10,<3.13"
@@ -41,11 +41,9 @@ dependencies = [
     "instaloader (>=0.0.0)",
     "tqdm (>=0.0.0)",
     "jinja2 (>=0.0.0)",
-    "pyOpenSSL (==24.2.1)",
-    "cryptography (>=41.0.0,<42.0.0)",
     "boto3 (>=1.28.0,<2.0.0)",
     "dataclasses-json (>=0.0.0)",
-    "yt-dlp (>=2025.1.26,<2026.0.0)",
+    "yt-dlp (>=2025.3.21,<2026.0.0)",
     "numpy (==2.1.3)",
     "vk-url-scraper (>=0.0.0)",
     "requests[socks] (>=0.0.0)",
@@ -53,10 +51,12 @@ dependencies = [
     "jsonlines (>=0.0.0)",
     "pysubs2 (>=0.0.0)",
     "retrying (>=0.0.0)",
-    "tsp-client (>=0.0.0)",
-    "certvalidator (>=0.0.0)",
     "rich-argparse (>=1.6.0,<2.0.0)",
     "ruamel-yaml (>=0.18.10,<0.19.0)",
+    "rfc3161-client (>=1.0.1,<2.0.0)",
+    "cryptography (>44.0.1,<45.0.0)",
+    "opentimestamps (>=0.4.5,<0.5.0)",
+    "bgutil-ytdlp-pot-provider (>=0.7.3,<0.8.0)",
 ]
 
 [tool.poetry.group.dev.dependencies]
@@ -64,6 +64,8 @@ pytest = "^8.3.4"
 autopep8 = "^2.3.1"
 pytest-loguru = "^0.4.0"
 pytest-mock = "^3.14.0"
+ruff = "^0.9.10"
+pre-commit = "^4.1.0"
 
 [tool.poetry.group.docs.dependencies]
 sphinx = "^8.1.3"
@@ -89,4 +91,29 @@ documentation = "https://github.com/bellingcat/auto-archiver"
 markers = [
     "download: marks tests that download content from the network",
     "incremental: marks a class to run tests incrementally. If a test fails in the class, the remaining tests will be skipped",
-]
+]
+
+[tool.ruff]
+#exclude = ["docs"]
+line-length = 120
+# Remove this for a more detailed lint report
+output-format = "concise"
+# TODO: temp ignore rule for timestamping_enricher to allow for open PR
+exclude = ["src/auto_archiver/modules/timestamping_enricher/*"]
+
+
+[tool.ruff.lint]
+# Extend the rules to check for by adding them to this option:
+# See documentation for more details: https://docs.astral.sh/ruff/rules/
+#extend-select = ["B"]
+
+[tool.ruff.lint.per-file-ignores]
+# Ignore import violations in __init__.py files
+"__init__.py" = ["F401", "F403"]
+# Ignore 'useless expression' in manifest files.
+"__manifest__.py" = ["B018"]
+
+
+[tool.ruff.format]
+docstring-code-format = false
+

scripts/create_update_gdrive_oauth_token.py

@@ -1,5 +1,6 @@
 import os.path
-import click, json
+import click
+import json
 
 from google.auth.transport.requests import Request
 from google.oauth2.credentials import Credentials
@@ -70,11 +71,7 @@ def main(credentials, token):
         print(emailAddress)
 
         # Call the Drive v3 API and return some files
-        results = (
-            service.files()
-            .list(pageSize=10, fields="nextPageToken, files(id, name)")
-            .execute()
-        )
+        results = service.files().list(pageSize=10, fields="nextPageToken, files(id, name)").execute()
         items = results.get("files", [])
 
         if not items:

scripts/generate_google_services.sh

@@ -0,0 +1,135 @@
+#!/usr/bin/env bash
+
+set -e  # Exit on error
+
+
+UUID=$(LC_ALL=C tr -dc a-z0-9 </dev/urandom | head -c 16) 
+PROJECT_NAME="auto-archiver-$UUID"
+ACCOUNT_NAME="autoarchiver"
+KEY_FILE="service_account-$UUID.json"
+DEST_DIR="$1"
+
+echo "====================================================="
+echo "🔧 Auto-Archiver Google Services Setup Script"
+echo "====================================================="
+echo "This script will:"
+echo "  1. Install Google Cloud SDK if needed"
+echo "  2. Create a Google Cloud project named $PROJECT_NAME"
+echo "  3. Create a service account for Auto-Archiver"
+echo "  4. Generate a key file for API access"
+echo ""
+echo "  Tip: Pass a directory path as an argument to this script to move the key file there"
+echo "  e.g. ./generate_google_services.sh /path/to/secrets"
+echo "====================================================="
+
+# Check and install Google Cloud SDK based on platform
+install_gcloud_sdk() {
+    if command -v gcloud &> /dev/null; then
+        echo "✅ Google Cloud SDK is already installed"
+        return 0
+    fi
+
+    echo "📦 Installing Google Cloud SDK..."
+    
+    # Detect OS
+    case "$(uname -s)" in
+        Darwin*)
+            if command -v brew &> /dev/null; then
+                echo "🍺 Installing via Homebrew..."
+                brew install google-cloud-sdk --cask
+            else
+                echo "📥 Downloading Google Cloud SDK for macOS..."
+                curl -O https://dl.google.com/dl/cloudsdk/channels/rapid/downloads/google-cloud-cli-latest-darwin-x86_64.tar.gz
+                tar -xf google-cloud-cli-latest-darwin-x86_64.tar.gz
+                ./google-cloud-sdk/install.sh --quiet
+                rm google-cloud-cli-latest-darwin-x86_64.tar.gz
+                echo "🔄 Please restart your terminal and run this script again"
+                exit 0
+            fi
+            ;;
+        Linux*)
+            echo "📥 Downloading Google Cloud SDK for Linux..."
+            curl -O https://dl.google.com/dl/cloudsdk/channels/rapid/downloads/google-cloud-cli-latest-linux-x86_64.tar.gz
+            tar -xf google-cloud-cli-latest-linux-x86_64.tar.gz
+            ./google-cloud-sdk/install.sh --quiet
+            rm google-cloud-cli-latest-linux-x86_64.tar.gz
+            echo "🔄 Please restart your terminal and run this script again"
+            exit 0
+            ;;
+        CYGWIN*|MINGW*|MSYS*)
+            echo "⚠️ Windows detected. Please follow manual installation instructions at:"
+            echo "https://cloud.google.com/sdk/docs/install-sdk"
+            exit 1
+            ;;
+        *)
+            echo "⚠️ Unknown operating system. Please follow manual installation instructions at:"
+            echo "https://cloud.google.com/sdk/docs/install-sdk"
+            exit 1
+            ;;
+    esac
+    
+    echo "✅ Google Cloud SDK installed"
+}
+
+# Install Google Cloud SDK if needed
+install_gcloud_sdk
+
+# Login to Google Cloud
+if gcloud auth list --filter=status:ACTIVE --format="value(account)" | grep -q "@"; then
+    echo "✅ Already authenticated with Google Cloud"
+else
+    echo "🔑 Authenticating with Google Cloud..."
+    gcloud auth login
+fi
+
+# Create project
+echo "🌟 Creating Google Cloud project: $PROJECT_NAME"
+gcloud projects create $PROJECT_NAME
+
+# Create service account
+echo "👤 Creating service account: $ACCOUNT_NAME"
+gcloud iam service-accounts create $ACCOUNT_NAME --project $PROJECT_NAME
+
+# Enable required APIs (uncomment and add APIs as needed)
+echo "⬆️ Enabling required Google APIs..."
+gcloud services enable sheets.googleapis.com --project $PROJECT_NAME
+gcloud services enable drive.googleapis.com --project $PROJECT_NAME
+
+# Get the service account email
+echo "📧 Retrieving service account email..."
+ACCOUNT_EMAIL=$(gcloud iam service-accounts list --project $PROJECT_NAME --format="value(email)")
+
+# Create and download key
+echo "🔑 Generating service account key file: $KEY_FILE"
+gcloud iam service-accounts keys create $KEY_FILE --iam-account=$ACCOUNT_EMAIL
+
+# move the file to TARGET_DIR if provided
+if [[ -n "$DEST_DIR" ]]; then
+    # Expand `~` if used
+    DEST_DIR=$(eval echo "$DEST_DIR")
+
+    # Ensure the directory exists
+    if [[ ! -d "$DEST_DIR" ]]; then
+        mkdir -p "$DEST_DIR"
+    fi
+
+    DEST_PATH="$DEST_DIR/$KEY_FILE"
+    echo "🚚 Moving key file to: $DEST_PATH"
+    mv "$KEY_FILE" "$DEST_PATH"
+    KEY_FILE="$DEST_PATH"
+fi
+
+echo "====================================================="
+echo "✅ SETUP COMPLETE!"
+echo "====================================================="
+echo "📝 Important Information:"
+echo "  • Project Name: $PROJECT_NAME"
+echo "  • Service Account: $ACCOUNT_EMAIL"
+echo "  • Key File: $KEY_FILE"
+echo ""
+echo "📋 Next Steps:"
+echo "  1. Share any Google Sheets with this email address:"
+echo "     $ACCOUNT_EMAIL"
+echo "  2. Move $KEY_FILE to your auto-archiver secrets directory"
+echo "  3. Update your auto-archiver config to use this key file (if needed)"
+echo "====================================================="

scripts/generate_settings_schema.py

@@ -8,12 +8,14 @@ from auto_archiver.core.module import ModuleFactory
 from auto_archiver.core.consts import MODULE_TYPES
 from auto_archiver.core.config import EMPTY_CONFIG
 
+
 class SchemaEncoder(json.JSONEncoder):
     def default(self, obj):
         if isinstance(obj, set):
             return list(obj)
         return json.JSONEncoder.default(self, obj)
 
+
 # Get available modules
 module_factory = ModuleFactory()
 available_modules = module_factory.available_modules()
@@ -21,32 +23,41 @@ available_modules = module_factory.available_modules()
 modules_by_type = {}
 # Categorize modules by type
 for module in available_modules:
-    for type in module.manifest.get('type', []):
+    for type in module.manifest.get("type", []):
         modules_by_type.setdefault(type, []).append(module)
 
-all_modules_ordered_by_type = sorted(available_modules, key=lambda x: (MODULE_TYPES.index(x.type[0]), not x.requires_setup))
+all_modules_ordered_by_type = sorted(
+    available_modules, key=lambda x: (MODULE_TYPES.index(x.type[0]), not x.requires_setup)
+)
 
 yaml: YAML = YAML()
 
 config_string = io.BytesIO()
 yaml.dump(EMPTY_CONFIG, config_string)
-config_string = config_string.getvalue().decode('utf-8')
+config_string = config_string.getvalue().decode("utf-8")
 output_schema = {
-    'modules': dict((module.name, 
-                     {
-                         'name': module.name,
-                         'display_name': module.display_name,
-                         'manifest': module.manifest,
-                         'configs': module.configs or None
-                         }
-                         ) for module in all_modules_ordered_by_type),
-    'steps': dict((f"{module_type}s", [module.name for module in modules_by_type[module_type]]) for module_type in MODULE_TYPES),
-    'configs': [m.name for m in all_modules_ordered_by_type if m.configs],
-    'module_types': MODULE_TYPES,
-    'empty_config': config_string
+    "modules": dict(
+        (
+            module.name,
+            {
+                "name": module.name,
+                "display_name": module.display_name,
+                "manifest": module.manifest,
+                "configs": module.configs or None,
+            },
+        )
+        for module in all_modules_ordered_by_type
+    ),
+    "steps": dict(
+        (f"{module_type}s", [module.name for module in modules_by_type[module_type]]) for module_type in MODULE_TYPES
+    ),
+    "configs": [m.name for m in all_modules_ordered_by_type if m.configs],
+    "module_types": MODULE_TYPES,
+    "empty_config": config_string,
 }
 
 current_file_dir = os.path.dirname(os.path.abspath(__file__))
-output_file = os.path.join(current_file_dir, 'settings/src/schema.json')
-with open(output_file, 'w') as file:
-    json.dump(output_schema, file, indent=4, cls=SchemaEncoder)
+output_file = os.path.join(current_file_dir, "settings/src/schema.json")
+with open(output_file, "w") as file:
+    print(f"Writing schema to {output_file}")
+    json.dump(output_schema, file, indent=4, cls=SchemaEncoder)

scripts/instagrapi_server/.gitignore

@@ -0,0 +1,2 @@
+secrets*
+*instagrapi_session.json

scripts/instagrapi_server/Dockerfile

@@ -0,0 +1,19 @@
+FROM python:3.12-slim
+WORKDIR /app
+
+# Install Poetry
+RUN pip install --upgrade pip
+RUN pip install poetry
+
+# Copy all source code
+COPY . .
+
+# Prevent Poetry from creating a virtual environment
+RUN poetry config virtualenvs.create false
+
+# Install dependencies
+RUN poetry install --no-root
+
+
+# Use uvicorn to run the FastAPI app
+CMD ["poetry", "run", "uvicorn", "src.instaserver:app", "--host", "0.0.0.0", "--port", "8000"]

scripts/instagrapi_server/pyproject.toml

@@ -0,0 +1,18 @@
+[project]
+name = "instaserver"
+version = "0.1.0"
+description = "A FastAPI InstagrAPI server"
+package-mode = false
+requires-python = ">=3.10"
+dependencies = [
+    "fastapi (>=0.115.12,<0.116.0)",
+    "instagrapi (>=2.1.3,<3.0.0)",
+    "uvicorn (>=0.34.0,<0.35.0)",
+    "pillow (>=11.1.0,<12.0.0)",
+    "python-dotenv (>=1.1.0,<2.0.0)"
+]
+
+
+[build-system]
+requires = ["poetry-core>=2.0.0,<3.0.0"]
+build-backend = "poetry.core.masonry.api"

scripts/instagrapi_server/run_instagrapi_server.sh

@@ -0,0 +1,48 @@
+#!/usr/bin/env bash
+#
+# run_instagrapi_server.sh
+# Usage:
+#   From repo root:   ./scripts/instagrapi_server/run_instagrapi_server.sh
+#   Or from script dir: ./run_instagrapi_server.sh
+#
+
+set -e
+
+# Step 1: cd to the script's directory (contains Dockerfile and secrets/)
+cd "$(dirname "$0")" || exit 1
+
+# Create secrets/ if it doesn't exist
+if [[ ! -d "secrets" ]]; then
+  echo "Creating secrets/ directory..."
+  mkdir secrets
+fi
+
+echo "Enter your Instagram credentials to store in secrets/.env"
+read -rp "Instagram Username: " IGUSER
+read -rsp "Instagram Password: " IGPASS
+echo ""
+
+cat <<EOF > secrets/.env
+INSTAGRAM_USERNAME=$IGUSER
+INSTAGRAM_PASSWORD=$IGPASS
+EOF
+echo "Created secrets/.env with your credentials."
+
+# Build Docker image
+IMAGE_NAME="instagrapi-server"
+echo "Building Docker image '$IMAGE_NAME'..."
+docker build -t "$IMAGE_NAME" .
+
+# Run container
+CONTAINER_NAME="ig-instasrv"
+echo "Running container '$CONTAINER_NAME'..."
+docker run -d \
+  --env-file secrets/.env \
+  -v "$(pwd)/secrets:/app/secrets" \
+  -p 8000:8000 \
+  --name "$CONTAINER_NAME" \
+  "$IMAGE_NAME"
+
+echo "Done! Instagrapi server is running on port 8000."
+echo "Use 'docker logs $CONTAINER_NAME' to view logs."
+echo "Use 'docker stop $CONTAINER_NAME' and 'docker rm $CONTAINER_NAME' to stop/remove the container."

scripts/instagrapi_server/src/instaserver.py

@@ -0,0 +1,157 @@
+"""https://subzeroid.github.io/instagrapi/
+
+Run using the following command:
+ uvicorn src.instgrapinstance.instaserver:app --host 0.0.0.0 --port 8000 --reload
+"""
+
+import logging
+import os
+import sys
+from dotenv import load_dotenv
+
+from fastapi import FastAPI, HTTPException
+from instagrapi import Client
+from instagrapi.exceptions import LoginRequired, BadCredentials
+
+load_dotenv(dotenv_path="secrets/.env")
+logging.basicConfig(level=logging.INFO, format="%(asctime)s [%(levelname)s] %(message)s")
+
+INSTAGRAM_USERNAME = os.getenv("INSTAGRAM_USERNAME")
+INSTAGRAM_PASSWORD = os.getenv("INSTAGRAM_PASSWORD")
+SESSION_FILE = "secrets/instagrapi_session.json"
+
+app = FastAPI()
+cl = Client()
+
+
+@app.on_event("startup")
+def startup_event():
+    """Login automatically when server starts"""
+    try:
+        login_instagram()
+    except RuntimeError as e:
+        logging.error(f"API failed to start: {e}")
+        sys.exit(1)
+
+
+def login_instagram():
+    """Ensures Instagrapi is logged in and session is persistent"""
+    if not INSTAGRAM_USERNAME or not INSTAGRAM_PASSWORD:
+        raise RuntimeError("Instagram credentials are missing.")
+
+    if os.path.exists(SESSION_FILE):
+        try:
+            cl.load_settings(SESSION_FILE)
+            cl.get_timeline_feed()
+            logging.info("Using saved session.")
+            return
+        except LoginRequired:
+            logging.info("Session expired. Logging in again...")
+
+    try:
+        cl.login(INSTAGRAM_USERNAME, INSTAGRAM_PASSWORD)
+        cl.dump_settings(SESSION_FILE)
+        logging.info("Login successful, session saved.")
+    except BadCredentials as bc:
+        raise RuntimeError("Incorrect Instagram username or password.") from bc
+    except Exception as e:
+        raise RuntimeError(f"Login failed: {e}") from e
+
+
+@app.get("/v1/media/by/id")
+def get_media_by_id(id: str):
+    """Fetch post details by media ID"""
+    logging.info(f"Fetching media by ID: {id}")
+    try:
+        media = cl.media_info(id)
+        return media.model_dump()
+    except Exception as e:
+        logging.warning(f"Media not found for ID {id}: {e}")
+        raise HTTPException(status_code=404, detail="Post not found") from e
+
+
+@app.get("/v1/media/by/code")
+def get_media_by_code(code: str):
+    """Fetch post details by shortcode"""
+    logging.info(f"Fetching media by shortcode: {code}")
+    try:
+        media_id = cl.media_pk_from_code(code)
+        media = cl.media_info(media_id)
+        return media.model_dump()
+    except Exception as e:
+        logging.warning(f"Media not found for code {code}: {e}")
+        raise HTTPException(status_code=404, detail="Post not found") from e
+
+
+@app.get("/v2/user/tag/medias")
+def get_user_tagged_medias(user_id: str, page_id: str = None):
+    logging.info(f"Fetching tagged medias for user_id={user_id} page_id={page_id}")
+    try:
+        # Placeholder for now
+        items, next_page_id = [], None
+        return {"response": {"items": items}, "next_page_id": next_page_id}
+    except Exception as e:
+        logging.warning(f"Tagged media not found for {user_id}: {e}")
+        raise HTTPException(status_code=404, detail="Tagged media not found") from e
+
+
+@app.get("/v1/user/highlights")
+def get_user_highlights(user_id: str):
+    logging.info(f"Fetching highlights list for user_id={user_id}")
+    try:
+        highlights = cl.user_highlights(user_id)
+        return [h.model_dump() for h in highlights]
+    except Exception as e:
+        logging.warning(f"Highlights not found for {user_id}: {e}")
+        raise HTTPException(status_code=404, detail="No highlights found") from e
+
+
+@app.get("/v2/highlight/by/id")
+def get_highlight_by_id(id: str):
+    logging.info(f"Fetching highlight details for id={id}")
+    try:
+        highlight = cl.highlight_info(id)
+        return {"response": {"reels": {f"highlight:{id}": highlight.model_dump()}}}
+    except Exception as e:
+        logging.warning(f"Highlight not found for id {id}: {e}")
+        raise HTTPException(status_code=404, detail="Highlight not found") from e
+
+
+@app.get("/v1/user/stories/by/username")
+def get_stories(username: str):
+    logging.info(f"Fetching stories for username={username}")
+    try:
+        user_id = cl.user_id_from_username(username)
+        stories = cl.user_stories(user_id)
+        return [story.model_dump() for story in stories]
+    except Exception as e:
+        logging.warning(f"Stories not found for {username}: {e}")
+        raise HTTPException(status_code=404, detail="Stories not found") from e
+
+
+@app.get("/v2/user/by/username")
+def get_user_by_username(username: str):
+    logging.info(f"Fetching user profile for username={username}")
+    try:
+        user = cl.user_info_by_username(username)
+        return {"user": user.model_dump()}
+    except Exception as e:
+        logging.warning(f"User not found: {username}: {e}")
+        raise HTTPException(status_code=404, detail="User not found") from e
+
+
+@app.get("/v1/user/medias/chunk")
+def get_user_medias(user_id: str, end_cursor: str = None):
+    logging.info(f"Fetching paginated medias for user_id={user_id}, end_cursor={end_cursor}")
+    try:
+        posts, next_cursor = cl.user_medias_paginated(user_id, end_cursor=end_cursor)
+        return [[post.model_dump() for post in posts], next_cursor]
+    except Exception as e:
+        logging.warning(f"No posts found for user_id={user_id}: {e}")
+        raise HTTPException(status_code=404, detail="No posts found") from e
+
+
+if __name__ == "__main__":
+    import uvicorn
+
+    uvicorn.run(app, host="0.0.0.0", port=8000)

scripts/settings/package.json

@@ -13,7 +13,7 @@
     "@dnd-kit/sortable": "^10.0.0",
     "@emotion/react": "latest",
     "@emotion/styled": "latest",
-    "@mui/icons-material": "latest",
+    "@mui/icons-material": "^6.4.7",
     "@mui/material": "latest",
     "react": "19.0.0",
     "react-dom": "19.0.0",

scripts/settings/src/App.tsx

@@ -4,7 +4,7 @@ import Container from '@mui/material/Container';
 import Typography from '@mui/material/Typography';
 import Box from '@mui/material/Box';
 import FileUploadIcon from '@mui/icons-material/FileUpload';
-// 
+
 import {
   DndContext,
   closestCenter,
@@ -204,7 +204,7 @@ function ModuleTypes({ stepType, setEnabledModules, enabledModules, configValues
           {stepType}
         </Typography>
         <Typography variant="body1" >
-          Select the <a href="<a href={`https://auto-archiver.readthedocs.io/en/latest/modules/${stepType.slice(0,-1)}.html`}" target="_blank">{stepType}</a> you wish to enable. Drag to reorder.
+          Select the <a href={`https://auto-archiver.readthedocs.io/en/latest/modules/${stepType.slice(0,-1)}.html`} target="_blank">{stepType}</a> you wish to enable. Drag to reorder.
         </Typography>
       </Box>
       {showError ? <Typography variant="body1" color="error" >Only one {stepType.slice(0,-1)} can be enabled at a time.</Typography> : null}

scripts/settings/vite.config.ts

@@ -6,7 +6,7 @@ import { viteSingleFile } from "vite-plugin-singlefile"
 export default defineConfig({
   plugins: [react(), viteSingleFile()],
   build: {
-    minify: false,
-    sourcemap: true,
+    // minify: false,
+    // sourcemap: true,
   }
 });

scripts/telegram_setup.py

@@ -12,7 +12,6 @@ Then run this script to create a new session file.
 You will need to provide your phone number and a 2FA code the first time you run this script.
 """
 
-
 import os
 from telethon.sync import TelegramClient
 from loguru import logger
@@ -26,4 +25,3 @@ SESSION_FILE = "secrets/anon-insta"
 os.makedirs("secrets", exist_ok=True)
 with TelegramClient(SESSION_FILE, API_ID, API_HASH) as client:
     logger.success(f"New session file created: {SESSION_FILE}.session")
-

src/auto_archiver/__main__.py

@@ -1,9 +1,13 @@
-""" Entry point for the auto_archiver package. """
+"""Entry point for the auto_archiver package."""
+
 from auto_archiver.core.orchestrator import ArchivingOrchestrator
 import sys
 
+
 def main():
-    for _ in ArchivingOrchestrator()._command_line_run(sys.argv[1:]): pass
+    for _ in ArchivingOrchestrator()._command_line_run(sys.argv[1:]):
+        pass
+
 
 if __name__ == "__main__":
     main()

src/auto_archiver/core/__init__.py

@@ -1,6 +1,5 @@
-""" Core modules to handle things such as orchestration, metadata and configs..
+"""Core modules to handle things such as orchestration, metadata and configs.."""
 
-"""
 from .metadata import Metadata
 from .media import Media
 from .base_module import BaseModule
@@ -14,4 +13,4 @@ from .enricher import Enricher
 from .feeder import Feeder
 from .storage import Storage
 from .extractor import Extractor
-from .formatter import Formatter
+from .formatter import Formatter

src/auto_archiver/core/base_module.py

@@ -1,9 +1,8 @@
-
 from __future__ import annotations
 
-from typing import  Mapping, Any, Type, TYPE_CHECKING
+from typing import Mapping, Any, TYPE_CHECKING
 from abc import ABC
-from copy import deepcopy, copy
+from copy import deepcopy
 from tempfile import TemporaryDirectory
 from auto_archiver.utils import url as UrlUtil
 from auto_archiver.core.consts import MODULE_TYPES as CONF_MODULE_TYPES
@@ -13,8 +12,8 @@ from loguru import logger
 if TYPE_CHECKING:
     from .module import ModuleFactory
 
-class BaseModule(ABC):
 
+class BaseModule(ABC):
     """
     Base module class. All modules should inherit from this class.
 
@@ -46,14 +45,13 @@ class BaseModule(ABC):
 
     @property
     def storages(self) -> list:
-        return self.config.get('storages', [])
+        return self.config.get("storages", [])
 
     def config_setup(self, config: dict):
-
         # this is important. Each instance is given its own deepcopied config, so modules cannot
         # change values to affect other modules
         config = deepcopy(config)
-        authentication = deepcopy(config.pop('authentication', {}))
+        authentication = deepcopy(config.pop("authentication", {}))
 
         self.authentication = authentication
         self.config = config
@@ -61,18 +59,28 @@ class BaseModule(ABC):
             setattr(self, key, val)
 
     def setup(self):
-        # For any additional setup required by modules, e.g. autehntication
+        # For any additional setup required by modules outside of the configs in the manifesst,
+        # e.g. authentication
         pass
 
     def auth_for_site(self, site: str, extract_cookies=True) -> Mapping[str, Any]:
         """
         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'
-        
+
         :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).
 
-        :returns: authdict dict of login information for the given site
+        :returns: authdict dict -> {
+            "username": str,
+            "password": str,
+            "api_key": str,
+            "api_secret": str,
+            "cookie": str,
+            "cookies_file": str,
+            "cookies_from_browser": str,
+            "cookies_jar": CookieJar
+        }
 
         **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
@@ -86,15 +94,15 @@ class BaseModule(ABC):
         * cookie: str - a cookie string to use for login (specific to this site)\n
         * cookies_file: str - the path to a cookies file to use for login (specific to this site)\n
         * cookies_from_browser: str - the name of the browser to extract cookies from (specitic for 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?
 
-        site = UrlUtil.domain_for_url(site).lstrip("www.")
+        site = UrlUtil.domain_for_url(site).removeprefix("www.")
         # add the 'www' version of the site to the list of sites to check
         authdict = {}
 
-
         for to_try in [site, f"www.{site}"]:
             if to_try in self.authentication:
                 authdict.update(self.authentication[to_try])
@@ -104,17 +112,20 @@ class BaseModule(ABC):
         if not authdict:
             for key in self.authentication.keys():
                 if key in site or site in key:
-                    logger.debug(f"Could not find exact authentication information for site '{site}'. \
+                    logger.debug(
+                        f"Could not find exact authentication information for site '{site}'. \
 did find information for '{key}' which is close, is this what you meant? \
-If so, edit your authentication settings to make sure it exactly matches.")
+If so, edit your authentication settings to make sure it exactly matches."
+                    )
 
         def get_ytdlp_cookiejar(args):
             import yt_dlp
             from yt_dlp import parse_options
+
             logger.debug(f"Extracting cookies from settings: {args[1]}")
             # parse_options returns a named tuple as follows, we only need the ydl_options part
             # collections.namedtuple('ParsedOptions', ('parser', 'options', 'urls', 'ydl_opts'))
-            ytdlp_opts = getattr(parse_options(args), 'ydl_opts')
+            ytdlp_opts = getattr(parse_options(args), "ydl_opts")
             return yt_dlp.YoutubeDL(ytdlp_opts).cookiejar
 
         get_cookiejar_options = None
@@ -125,22 +136,21 @@ If so, edit your authentication settings to make sure it exactly matches.")
         # 3. cookies_from_browser setting in global config
         # 4. cookies_file setting in global config
 
-        if 'cookies_from_browser' in authdict:
-            get_cookiejar_options = ['--cookies-from-browser', authdict['cookies_from_browser']]
-        elif 'cookies_file' in authdict:
-            get_cookiejar_options = ['--cookies', authdict['cookies_file']]
-        elif 'cookies_from_browser' in self.authentication:
-            authdict['cookies_from_browser'] = self.authentication['cookies_from_browser']
-            get_cookiejar_options = ['--cookies-from-browser', self.authentication['cookies_from_browser']]
-        elif 'cookies_file' in self.authentication:
-            authdict['cookies_file'] = self.authentication['cookies_file']
-            get_cookiejar_options = ['--cookies', self.authentication['cookies_file']]
+        if "cookies_from_browser" in authdict:
+            get_cookiejar_options = ["--cookies-from-browser", authdict["cookies_from_browser"]]
+        elif "cookies_file" in authdict:
+            get_cookiejar_options = ["--cookies", authdict["cookies_file"]]
+        elif "cookies_from_browser" in self.authentication:
+            authdict["cookies_from_browser"] = self.authentication["cookies_from_browser"]
+            get_cookiejar_options = ["--cookies-from-browser", self.authentication["cookies_from_browser"]]
+        elif "cookies_file" in self.authentication:
+            authdict["cookies_file"] = self.authentication["cookies_file"]
+            get_cookiejar_options = ["--cookies", self.authentication["cookies_file"]]
 
-        
         if get_cookiejar_options:
-            authdict['cookies_jar'] = get_ytdlp_cookiejar(get_cookiejar_options)
+            authdict["cookies_jar"] = get_ytdlp_cookiejar(get_cookiejar_options)
 
         return authdict
-    
+
     def repr(self):
-        return f"Module<'{self.display_name}' (config: {self.config[self.name]})>"
+        return f"Module<'{self.display_name}' (config: {self.config[self.name]})>"

src/auto_archiver/core/config.py

@@ -6,26 +6,28 @@ flexible setup in various environments.
 """
 
 import argparse
-from ruamel.yaml import YAML, CommentedMap, add_representer
+from ruamel.yaml import YAML, CommentedMap
 import json
+import os
 
 from loguru import logger
 
 from copy import deepcopy
 from auto_archiver.core.consts import MODULE_TYPES
 
-from typing import Any, List, Type, Tuple
 
 _yaml: YAML = YAML()
 
 DEFAULT_CONFIG_FILE = "secrets/orchestration.yaml"
 
-EMPTY_CONFIG = _yaml.load("""
+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 MODULE_TYPES]) + \
-"""
+steps:"""
+    + "".join([f"\n   {module}s: []" for module in MODULE_TYPES])
+    + """
 
 # Global configuration
 
@@ -52,50 +54,54 @@ authentication: {}
 logging:
   level: INFO
 
-""")
+"""
+)
 # note: 'logging' is explicitly added above in order to better format the config file
 
 
 # Arg Parse Actions/Classes
 class AuthenticationJsonParseAction(argparse.Action):
     def __call__(self, parser, namespace, values, option_string=None):
-
         try:
             auth_dict = json.loads(values)
             setattr(namespace, self.dest, auth_dict)
         except json.JSONDecodeError as e:
-            raise argparse.ArgumentTypeError(f"Invalid JSON input for argument '{self.dest}': {e}")
+            raise argparse.ArgumentTypeError(f"Invalid JSON input for argument '{self.dest}': {e}") from e
 
         def load_from_file(path):
             try:
-                with open(path, '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
+                    if auth_dict.get("authentication"):
+                        auth_dict = auth_dict["authentication"]
+                    auth_dict["load_from_file"] = path
                     return auth_dict
-            except:
+            except Exception:
                 return None
 
-        if isinstance(auth_dict, dict) and auth_dict.get('from_file'):
-            auth_dict = load_from_file(auth_dict['from_file'])
+        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")
-        global_options = ['cookies_from_browser', 'cookies_file', 'load_from_file']
+            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}")
+                raise argparse.ArgumentTypeError(
+                    f"Authentication must be a dictionary of site names and their authentication methods. Valid global configs are {global_options}"
+                )
 
         setattr(namespace, self.dest, auth_dict)
 
@@ -106,8 +112,8 @@ class UniqueAppendAction(argparse.Action):
             if value not in getattr(namespace, self.dest):
                 getattr(namespace, self.dest).append(value)
 
-class DefaultValidatingParser(argparse.ArgumentParser):
 
+class DefaultValidatingParser(argparse.ArgumentParser):
     def error(self, message):
         """
         Override of error to format a nicer looking error message using logger
@@ -136,8 +142,10 @@ class DefaultValidatingParser(argparse.ArgumentParser):
 
         return super().parse_known_args(args, namespace)
 
+
 # Config Utils
 
+
 def to_dot_notation(yaml_conf: CommentedMap | dict) -> dict:
     dotdict = {}
 
@@ -151,6 +159,7 @@ def to_dot_notation(yaml_conf: CommentedMap | dict) -> dict:
     process_subdict(yaml_conf)
     return dotdict
 
+
 def from_dot_notation(dotdict: dict) -> dict:
     normal_dict = {}
 
@@ -171,9 +180,11 @@ def from_dot_notation(dotdict: dict) -> dict:
 def is_list_type(value):
     return isinstance(value, list) or isinstance(value, tuple) or isinstance(value, set)
 
+
 def is_dict_type(value):
     return isinstance(value, dict) or isinstance(value, CommentedMap)
 
+
 def merge_dicts(dotdict: dict, yaml_dict: CommentedMap) -> CommentedMap:
     yaml_dict: CommentedMap = deepcopy(yaml_dict)
 
@@ -184,7 +195,7 @@ def merge_dicts(dotdict: dict, yaml_dict: CommentedMap) -> CommentedMap:
                 yaml_subdict[key] = value
                 continue
 
-            if key == 'steps':
+            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
@@ -199,6 +210,7 @@ def merge_dicts(dotdict: dict, yaml_dict: CommentedMap) -> CommentedMap:
     update_dict(from_dot_notation(dotdict), yaml_dict)
     return yaml_dict
 
+
 def read_yaml(yaml_filename: str) -> CommentedMap:
     config = None
     try:
@@ -212,20 +224,26 @@ def read_yaml(yaml_filename: str) -> CommentedMap:
 
     return config
 
+
 # TODO: make this tidier/find a way to notify of which keys should not be stored
 
 
 def store_yaml(config: CommentedMap, yaml_filename: str) -> None:
     config_to_save = deepcopy(config)
 
+    ## if the save path is the default location (secrets) then create the 'secrets' folder
+    if os.path.dirname(yaml_filename) == "secrets":
+        os.makedirs("secrets", exist_ok=True)
+
     auth_dict = config_to_save.get("authentication", {})
-    if auth_dict and auth_dict.get('load_from_file'):
+    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)
+    config_to_save.pop("urls", None)
     with open(yaml_filename, "w", encoding="utf-8") as outf:
         _yaml.dump(config_to_save, outf)
 
+
 def is_valid_config(config: CommentedMap) -> bool:
-    return config and config != EMPTY_CONFIG
+    return config and config != EMPTY_CONFIG

src/auto_archiver/core/consts.py

@@ -1,23 +1,19 @@
+class SetupError(ValueError):
+    pass
 
-MODULE_TYPES = [
-    'feeder',
-    'extractor',
-    'enricher',
-    'database',
-    'storage',
-    'formatter'
-]
+
+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 software
-    '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
-}
+    "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 software
+    "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
+}

src/auto_archiver/core/database.py

@@ -1,6 +1,6 @@
 """
 Database module for the auto-archiver that defines the interface for implementing database modules
-in the media archiving framework. 
+in the media archiving framework.
 """
 
 from __future__ import annotations
@@ -9,6 +9,7 @@ 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.
@@ -20,7 +21,7 @@ class Database(BaseModule):
         """signals the DB that the given item archival has started"""
         pass
 
-    def failed(self, item: Metadata, reason:str) -> None:
+    def failed(self, item: Metadata, reason: str) -> None:
         """update DB accordingly for failure"""
         pass
 
@@ -34,6 +35,6 @@ class Database(BaseModule):
         return False
 
     @abstractmethod
-    def done(self, item: Metadata, cached: bool=False) -> None:
+    def done(self, item: Metadata, cached: bool = False) -> None:
         """archival result ready - should be saved to DB"""
         pass

src/auto_archiver/core/enricher.py

@@ -8,13 +8,15 @@ the archiving step and before storage or formatting.
 
 Enrichers are optional but highly useful for making the archived data more powerful.
 """
+
 from __future__ import annotations
 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.
-    
+
     Enricher modules must implement the `enrich` method to define their behavior.
     """
 

src/auto_archiver/core/extractor.py

@@ -1,17 +1,15 @@
-""" The `extractor` module defines the base functionality for implementing extractors in the media archiving framework.
-    This class provides common utility methods and a standard interface for extractors.
+"""The `extractor` module defines the base functionality for implementing extractors in the media archiving framework.
+This class provides common utility methods and a standard interface for extractors.
 
-    Factory method to initialize an extractor instance based on its name.
+Factory method to initialize an extractor instance based on its name.
 
 
 """
+
 from __future__ import annotations
-from pathlib import Path
 from abc import abstractmethod
-from dataclasses import dataclass
 import mimetypes
 import os
-import mimetypes
 import requests
 from loguru import logger
 from retrying import retry
@@ -39,7 +37,7 @@ class Extractor(BaseModule):
         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.
@@ -58,7 +56,7 @@ class Extractor(BaseModule):
         """
         if self.valid_url:
             return self.match_link(url) is not None
-        
+
         return True
 
     def _guess_file_type(self, path: str) -> str:
@@ -74,16 +72,17 @@ class Extractor(BaseModule):
     @retry(wait_random_min=500, wait_random_max=3500, stop_max_attempt_number=5)
     def download_from_url(self, url: str, to_filename: str = None, verbose=True) -> str:
         """
-            downloads a URL to provided filename, or inferred from URL, returns local filename
+        downloads a URL to provided filename, or inferred from URL, returns local filename
         """
         if not to_filename:
-            to_filename = url.split('/')[-1].split('?')[0]
+            to_filename = url.split("/")[-1].split("?")[0]
             if len(to_filename) > 64:
                 to_filename = to_filename[-64:]
         to_filename = os.path.join(self.tmp_dir, to_filename)
-        if verbose: logger.debug(f"downloading {url[0:50]=} {to_filename=}")
+        if verbose:
+            logger.debug(f"downloading {url[0:50]=} {to_filename=}")
         headers = {
-            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36'
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36"
         }
         try:
             d = requests.get(url, stream=True, headers=headers, timeout=30)
@@ -91,12 +90,12 @@ class Extractor(BaseModule):
 
             # get mimetype from the response headers
             if not mimetypes.guess_type(to_filename)[0]:
-                content_type = d.headers.get('Content-Type') or self._guess_file_type(url)
+                content_type = d.headers.get("Content-Type") or self._guess_file_type(url)
                 extension = mimetypes.guess_extension(content_type)
                 if extension:
                     to_filename += extension
 
-            with open(to_filename, 'wb') as f:
+            with open(to_filename, "wb") as f:
                 for chunk in d.iter_content(chunk_size=8192):
                     f.write(chunk)
             return to_filename
@@ -108,8 +107,8 @@ class Extractor(BaseModule):
     def download(self, item: Metadata) -> Metadata | False:
         """
         Downloads the media from the given URL and returns a Metadata object with the downloaded media.
-        
+
         If the URL is not supported or the download fails, this method should return False.
 
         """
-        pass
+        pass

src/auto_archiver/core/feeder.py

@@ -1,5 +1,5 @@
 """
-The feeder base module defines the interface for implementing feeders in the media archiving framework. 
+The feeder base module defines the interface for implementing feeders in the media archiving framework.
 """
 
 from __future__ import annotations
@@ -7,8 +7,8 @@ from abc import abstractmethod
 from auto_archiver.core import Metadata
 from auto_archiver.core import BaseModule
 
-class Feeder(BaseModule):
 
+class Feeder(BaseModule):
     """
     Base class for implementing feeders in the media archiving framework.
 
@@ -19,7 +19,7 @@ class Feeder(BaseModule):
     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
+        return None

src/auto_archiver/core/formatter.py

@@ -12,7 +12,7 @@ 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.
     """
 
@@ -21,4 +21,4 @@ class Formatter(BaseModule):
         """
         Formats a Metadata object into a user-viewable format (e.g. HTML) and stores it if needed.
         """
-        return None
+        return None

src/auto_archiver/core/media.py

@@ -6,7 +6,7 @@ nested media retrieval, and type validation.
 from __future__ import annotations
 import os
 import traceback
-from typing import Any, List
+from typing import Any, List, Iterator
 from dataclasses import dataclass, field
 from dataclasses_json import dataclass_json, config
 import mimetypes
@@ -21,14 +21,14 @@ class Media:
     Represents a media file with associated properties and storage details.
 
     Attributes:
-    - filename: The file path of the media.
-    - key: An optional identifier for the media.
+    - filename: The file path of the media as saved locally (temporarily, before uploading to the storage).
     - urls: A list of URLs where the media is stored or accessible.
     - properties: Additional metadata or transformations for the media.
     - _mimetype: The media's mimetype (e.g., image/jpeg, video/mp4).
     """
+
     filename: str
-    key: str = None
+    _key: str = None
     urls: List[str] = field(default_factory=list)
     properties: dict = field(default_factory=dict)
     _mimetype: str = None  # eg: image/jpeg
@@ -47,19 +47,20 @@ class Media:
             for any_media in self.all_inner_media(include_self=True):
                 s.store(any_media, url, metadata=metadata)
 
-    def all_inner_media(self, include_self=False):
+    def all_inner_media(self, include_self=False) -> Iterator[Media]:
         """Retrieves all media, including nested media within properties or transformations on original media.
         This function returns a generator for all the inner media.
 
         """
-        if include_self: yield self
+        if include_self:
+            yield self
         for prop in self.properties.values():
-            if isinstance(prop, Media): 
+            if isinstance(prop, Media):
                 for inner_media in prop.all_inner_media(include_self=True):
                     yield inner_media
             if isinstance(prop, list):
                 for prop_media in prop:
-                    if isinstance(prop_media, Media): 
+                    if isinstance(prop_media, Media):
                         for inner_media in prop_media.all_inner_media(include_self=True):
                             yield inner_media
 
@@ -67,6 +68,10 @@ class Media:
         # checks if the media is already stored in the given storage
         return len(self.urls) > 0 and len(self.urls) == len(in_storage.config["steps"]["storages"])
 
+    @property
+    def key(self) -> str:
+        return self._key
+
     def set(self, key: str, value: Any) -> Media:
         self.properties[key] = value
         return self
@@ -110,15 +115,17 @@ class Media:
         # checks for video streams with ffmpeg, or min file size for a video
         # self.is_video() should be used together with this method
         try:
-            streams = ffmpeg.probe(self.filename, select_streams='v')['streams']
+            streams = ffmpeg.probe(self.filename, select_streams="v")["streams"]
             logger.warning(f"STREAMS FOR {self.filename} {streams}")
             return any(s.get("duration_ts", 0) > 0 for s in streams)
-        except Error: return False # ffmpeg errors when reading bad files
+        except Error:
+            return False  # ffmpeg errors when reading bad files
         except Exception as e:
             logger.error(e)
             logger.error(traceback.format_exc())
             try:
                 fsize = os.path.getsize(self.filename)
                 return fsize > 20_000
-            except: pass
+            except Exception as e:
+                pass
         return True

src/auto_archiver/core/metadata.py

@@ -13,7 +13,7 @@ from __future__ import annotations
 import hashlib
 from typing import Any, List, Union, Dict
 from dataclasses import dataclass, field
-from dataclasses_json import dataclass_json, config
+from dataclasses_json import dataclass_json
 import datetime
 from urllib.parse import urlparse
 from dateutil.parser import parse as parse_dt
@@ -21,6 +21,7 @@ from loguru import logger
 
 from .media import Media
 
+
 @dataclass_json  # annotation order matters
 @dataclass
 class Metadata:
@@ -40,19 +41,23 @@ class Metadata:
         - If `True`, this instance's values are overwritten by `right`.
         - If `False`, the inverse applies.
         """
-        if not right: return self
+        if not right:
+            return self
         if overwrite_left:
             if right.status and len(right.status):
                 self.status = right.status
             self._context.update(right._context)
             for k, v in right.metadata.items():
-                assert k not in self.metadata or type(v) == type(self.get(k))
-                if type(v) not in [dict, list, set] or k not in self.metadata:
+                assert k not in self.metadata or type(v) is type(self.get(k))
+                if not isinstance(v, (dict, list, set)) or k not in self.metadata:
                     self.set(k, v)
                 else:  # key conflict
-                    if type(v) in [dict, set]: self.set(k, self.get(k) | v)
-                    elif type(v) == list: self.set(k, self.get(k) + v)
+                    if isinstance(v, (dict, set)):
+                        self.set(k, self.get(k) | v)
+                    elif type(v) is list:
+                        self.set(k, self.get(k) + v)
             self.media.extend(right.media)
+
         else:  # invert and do same logic
             return right.merge(self)
         return self
@@ -69,7 +74,7 @@ class Metadata:
 
     def append(self, key: str, val: Any) -> Metadata:
         if key not in self.metadata:
-            self.metadata[key] = []    
+            self.metadata[key] = []
         self.metadata[key] = val
         return self
 
@@ -80,24 +85,26 @@ class Metadata:
         return self.metadata.get(key, default)
 
     def success(self, context: str = None) -> Metadata:
-        if context: self.status = f"{context}: success"
-        else: self.status = "success"
+        if context:
+            self.status = f"{context}: success"
+        else:
+            self.status = "success"
         return self
 
     def is_success(self) -> bool:
         return "success" in self.status
 
     def is_empty(self) -> bool:
-        meaningfull_ids = set(self.metadata.keys()) - set(["_processed_at", "url", "total_bytes", "total_size", "archive_duration_seconds"])
+        meaningfull_ids = set(self.metadata.keys()) - set(
+            ["_processed_at", "url", "total_bytes", "total_size", "archive_duration_seconds"]
+        )
         return not self.is_success() and len(self.media) == 0 and len(meaningfull_ids) == 0
 
     @property  # getter .netloc
     def netloc(self) -> str:
         return urlparse(self.get_url()).netloc
 
-
-# custom getter/setters
-
+    # custom getter/setters
 
     def set_url(self, url: str) -> Metadata:
         assert type(url) is str and len(url) > 0, "invalid URL"
@@ -120,36 +127,43 @@ class Metadata:
         return self.get("title")
 
     def set_timestamp(self, timestamp: datetime.datetime) -> Metadata:
-        if type(timestamp) == str:
+        if isinstance(timestamp, str):
             timestamp = parse_dt(timestamp)
-        assert type(timestamp) == datetime.datetime, "set_timestamp expects a datetime instance"
+        assert isinstance(timestamp, datetime.datetime), "set_timestamp expects a datetime instance"
         return self.set("timestamp", timestamp)
 
-    def get_timestamp(self, utc=True, iso=True) -> datetime.datetime:
+    def get_timestamp(self, utc=True, iso=True) -> datetime.datetime | str | None:
         ts = self.get("timestamp")
-        if not ts: return 
+        if not ts:
+            return None
         try:
-            if type(ts) == str: ts = datetime.datetime.fromisoformat(ts)
-            if type(ts) == float: ts = datetime.datetime.fromtimestamp(ts)
-            if utc: ts = ts.replace(tzinfo=datetime.timezone.utc)
-            if iso: return ts.isoformat()
-            return ts
+            if isinstance(ts, str):
+                ts = datetime.datetime.fromisoformat(ts)
+            elif isinstance(ts, float):
+                ts = datetime.datetime.fromtimestamp(ts)
+            if utc:
+                ts = ts.replace(tzinfo=datetime.timezone.utc)
+            return ts.isoformat() if iso else ts
         except Exception as e:
             logger.error(f"Unable to parse timestamp {ts}: {e}")
-            return
+            return None
 
     def add_media(self, media: Media, id: str = None) -> Metadata:
         # adds a new media, optionally including an id
-        if media is None: return
+        if media is None:
+            return
         if id is not None:
-            assert not len([1 for m in self.media if m.get("id") == id]), f"cannot add 2 pieces of media with the same id {id}"
+            assert not len([1 for m in self.media if m.get("id") == id]), (
+                f"cannot add 2 pieces of media with the same id {id}"
+            )
             media.set("id", id)
         self.media.append(media)
         return media
 
     def get_media_by_id(self, id: str, default=None) -> Media:
         for m in self.media:
-            if m.get("id") == id: return m
+            if m.get("id") == id:
+                return m
         return default
 
     def remove_duplicate_media_by_hash(self) -> None:
@@ -159,7 +173,8 @@ class Metadata:
             with open(filename, "rb") as f:
                 while True:
                     buf = f.read(chunksize)
-                    if not buf: break
+                    if not buf:
+                        break
                     hash_algo.update(buf)
             return hash_algo.hexdigest()
 
@@ -167,15 +182,18 @@ class Metadata:
         new_media = []
         for m in self.media:
             h = m.get("hash")
-            if not h: h = calculate_hash_in_chunks(hashlib.sha256(), int(1.6e7), m.filename)
-            if len(h) and h in media_hashes: continue
+            if not h:
+                h = calculate_hash_in_chunks(hashlib.sha256(), int(1.6e7), m.filename)
+            if len(h) and h in media_hashes:
+                continue
             media_hashes.add(h)
             new_media.append(m)
         self.media = new_media
 
     def get_first_image(self, default=None) -> Media:
         for m in self.media:
-            if "image" in m.mimetype: return m
+            if "image" in m.mimetype:
+                return m
         return default
 
     def set_final_media(self, final: Media) -> Metadata:
@@ -193,22 +211,25 @@ class Metadata:
     def __str__(self) -> str:
         return self.__repr__()
 
-
     @staticmethod
     def choose_most_complete(results: List[Metadata]) -> Metadata:
         # returns the most complete result from a list of results
         # prioritizes results with more media, then more metadata
-        if len(results) == 0: return None
-        if len(results) == 1: return results[0]
+        if len(results) == 0:
+            return None
+        if len(results) == 1:
+            return results[0]
         most_complete = results[0]
         for r in results[1:]:
-            if len(r.media) > len(most_complete.media): most_complete = r
-            elif len(r.media) == len(most_complete.media) and len(r.metadata) > len(most_complete.metadata): most_complete = r
+            if len(r.media) > len(most_complete.media):
+                most_complete = r
+            elif len(r.media) == len(most_complete.media) and len(r.metadata) > len(most_complete.metadata):
+                most_complete = r
         return most_complete
 
     def set_context(self, key: str, val: Any) -> Metadata:
         self._context[key] = val
         return self
-    
+
     def get_context(self, key: str, default: Any = None) -> Any:
-        return self._context.get(key, default)
+        return self._context.get(key, default)

src/auto_archiver/core/module.py

@@ -3,10 +3,12 @@ Defines the Step abstract base class, which acts as a blueprint for steps in the
 by handling user configuration, validating the steps properties, and implementing dynamic instantiation.
 
 """
+
 from __future__ import annotations
+import subprocess
 
 from dataclasses import dataclass
-from typing import List, TYPE_CHECKING
+from typing import List, TYPE_CHECKING, Type
 import shutil
 import ast
 import copy
@@ -16,7 +18,7 @@ import os
 from os.path import join
 from loguru import logger
 import auto_archiver
-from auto_archiver.core.consts import DEFAULT_MANIFEST, MANIFEST_FILE
+from auto_archiver.core.consts import DEFAULT_MANIFEST, MANIFEST_FILE, SetupError
 
 if TYPE_CHECKING:
     from .base_module import BaseModule
@@ -24,17 +26,17 @@ if TYPE_CHECKING:
 
 HAS_SETUP_PATHS = False
 
-class ModuleFactory:
 
+class ModuleFactory:
     def __init__(self):
         self._lazy_modules = {}
 
     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
 
@@ -46,34 +48,36 @@ class ModuleFactory:
 
             # 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. \
+                if HAS_SETUP_PATHS:
+                    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)
+                                       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:
+    def get_module(self, module_name: str, config: dict) -> Type[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]
@@ -81,13 +85,18 @@ class ModuleFactory:
         available = self.available_modules(limit_to_modules=[module_name], suppress_warnings=suppress_warnings)
         if not available:
             message = f"Module '{module_name}' not found. Are you sure it's installed/exists?"
-            if 'archiver' in module_name:
-                message += f" Did you mean {module_name.replace('archiver', 'extractor')}?"
+            if "archiver" in module_name:
+                message += f" Did you mean '{module_name.replace('archiver', 'extractor')}'?"
+            elif "gsheet" in module_name:
+                message += " Did you mean 'gsheet_feeder_db'?"
+            elif "atlos" in module_name:
+                message += " Did you mean 'atlos_feeder_db_storage'?"
             raise IndexError(message)
         return available[0]
 
-    def available_modules(self, limit_to_modules: List[str]= [], suppress_warnings: bool = False) -> List[LazyBaseModule]:
-        
+    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
@@ -119,7 +128,7 @@ class ModuleFactory:
                 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):
@@ -127,15 +136,16 @@ class ModuleFactory:
 
         return all_modules
 
+
 @dataclass
 class LazyBaseModule:
-
     """
     A lazy module class, which only loads the manifest and does not load the module itself.
 
     This is useful for getting information about a module without actually loading it.
 
     """
+
     name: str
     description: str
     path: str
@@ -152,30 +162,30 @@ class LazyBaseModule:
 
     @property
     def type(self):
-        return self.manifest['type']
+        return self.manifest["type"]
 
     @property
     def entry_point(self):
-        if not self._entry_point and not self.manifest['entry_point']:
+        if not self._entry_point and not self.manifest["entry_point"]:
             # try to create the entry point from the module name
             self._entry_point = f"{self.name}::{self.name.replace('_', ' ').title().replace(' ', '')}"
         return self._entry_point
 
     @property
     def dependencies(self) -> dict:
-        return self.manifest['dependencies']
-    
+        return self.manifest["dependencies"]
+
     @property
     def configs(self) -> dict:
-        return self.manifest['configs']
-    
+        return self.manifest["configs"]
+
     @property
     def requires_setup(self) -> bool:
-        return self.manifest['requires_setup']
-    
+        return self.manifest["requires_setup"]
+
     @property
     def display_name(self) -> str:
-        return self.manifest['name']
+        return self.manifest["name"]
 
     @property
     def manifest(self) -> dict:
@@ -189,40 +199,38 @@ class LazyBaseModule:
             try:
                 manifest.update(ast.literal_eval(f.read()))
             except (ValueError, TypeError, SyntaxError, MemoryError, RecursionError) as e:
-                raise ValueError(f"Error loading manifest from file {self.path}/{MANIFEST_FILE}: {e}")
-            
+                raise ValueError(f"Error loading manifest from file {self.path}/{MANIFEST_FILE}: {e}") from e
+
         self._manifest = manifest
-        self._entry_point = manifest['entry_point']
-        self.description = manifest['description']
-        self.version = manifest['version']
+        self._entry_point = manifest["entry_point"]
+        self.description = manifest["description"]
+        self.version = manifest["version"]
 
         return manifest
 
     def load(self, config) -> BaseModule:
-
         if self._instance:
             return self._instance
 
         # check external dependencies are installed
         def check_deps(deps, check):
-            for dep in deps:
-                if not len(dep):
-                    # 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.")
-                    exit(1)
+            for dep in filter(lambda d: len(d.strip()) > 0, deps):
+                if not check(dep.strip()):
+                    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 documentation for more information."
+                    )
+                    raise SetupError()
 
         def check_python_dep(dep):
             # first check if it's a module:
             try:
                 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
+                    # we must now load this module and set it up with the config
                     m.load(config)
                     return True
-                except:
+                except Exception:
                     logger.error(f"Unable to setup module '{dep}' for use in module '{self.name}'")
                     return False
             except IndexError:
@@ -231,13 +239,26 @@ class LazyBaseModule:
 
             return find_spec(dep)
 
-        check_deps(self.dependencies.get('python', []), check_python_dep)
-        check_deps(self.dependencies.get('bin', []), lambda dep: shutil.which(dep))
+        def check_bin_dep(dep):
+            dep_exists = shutil.which(dep)
 
+            if dep == "docker":
+                if os.environ.get("RUNNING_IN_DOCKER"):
+                    # this is only for the WACZ enricher, which requires docker
+                    # if we're already running in docker then we don't need docker
+                    return True
+
+                # check if docker daemon is running
+                return dep_exists and subprocess.run(["docker", "ps", "-q"]).returncode == 0
+
+            return dep_exists
+
+        check_deps(self.dependencies.get("python", []), check_python_dep)
+        check_deps(self.dependencies.get("bin", []), check_bin_dep)
 
         logger.debug(f"Loading module '{self.display_name}'...")
 
-        for qualname in [self.name, f'auto_archiver.modules.{self.name}']:
+        for qualname in [self.name, f"auto_archiver.modules.{self.name}"]:
             try:
                 # first import the whole module, to make sure it's working properly
                 __import__(qualname)
@@ -246,28 +267,29 @@ class LazyBaseModule:
                 pass
 
         # then import the file for the entry point
-        file_name, class_name = self.entry_point.split('::')
-        sub_qualname = f'{qualname}.{file_name}'
+        file_name, class_name = self.entry_point.split("::")
+        sub_qualname = f"{qualname}.{file_name}"
 
-        __import__(f'{qualname}.{file_name}', fromlist=[self.entry_point])
+        __import__(f"{qualname}.{file_name}", fromlist=[self.entry_point])
         # finally, get the class instance
         instance: BaseModule = getattr(sys.modules[sub_qualname], class_name)()
 
+        # save the instance for future easy loading
+        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 'default' in v)
 
-        config[self.name] = default_config  | config.get(self.name, {})
+        # merge the default config with the user config
+        default_config = dict((k, v["default"]) for k, v in self.configs.items() if "default" in v)
+
+        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):
-        return f"Module<'{self.display_name}' ({self.name})>"
+        return f"Module<'{self.display_name}' ({self.name})>"

src/auto_archiver/core/orchestrator.py

@@ -1,10 +1,11 @@
-""" Orchestrates all archiving steps, including feeding items,
-    archiving them with specific archivers, enrichment, storage,
-    formatting, database operations and clean up.
+"""Orchestrates all archiving steps, including feeding items,
+archiving them with specific archivers, enrichment, storage,
+formatting, database operations and clean up.
 
 """
 
 from __future__ import annotations
+from packaging import version
 from typing import Generator, Union, List, Type, TYPE_CHECKING
 import argparse
 import os
@@ -19,21 +20,28 @@ import requests
 
 from .metadata import Metadata, Media
 from auto_archiver.version import __version__
-from .config import read_yaml, store_yaml, to_dot_notation, merge_dicts, is_valid_config, \
-    DefaultValidatingParser, UniqueAppendAction, AuthenticationJsonParseAction, DEFAULT_CONFIG_FILE
+from .config import (
+    read_yaml,
+    store_yaml,
+    to_dot_notation,
+    merge_dicts,
+    is_valid_config,
+    DefaultValidatingParser,
+    UniqueAppendAction,
+    AuthenticationJsonParseAction,
+    DEFAULT_CONFIG_FILE,
+)
 from .module import ModuleFactory, LazyBaseModule
 from . import validators, Feeder, Extractor, Database, Storage, Formatter, Enricher
-from .consts import MODULE_TYPES
+from .consts import MODULE_TYPES, SetupError
 from auto_archiver.utils.url import check_url_or_raise
 
 if TYPE_CHECKING:
     from .base_module import BaseModule
     from .module import LazyBaseModule
 
-class SetupError(ValueError):
-    pass
-class ArchivingOrchestrator:
 
+class ArchivingOrchestrator:
     # instance variables
     module_factory: ModuleFactory
     setup_finished: bool
@@ -63,30 +71,63 @@ class ArchivingOrchestrator:
             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__)
-        parser.add_argument('--config', action='store', dest="config_file", help='the filename of the YAML configuration file (defaults to \'config.yaml\')', default=DEFAULT_CONFIG_FILE)
-        parser.add_argument('--mode', action='store', dest='mode', type=str, choices=['simple', 'full'], help='the mode to run the archiver in', default='simple')
+        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__)
+        parser.add_argument(
+            "--config",
+            action="store",
+            dest="config_file",
+            help="the filename of the YAML configuration file (defaults to 'config.yaml')",
+            default=DEFAULT_CONFIG_FILE,
+        )
+        parser.add_argument(
+            "--mode",
+            action="store",
+            dest="mode",
+            type=str,
+            choices=["simple", "full"],
+            help="the mode to run the archiver in",
+            default="simple",
+        )
         # override the default 'help' so we can inject all the configs and show those
-        parser.add_argument('-s', '--store', dest='store', default=False, help='Store the created config in the config file', action=argparse.BooleanOptionalAction)
-        parser.add_argument('--module_paths', dest='module_paths', nargs='+', default=[], help='additional paths to search for modules', action=UniqueAppendAction)
+        parser.add_argument(
+            "-s",
+            "--store",
+            dest="store",
+            default=False,
+            help="Store the created config in the config file",
+            action=argparse.BooleanOptionalAction,
+        )
+        parser.add_argument(
+            "--module_paths",
+            dest="module_paths",
+            nargs="+",
+            default=[],
+            help="additional paths to search for modules",
+            action=UniqueAppendAction,
+        )
 
         self.basic_parser = parser
         return parser
-    
+
     def check_steps(self, config):
         for module_type in MODULE_TYPES:
-            if not config['steps'].get(f"{module_type}s", []):
-                if module_type == 'feeder' or module_type == 'formatter' and config['steps'].get(f"{module_type}"):
-                    raise SetupError(f"It appears you have '{module_type}' set under 'steps' in your configuration file, but as of version 0.13.0 of Auto Archiver, you must use '{module_type}s'. Change this in your configuration file and try again. \
-Here's how that would look: \n\nsteps:\n  {module_type}s:\n  - [your_{module_type}_name_here]\n  {'extractors:...' if module_type == 'feeder' else '...'}\n")
-                if module_type == 'extractor' and config['steps'].get('archivers'):
-                    raise SetupError(f"As of version 0.13.0 of Auto Archiver, the 'archivers' step name has been changed to 'extractors'. Change this in your configuration file and try again. \
-Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_here]\n  enrichers:...\n")
-                raise SetupError(f"No {module_type}s were configured. Make sure to set at least one {module_type} in your configuration file or on the command line (using --{module_type}s)")
+            if not config["steps"].get(f"{module_type}s", []):
+                if (module_type == "feeder" or module_type == "formatter") and config["steps"].get(f"{module_type}"):
+                    raise SetupError(
+                        f"It appears you have '{module_type}' set under 'steps' in your configuration file, but as of version 0.13.0 of Auto Archiver, you must use '{module_type}s'. Change this in your configuration file and try again. \
+Here's how that would look: \n\nsteps:\n  {module_type}s:\n  - [your_{module_type}_name_here]\n  {'extractors:...' if module_type == 'feeder' else '...'}\n"
+                    )
+                if module_type == "extractor" and config["steps"].get("archivers"):
+                    raise SetupError(
+                        "As of version 0.13.0 of Auto Archiver, the 'archivers' step name has been changed to 'extractors'. Change this in your configuration file and try again. \
+Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_here]\n  enrichers:...\n"
+                    )
+                raise SetupError(
+                    f"No {module_type}s were configured. Make sure to set at least one {module_type} in your configuration file or on the command line (using --{module_type}s)"
+                )
 
     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,
@@ -94,7 +135,9 @@ Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_
         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", [])
+            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,
@@ -117,30 +160,32 @@ Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_
             enabled_modules = []
             # first loads the modules from the config file, then from the command line
             for module_type in MODULE_TYPES:
-                enabled_modules.extend(yaml_config['steps'].get(f"{module_type}s", []))
+                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 = self.module_factory.available_modules(limit_to_modules=enabled_modules, suppress_warnings=True)
+            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':
+        elif basic_config.mode == "simple":
             simple_modules = [module for module in self.module_factory.available_modules() if not module.requires_setup]
             self.add_individual_module_args(simple_modules, parser)
 
             # 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)
+                    yaml_config["steps"].setdefault(f"{module_type}s", []).append(module.name)
         else:
             # load all modules, they're not using the 'simple' mode
             all_modules = self.module_factory.available_modules()
             # add all the modules to the steps
             for module in all_modules:
                 for module_type in module.type:
-                    yaml_config['steps'].setdefault(f"{module_type}s", []).append(module.name)
+                    yaml_config["steps"].setdefault(f"{module_type}s", []).append(module.name)
 
             self.add_individual_module_args(all_modules, parser)
-        
+
         parser.set_defaults(**to_dot_notation(yaml_config))
 
         # reload the parser with the new arguments, now that we have them
@@ -166,43 +211,76 @@ Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_
             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)
+            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
 
-        parser.add_argument('--authentication', dest='authentication', help='A dictionary of sites and their authentication methods \
+        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.',
-                                                                            default={},
-                                                                            nargs="?",
-                                                                            action=AuthenticationJsonParseAction)
+                                                                            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_individual_module_args(self, modules: list[LazyBaseModule] = None, parser: argparse.ArgumentParser = None) -> None:
+        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_individual_module_args(
+        self, modules: list[LazyBaseModule] = None, parser: argparse.ArgumentParser = None
+    ) -> None:
         if not modules:
             modules = self.module_factory.available_modules()
-        
+
         for module in modules:
-            if module.name == 'cli_feeder':
+            if module.name == "cli_feeder":
                 # special case. For the CLI feeder, allow passing URLs directly on the command line without setting --cli_feeder.urls=
-                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(
+                    "urls",
+                    nargs="*",
+                    default=[],
+                    help="URL(s) to archive, either a single URL or a list of urls, should not come from config.yaml",
+                )
                 continue
-                
+
             if not module.configs:
                 # this module has no configs, don't show anything in the help
                 # (TODO: do we want to show something about this module though, like a description?)
@@ -211,21 +289,21 @@ Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_
             group = parser.add_argument_group(module.display_name or module.name, f"{module.description[:100]}...")
 
             for name, kwargs in module.configs.items():
-                if not kwargs.get('metavar', None):
+                if not kwargs.get("metavar", None):
                     # make a nicer metavar, metavar is what's used in the help, e.g. --cli_feeder.urls [METAVAR]
-                    kwargs['metavar'] = name.upper()
+                    kwargs["metavar"] = name.upper()
 
-                if kwargs.get('required', False):
+                if kwargs.get("required", False):
                     # required args shouldn't have a 'default' value, remove it
-                    kwargs.pop('default', None)
+                    kwargs.pop("default", None)
 
-                kwargs.pop('cli_set', None)
-                should_store = kwargs.pop('should_store', False)
-                kwargs['dest'] = f"{module.name}.{kwargs.pop('dest', name)}"
+                kwargs.pop("cli_set", None)
+                should_store = kwargs.pop("should_store", False)
+                kwargs["dest"] = f"{module.name}.{kwargs.pop('dest', name)}"
                 try:
-                    kwargs['type'] = getattr(validators, kwargs.get('type', '__invalid__'))
+                    kwargs["type"] = getattr(validators, kwargs.get("type", "__invalid__"))
                 except AttributeError:
-                    kwargs['type'] = __builtins__.get(kwargs.get('type'), str)
+                    kwargs["type"] = __builtins__.get(kwargs.get("type"), str)
                 arg = group.add_argument(f"--{module.name}.{name}", **kwargs)
                 arg.should_store = should_store
 
@@ -240,12 +318,11 @@ Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_
         self.basic_parser.exit()
 
     def setup_logging(self, config):
+        logging_config = config["logging"]
 
-        logging_config = config['logging']
-
-        if logging_config.get('enabled', True) is False:
+        if logging_config.get("enabled", True) is False:
             # disabled logging settings, they're set on a higher level
-            logger.disable('auto_archiver')
+            logger.disable("auto_archiver")
             return
 
         # setup loguru logging
@@ -255,48 +332,66 @@ Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_
             pass
 
         # 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'])
+        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):
         """
-        Traverses all modules in 'steps' and loads them into the orchestrator, storing them in the 
+        Traverses all modules in 'steps' and loads them into the orchestrator, storing them in the
         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 MODULE_TYPES:
-
             step_items = []
             modules_to_load = modules_by_type[f"{module_type}s"]
             if not modules_to_load:
-                raise SetupError(f"No {module_type}s were configured. Make sure to set at least one {module_type} in your configuration file or on the command line (using --{module_type}s)")
+                raise SetupError(
+                    f"No {module_type}s were configured. Make sure to set at least one {module_type} in your configuration file or on the command line (using --{module_type}s)"
+                )
 
             def check_steps_ok():
                 if not len(step_items):
                     if len(modules_to_load):
-                        logger.error(f"Unable to load any {module_type}s. Tried the following, but none were available: {modules_to_load}")
-                    raise SetupError(f"NO {module_type.upper()}S LOADED. Please check your configuration and try again.")
-                
+                        logger.error(
+                            f"Unable to load any {module_type}s. Tried the following, but none were available: {modules_to_load}"
+                        )
+                    raise SetupError(
+                        f"NO {module_type.upper()}S LOADED. Please check your configuration and try again."
+                    )
 
-                if (module_type == 'feeder' or module_type == 'formatter') and len(step_items) > 1:
-                    raise SetupError(f"Only one {module_type} is allowed, found {len(step_items)} {module_type}s. Please remove one of the following from your configuration file: {modules_to_load}")
+                if (module_type == "feeder" or module_type == "formatter") and len(step_items) > 1:
+                    raise SetupError(
+                        f"Only one {module_type} is allowed, found {len(step_items)} {module_type}s. Please remove one of the following from your configuration file: {modules_to_load}"
+                    )
 
             for module in modules_to_load:
-
                 if module in invalid_modules:
                     continue
 
+                # check to make sure that we're trying to load it as the correct type - i.e. make sure the user hasn't put it under the wrong 'step'
+                lazy_module: LazyBaseModule = self.module_factory.get_module_lazy(module)
+                if module_type not in lazy_module.type:
+                    types = ",".join(f"'{t}'" for t in lazy_module.type)
+                    raise SetupError(
+                        f"Configuration Error: Module '{module}' is not a {module_type}, but has the types: {types}. Please check you set this module up under the right step in your orchestration file."
+                    )
+
                 loaded_module = None
                 try:
-                    loaded_module: BaseModule = self.module_factory.get_module(module, self.config)
+                    loaded_module: BaseModule = lazy_module.load(self.config)
                 except (KeyboardInterrupt, Exception) as e:
-                    logger.error(f"Error during setup of modules: {e}\n{traceback.format_exc()}")
-                    if loaded_module and module_type == 'extractor':
-                        loaded_module.cleanup()
+                    if not isinstance(e, KeyboardInterrupt) and not isinstance(e, SetupError):
+                        logger.error(f"Error during setup of modules: {e}\n{traceback.format_exc()}")
+
+                    # access the _instance here because loaded_module may not return if there's an error
+                    if lazy_module._instance and module_type == "extractor":
+                        lazy_module._instance.cleanup()
                     raise e
 
                 if not loaded_module:
@@ -310,11 +405,13 @@ Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_
 
     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.")
+            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."
+            )
             raise FileNotFoundError(f"Configuration file {config_file} not found")
 
         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
@@ -337,49 +434,55 @@ Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_
         yaml_config = self.load_config(basic_config.config_file)
 
         return self.setup_complete_parser(basic_config, yaml_config, unused_args)
-    
+
     def check_for_updates(self):
         response = requests.get("https://pypi.org/pypi/auto-archiver/json").json()
-        latest_version = response['info']['version']
+        latest_version = version.parse(response["info"]["version"])
+        current_version = version.parse(__version__)
         # check version compared to current version
-        if latest_version != __version__:
-            if os.environ.get('RUNNING_IN_DOCKER'):
+        if latest_version > current_version:
+            if os.environ.get("RUNNING_IN_DOCKER"):
                 update_cmd = "`docker pull bellingcat/auto-archiver:latest`"
             else:
                 update_cmd = "`pip install --upgrade auto-archiver`"
             logger.warning("")
             logger.warning("********* IMPORTANT: UPDATE AVAILABLE ********")
-            logger.warning(f"A new version of auto-archiver is available (v{latest_version}, you have {__version__})")
+            logger.warning(
+                f"A new version of auto-archiver is available (v{latest_version}, you have v{current_version})"
+            )
             logger.warning(f"Make sure to update to the latest version using: {update_cmd}")
             logger.warning("")
 
-        
     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
         """
 
         self.check_for_updates()
 
         if self.setup_finished:
-            logger.warning("The `setup_config()` function should only ever be run once. \
+            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.")
+                           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'])
+        self.install_modules(self.config["steps"])
 
         # log out the modules that were loaded
         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")))
-        
+            logger.info(
+                f"{module_type.upper()}S: " + ", ".join(m.display_name for m in getattr(self, f"{module_type}s"))
+            )
+
         self.setup_finished = True
 
     def _command_line_run(self, args: list) -> Generator[Metadata]:
@@ -387,9 +490,9 @@ Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_
         This is the main entry point for the orchestrator, when run from the command line.
 
         :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'
@@ -407,7 +510,6 @@ Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_
             e.cleanup()
 
     def feed(self) -> Generator[Metadata]:
-        
         url_count = 0
         for feeder in self.feeders:
             for item in feeder:
@@ -438,9 +540,9 @@ Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_
             self.cleanup()
             exit()
         except Exception as e:
-            logger.error(f'Got unexpected error on item {item}: {e}\n{traceback.format_exc()}')
+            logger.error(f"Got unexpected error on item {item}: {e}\n{traceback.format_exc()}")
             for d in self.databases:
-                if type(e) == AssertionError:
+                if isinstance(e, AssertionError):
                     d.failed(item, str(e))
                 else:
                     d.failed(item, reason="unexpected error")
@@ -453,13 +555,13 @@ Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_
 
     def archive(self, result: Metadata) -> Union[Metadata, None]:
         """
-            Runs the archiving process for a single URL
-            1. Each archiver can sanitize its own URLs
-            2. Check for cached results in Databases, and signal start to the databases
-            3. Call Archivers until one succeeds
-            4. Call Enrichers
-            5. Store all downloaded/generated media
-            6. Call selected Formatter and store formatted if needed
+        Runs the archiving process for a single URL
+        1. Each archiver can sanitize its own URLs
+        2. Check for cached results in Databases, and signal start to the databases
+        3. Call Archivers until one succeeds
+        4. Call Enrichers
+        5. Store all downloaded/generated media
+        6. Call selected Formatter and store formatted if needed
         """
 
         original_url = result.get_url().strip()
@@ -475,7 +577,8 @@ Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_
             url = a.sanitize_url(url)
 
         result.set_url(url)
-        if original_url != url: result.set("original_url", original_url)
+        if original_url != url:
+            result.set("original_url", original_url)
 
         # 2 - notify start to DBs, propagate already archived if feature enabled in DBs
         cached_result = None
@@ -486,7 +589,8 @@ Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_
         if cached_result:
             logger.debug("Found previously archived entry")
             for d in self.databases:
-                try: d.done(cached_result, cached=True)
+                try:
+                    d.done(cached_result, cached=True)
                 except Exception as e:
                     logger.error(f"ERROR database {d.name}: {e}: {traceback.format_exc()}")
             return cached_result
@@ -496,13 +600,15 @@ Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_
             logger.info(f"Trying extractor {a.name} for {url}")
             try:
                 result.merge(a.download(result))
-                if result.is_success(): break
+                if result.is_success():
+                    break
             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)
+            try:
+                e.enrich(result)
             except Exception as exc:
                 logger.error(f"ERROR enricher {e.name}: {exc}: {traceback.format_exc()}")
 
@@ -520,12 +626,12 @@ Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_
 
         # signal completion to databases and archivers
         for d in self.databases:
-            try: d.done(result)
+            try:
+                d.done(result)
             except Exception as e:
                 logger.error(f"ERROR database {d.name}: {e}: {traceback.format_exc()}")
 
         return result
-    
 
     def setup_authentication(self, config: dict) -> dict:
         """
@@ -534,7 +640,7 @@ Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_
         Split up strings into multiple sites if they are comma separated
         """
 
-        authentication = config.get('authentication', {})
+        authentication = config.get("authentication", {})
 
         # extract out concatenated sites
         for key, val in copy(authentication).items():
@@ -543,8 +649,8 @@ Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_
                     site = site.strip()
                     authentication[site] = val
                 del authentication[key]
-        
-        config['authentication'] = authentication
+
+        config["authentication"] = authentication
         return config
 
     # Helper Properties

src/auto_archiver/core/storage.py

@@ -1,5 +1,22 @@
 """
 Base module for Storage modules – modular components that store media objects in various locations.
+
+If you are looking to implement a new storage module, you should subclass the `Storage` class and
+implement the `get_cdn_url` and `uploadf` methods.
+
+Your module **must** also have two config variables 'path_generator' and 'filename_generator' which
+determine how the key is generated for the media object. The 'path_generator' and 'filename_generator'
+variables can be set to one of the following values:
+- 'flat': A flat structure with no subfolders
+- 'url': A structure based on the URL of the media object
+- 'random': A random structure
+
+The 'filename_generator' variable can be set to one of the following values:
+- 'random': A random string
+- 'static': A replicable strategy such as a hash
+
+If you don't want to use this naming convention, you can override the `set_key` method in your subclass.
+
 """
 
 from __future__ import annotations
@@ -15,18 +32,19 @@ 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
 
+
 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): 
+    def store(self, media: Media, url: str, metadata: Metadata = None) -> None:
+        if media.is_stored(in_storage=self):
             logger.debug(f"{media.key} already stored, skipping")
             return
+
         self.set_key(media, url, metadata)
         self.upload(media, metadata=metadata)
         media.add_url(self.get_cdn_url(media))
@@ -42,42 +60,55 @@ class Storage(BaseModule):
     def uploadf(self, file: IO[bytes], key: str, **kwargs: dict) -> bool:
         """
         Uploads (or saves) a file to the storage service/location.
+
+        This method should not be called directly, but instead through the 'store' method,
+        which sets up the media for storage.
         """
         pass
 
     def upload(self, media: Media, **kwargs) -> bool:
-        logger.debug(f'[{self.__class__.__name__}] storing file {media.filename} with key {media.key}')
-        with open(media.filename, 'rb') as f:
+        """
+        Uploads a media object to the storage service.
+
+        This method should not be called directly, but instead be called through the 'store' method,
+        which sets up the media for storage.
+        """
+        logger.debug(f"[{self.__class__.__name__}] storing file {media.filename} with key {media.key}")
+        with open(media.filename, "rb") as f:
             return self.uploadf(f, media, **kwargs)
 
-    def set_key(self, media: Media, url, metadata: Metadata) -> None:
+    def set_key(self, media: Media, url: str, metadata: Metadata) -> None:
         """takes the media and optionally item info and generates a key"""
-        if media.key is not None and len(media.key) > 0: return
-        folder = metadata.get_context('folder', '')
+
+        if media.key is not None and len(media.key) > 0:
+            # media key is already set
+            return
+
+        folder = metadata.get_context("folder", "")
         filename, ext = os.path.splitext(media.filename)
 
         # Handle path_generator logic
-        path_generator = self.config.get("path_generator", "url")
+        path_generator = self.path_generator
         if path_generator == "flat":
             path = ""
-            filename = slugify(filename)  # Ensure filename is slugified
         elif path_generator == "url":
-            path = slugify(url)
+            path = slugify(url)[:70]
         elif path_generator == "random":
-            path = self.config.get("random_path", random_str(24), True)
+            path = random_str(24)
         else:
             raise ValueError(f"Invalid path_generator: {path_generator}")
 
         # Handle filename_generator logic
-        filename_generator = self.config.get("filename_generator", "random")
+        filename_generator = self.filename_generator
         if filename_generator == "random":
             filename = random_str(24)
         elif filename_generator == "static":
             # load the hash_enricher module
-            he = self.module_factory.get_module(HashEnricher, self.config)
+            he: HashEnricher = self.module_factory.get_module("hash_enricher", self.config)
             hd = he.calculate_hash(media.filename)
             filename = hd[:24]
         else:
             raise ValueError(f"Invalid filename_generator: {filename_generator}")
 
-        media.key = os.path.join(folder, path, f"{filename}{ext}")
+        key = os.path.join(folder, path, f"{filename}{ext}")
+        media._key = key

src/auto_archiver/core/validators.py

@@ -3,10 +3,6 @@ from pathlib import Path
 import argparse
 import json
 
-def example_validator(value):
-    if "example" not in value:
-        raise argparse.ArgumentTypeError(f"{value} is not a valid value for this argument")
-    return value
 
 def positive_number(value):
     if value < 0:
@@ -19,5 +15,6 @@ def valid_file(value):
         raise argparse.ArgumentTypeError(f"File '{value}' does not exist.")
     return value
 
+
 def json_loader(cli_val):
-    return json.loads(cli_val)
+    return json.loads(cli_val)

src/auto_archiver/modules/api_db/__init__.py

@@ -1 +1 @@
-from .api_db import AAApiDb
+from .api_db import AAApiDb

src/auto_archiver/modules/api_db/__manifest__.py

@@ -11,8 +11,7 @@
             "required": True,
             "help": "API endpoint where calls are made to",
         },
-        "api_token": {"default": None,
-                      "help": "API Bearer token."},
+        "api_token": {"default": None, "help": "API Bearer token."},
         "public": {
             "default": False,
             "type": "bool",
@@ -24,9 +23,9 @@
             "help": "which group of users have access to the archive in case public=false as author",
         },
         "use_api_cache": {
-            "default": True,
+            "default": False,
             "type": "bool",
-            "help": "if False then the API database will be queried prior to any archiving operations and stop if the link has already been archived",
+            "help": "if True then the API database will be queried prior to any archiving operations and stop if the link has already been archived",
         },
         "store_results": {
             "default": True,

src/auto_archiver/modules/api_db/api_db.py

@@ -12,10 +12,11 @@ class AAApiDb(Database):
     """Connects to auto-archiver-api instance"""
 
     def fetch(self, item: Metadata) -> Union[Metadata, bool]:
-        """ query the database for the existence of this item.
-            Helps avoid re-archiving the same URL multiple times.
+        """query the database for the existence of this item.
+        Helps avoid re-archiving the same URL multiple times.
         """
-        if not self.use_api_cache: return
+        if not self.use_api_cache:
+            return
 
         params = {"url": item.get_url(), "limit": 15}
         headers = {"Authorization": f"Bearer {self.api_token}", "accept": "application/json"}
@@ -32,22 +33,25 @@ class AAApiDb(Database):
 
     def done(self, item: Metadata, cached: bool = False) -> None:
         """archival result ready - should be saved to DB"""
-        if not self.store_results: return
+        if not self.store_results:
+            return
         if cached:
             logger.debug(f"skipping saving archive of {item.get_url()} to the AA API because it was cached")
             return
         logger.debug(f"saving archive of {item.get_url()} to the AA API.")
 
         payload = {
-            'author_id': self.author_id,
-            'url': item.get_url(),
-            'public': self.public,
-            'group_id': self.group_id,
-            'tags': list(self.tags),
-            'result': item.to_json(),
+            "author_id": self.author_id,
+            "url": item.get_url(),
+            "public": self.public,
+            "group_id": self.group_id,
+            "tags": list(self.tags),
+            "result": item.to_json(),
         }
         headers = {"Authorization": f"Bearer {self.api_token}"}
-        response = requests.post(os.path.join(self.api_endpoint, "interop/submit-archive"), json=payload, headers=headers)
+        response = requests.post(
+            os.path.join(self.api_endpoint, "interop/submit-archive"), json=payload, headers=headers
+        )
 
         if response.status_code == 201:
             logger.success(f"AA API: {response.json()}")

src/auto_archiver/modules/atlos_feeder_db_storage/__init__.py

@@ -1 +1 @@
-from .atlos_feeder_db_storage import AtlosFeederDbStorage
+from .atlos_feeder_db_storage import AtlosFeederDbStorage

src/auto_archiver/modules/atlos_feeder_db_storage/__manifest__.py

@@ -1,7 +1,7 @@
 {
     "name": "Atlos Feeder Database Storage",
     "type": ["feeder", "database", "storage"],
-"entry_point": "atlos_feeder_db_storage::AtlosFeederDbStorage",
+    "entry_point": "atlos_feeder_db_storage::AtlosFeederDbStorage",
     "requires_setup": True,
     "dependencies": {
         "python": ["loguru", "requests"],
@@ -15,7 +15,7 @@
         "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"
+            "type": "str",
         },
     },
     "description": """
@@ -42,5 +42,5 @@
     - Requires an Atlos account with a project and a valid API token for authentication.
     - Ensures only unprocessed, visible, and ready-to-archive URLs are returned.
     - Feches any media items within an Atlos project, regardless of separation into incidents.
-    """
+    """,
 }

src/auto_archiver/modules/atlos_feeder_db_storage/atlos_feeder_db_storage.py

@@ -10,7 +10,6 @@ from auto_archiver.utils import calculate_file_hash
 
 
 class AtlosFeederDbStorage(Feeder, Database, Storage):
-
     def setup(self) -> requests.Session:
         """create and return a persistent session."""
         self.session = requests.Session()
@@ -18,9 +17,7 @@ class AtlosFeederDbStorage(Feeder, Database, Storage):
     def _get(self, endpoint: str, params: Optional[dict] = None) -> dict:
         """Wrapper for GET requests to the Atlos API."""
         url = f"{self.atlos_url}{endpoint}"
-        response = self.session.get(
-            url, headers={"Authorization": f"Bearer {self.api_token}"}, params=params
-        )
+        response = self.session.get(url, headers={"Authorization": f"Bearer {self.api_token}"}, params=params)
         response.raise_for_status()
         return response.json()
 
@@ -85,10 +82,7 @@ class AtlosFeederDbStorage(Feeder, Database, Storage):
     def _process_metadata(self, item: Metadata) -> dict:
         """Process metadata for storage on Atlos. Will convert any datetime
         objects to ISO format."""
-        return {
-            k: v.isoformat() if hasattr(v, "isoformat") else v
-            for k, v in item.metadata.items()
-        }
+        return {k: v.isoformat() if hasattr(v, "isoformat") else v for k, v in item.metadata.items()}
 
     def done(self, item: Metadata, cached: bool = False) -> None:
         """Mark an item as successfully archived in Atlos."""
@@ -129,10 +123,7 @@ class AtlosFeederDbStorage(Feeder, Database, Storage):
 
         # Check whether the media has already been uploaded
         source_material = self._get(f"/api/v2/source_material/{atlos_id}")["result"]
-        existing_media = [
-            artifact.get("file_hash_sha256")
-            for artifact in source_material.get("artifacts", [])
-        ]
+        existing_media = [artifact.get("file_hash_sha256") for artifact in source_material.get("artifacts", [])]
         if media_hash in existing_media:
             logger.info(f"{media.filename} with SHA256 {media_hash} already uploaded to Atlos")
             return True
@@ -150,4 +141,3 @@ class AtlosFeederDbStorage(Feeder, Database, Storage):
     def uploadf(self, file: IO[bytes], key: str, **kwargs: dict) -> bool:
         """Upload a file-like object; not implemented."""
         pass
-

src/auto_archiver/modules/cli_feeder/__manifest__.py

@@ -1,16 +1,15 @@
 {
-    'name': 'Command Line Feeder',
-    'type': ['feeder'],
-    'entry_point': 'cli_feeder::CLIFeeder',
-    'requires_setup': False,
-    'description': 'Feeds URLs to orchestrator from the command line',
-    'configs': {
-        'urls': {
-            'default': None,
-            'help': 'URL(s) to archive, either a single URL or a list of urls, should not come from config.yaml',
+    "name": "Command Line Feeder",
+    "type": ["feeder"],
+    "entry_point": "cli_feeder::CLIFeeder",
+    "requires_setup": False,
+    "configs": {
+        "urls": {
+            "default": None,
+            "help": "URL(s) to archive, either a single URL or a list of urls, should not come from config.yaml",
         },
     },
-    'description': """
+    "description": """
 The Command Line Feeder is the default enabled feeder for the Auto Archiver. It allows you to pass URLs directly to the orchestrator from the command line 
 without the need to specify any additional configuration or command line arguments:
 
@@ -20,4 +19,4 @@ You can pass multiple URLs by separating them with a space. The URLs will be pro
 
 `auto-archiver --feeder cli_feeder -- https://example.com/1/ https://example.com/2/`
 """,
-}
+}

src/auto_archiver/modules/cli_feeder/cli_feeder.py

@@ -2,20 +2,22 @@ from loguru import logger
 
 from auto_archiver.core.feeder import Feeder
 from auto_archiver.core.metadata import Metadata
+from auto_archiver.core.consts import SetupError
+
 
 class CLIFeeder(Feeder):
-
     def setup(self) -> None:
-        self.urls = self.config['urls']
+        self.urls = self.config["urls"]
         if not self.urls:
-            raise ValueError("No URLs provided. Please provide at least one URL via the command line, or set up an alternative feeder. Use --help for more information.")
+            raise SetupError(
+                "No URLs provided. Please provide at least one URL via the command line, or set up an alternative feeder. Use --help for more information."
+            )
 
     def __iter__(self) -> Metadata:
-        urls = self.config['urls']
+        urls = self.config["urls"]
         for url in urls:
             logger.debug(f"Processing {url}")
             m = Metadata().set_url(url)
-            m.set_context("folder", "cli")
             yield m
 
-        logger.success(f"Processed {len(urls)} URL(s)")
+        logger.success(f"Processed {len(urls)} URL(s)")

src/auto_archiver/modules/console_db/__init__.py

@@ -1 +1 @@
-from .console_db import ConsoleDb
+from .console_db import ConsoleDb

src/auto_archiver/modules/console_db/console_db.py

@@ -6,18 +6,18 @@ from auto_archiver.core import Metadata
 
 class ConsoleDb(Database):
     """
-        Outputs results to the console
+    Outputs results to the console
     """
 
     def started(self, item: Metadata) -> None:
         logger.info(f"STARTED {item}")
 
-    def failed(self, item: Metadata, reason:str) -> None:
+    def failed(self, item: Metadata, reason: str) -> None:
         logger.error(f"FAILED {item}: {reason}")
 
     def aborted(self, item: Metadata) -> None:
         logger.warning(f"ABORTED {item}")
 
-    def done(self, item: Metadata, cached: bool=False) -> None:
+    def done(self, item: Metadata, cached: bool = False) -> None:
         """archival result ready - should be saved to DB"""
-        logger.success(f"DONE {item}")
+        logger.success(f"DONE {item}")

src/auto_archiver/modules/csv_db/__init__.py

@@ -1 +1 @@
-from .csv_db import CSVDb
+from .csv_db import CSVDb

src/auto_archiver/modules/csv_db/__manifest__.py

@@ -2,12 +2,11 @@
     "name": "CSV Database",
     "type": ["database"],
     "requires_setup": False,
-    "dependencies": {"python": ["loguru"]
-                              },
-    'entry_point': 'csv_db::CSVDb',
+    "dependencies": {"python": ["loguru"]},
+    "entry_point": "csv_db::CSVDb",
     "configs": {
-            "csv_file": {"default": "db.csv", "help": "CSV file name to save metadata to"},
-        },
+        "csv_file": {"default": "db.csv", "help": "CSV file name to save metadata to"},
+    },
     "description": """
 Handles exporting archival results to a CSV file.
 

src/auto_archiver/modules/csv_db/csv_db.py

@@ -9,14 +9,15 @@ from auto_archiver.core import Metadata
 
 class CSVDb(Database):
     """
-        Outputs results to a CSV file
+    Outputs results to a CSV file
     """
 
-    def done(self, item: Metadata, cached: bool=False) -> None:
+    def done(self, item: Metadata, cached: bool = False) -> None:
         """archival result ready - should be saved to DB"""
         logger.success(f"DONE {item}")
         is_empty = not os.path.isfile(self.csv_file) or os.path.getsize(self.csv_file) == 0
         with open(self.csv_file, "a", encoding="utf-8") as outf:
             writer = DictWriter(outf, fieldnames=asdict(Metadata()))
-            if is_empty: writer.writeheader()
+            if is_empty:
+                writer.writeheader()
             writer.writerow(asdict(item))

src/auto_archiver/modules/csv_feeder/__init__.py

@@ -1 +1 @@
-from .csv_feeder import CSVFeeder
+from .csv_feeder import CSVFeeder

src/auto_archiver/modules/csv_feeder/__manifest__.py

@@ -1,27 +1,23 @@
 {
     "name": "CSV Feeder",
     "type": ["feeder"],
-    "requires_setup": False,
-    "dependencies": {
-        "python": ["loguru"],
-        "bin": [""]
-    },
-    'requires_setup': True,
-    'entry_point': "csv_feeder::CSVFeeder",
+    "dependencies": {"python": ["loguru"], "bin": [""]},
+    "requires_setup": True,
+    "entry_point": "csv_feeder::CSVFeeder",
     "configs": {
-            "files": {
-                "default": None,
-                "help": "Path to the input file(s) to read the URLs from, comma separated. \
+        "files": {
+            "default": None,
+            "help": "Path to the input file(s) to read the URLs from, comma separated. \
                         Input files should be formatted with one URL per line",
-                "required": True,
-                "type": "valid_file",
-                "nargs": "+",
-            },
-            "column": {
-                "default": None,
-                "help": "Column number or name to read the URLs from, 0-indexed",
-            }
+            "required": True,
+            "type": "valid_file",
+            "nargs": "+",
         },
+        "column": {
+            "default": None,
+            "help": "Column number or name to read the URLs from, 0-indexed",
+        },
+    },
     "description": """
     Reads URLs from CSV files and feeds them into the archiving process.
 
@@ -33,5 +29,5 @@
     ### Setup
     - Input files should be formatted with one URL per line, with or without a header row.
     - If you have a header row, you can specify the column number or name to read URLs from using the 'column' config option.
-    """
+    """,
 }

src/auto_archiver/modules/csv_feeder/csv_feeder.py

@@ -5,11 +5,10 @@ from auto_archiver.core import Feeder
 from auto_archiver.core import Metadata
 from auto_archiver.utils import url_or_none
 
+
 class CSVFeeder(Feeder):
-
     column = None
 
-
     def __iter__(self) -> Metadata:
         for file in self.files:
             with open(file, "r") as f:
@@ -20,9 +19,11 @@ class CSVFeeder(Feeder):
                     try:
                         url_column = first_row.index(url_column)
                     except ValueError:
-                        logger.error(f"Column {url_column} not found in header row: {first_row}. Did you set the 'column' config correctly?")
+                        logger.error(
+                            f"Column {url_column} not found in header row: {first_row}. Did you set the 'column' config correctly?"
+                        )
                         return
-                elif not(url_or_none(first_row[url_column])):
+                elif not (url_or_none(first_row[url_column])):
                     # it's a header row, but we've been given a column number already
                     logger.debug(f"Skipping header row: {first_row}")
                 else:
@@ -35,4 +36,4 @@ class CSVFeeder(Feeder):
                         continue
                     url = row[url_column]
                     logger.debug(f"Processing {url}")
-                    yield Metadata().set_url(url)
+                    yield Metadata().set_url(url)

src/auto_archiver/modules/gdrive_storage/__init__.py

@@ -1 +1 @@
-from .gdrive_storage import GDriveStorage
+from .gdrive_storage import GDriveStorage

src/auto_archiver/modules/gdrive_storage/__manifest__.py

@@ -19,14 +19,21 @@
         },
         "filename_generator": {
             "default": "static",
-            "help": "how to name stored files: 'random' creates a random string; 'static' uses a replicable strategy such as a hash.",
+            "help": "how to name stored files: 'random' creates a random string; 'static' uses a hash, with the settings of the 'hash_enricher' module (defaults to SHA256 if not enabled).",
             "choices": ["random", "static"],
         },
-        "root_folder_id": {"required": True,
-                           "help": "root google drive folder ID to use as storage, found in URL: 'https://drive.google.com/drive/folders/FOLDER_ID'"},
-        "oauth_token": {"default": None,
-                        "help": "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": {"default": "secrets/service_account.json", "help": "service account JSON file path, same as used for Google Sheets. NOTE: storage used will count towards the developer account."},
+        "root_folder_id": {
+            "required": True,
+            "help": "root google drive folder ID to use as storage, found in URL: 'https://drive.google.com/drive/folders/FOLDER_ID'",
+        },
+        "oauth_token": {
+            "default": None,
+            "help": "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": {
+            "default": "secrets/service_account.json",
+            "help": "service account JSON file path, same as used for Google Sheets. NOTE: storage used will count towards the developer account.",
+        },
     },
     "description": """
     
@@ -94,5 +101,5 @@ This module integrates Google Drive as a storage backend, enabling automatic fol
     https://davemateer.com/2022/04/28/google-drive-with-python#tokens
     
     
-"""
+""",
 }

src/auto_archiver/modules/gdrive_storage/gdrive_storage.py

@@ -1,4 +1,3 @@
-
 import json
 import os
 import time
@@ -15,12 +14,9 @@ from auto_archiver.core import Media
 from auto_archiver.core import Storage
 
 
-
-
 class GDriveStorage(Storage):
-
     def setup(self) -> None:
-        self.scopes = ['https://www.googleapis.com/auth/drive']
+        self.scopes = ["https://www.googleapis.com/auth/drive"]
         # Initialize Google Drive service
         self._setup_google_drive_service()
 
@@ -37,25 +33,25 @@ class GDriveStorage(Storage):
 
     def _initialize_with_oauth_token(self):
         """Initialize Google Drive service with OAuth token."""
-        with open(self.oauth_token, 'r') as stream:
+        with open(self.oauth_token, "r") as stream:
             creds_json = json.load(stream)
-            creds_json['refresh_token'] = creds_json.get("refresh_token", "")
+            creds_json["refresh_token"] = creds_json.get("refresh_token", "")
 
         creds = Credentials.from_authorized_user_info(creds_json, self.scopes)
         if not creds.valid and creds.expired and creds.refresh_token:
             creds.refresh(Request())
-            with open(self.oauth_token, 'w') as token_file:
+            with open(self.oauth_token, "w") as token_file:
                 logger.debug("Saving refreshed OAuth token.")
                 token_file.write(creds.to_json())
         elif not creds.valid:
             raise ValueError("Invalid OAuth token. Please regenerate the token.")
 
-        return build('drive', 'v3', credentials=creds)
+        return build("drive", "v3", credentials=creds)
 
     def _initialize_with_service_account(self):
         """Initialize Google Drive service with service account."""
         creds = service_account.Credentials.from_service_account_file(self.service_account, scopes=self.scopes)
-        return build('drive', 'v3', credentials=creds)
+        return build("drive", "v3", credentials=creds)
 
     def get_cdn_url(self, media: Media) -> str:
         """
@@ -79,7 +75,7 @@ class GDriveStorage(Storage):
         return f"https://drive.google.com/file/d/{file_id}/view?usp=sharing"
 
     def upload(self, media: Media, **kwargs) -> bool:
-        logger.debug(f'[{self.__class__.__name__}] storing file {media.filename} with key {media.key}')
+        logger.debug(f"[{self.__class__.__name__}] storing file {media.filename} with key {media.key}")
         """
         1. for each sub-folder in the path check if exists or create
         2. upload file to root_id/other_paths.../filename
@@ -95,25 +91,30 @@ class GDriveStorage(Storage):
             parent_id = upload_to
 
         # upload file to gd
-        logger.debug(f'uploading {filename=} to folder id {upload_to}')
-        file_metadata = {
-            'name': [filename],
-            'parents': [upload_to]
-        }
+        logger.debug(f"uploading {filename=} to folder id {upload_to}")
+        file_metadata = {"name": [filename], "parents": [upload_to]}
         media = MediaFileUpload(media.filename, resumable=True)
-        gd_file = self.service.files().create(supportsAllDrives=True, body=file_metadata, media_body=media, fields='id').execute()
-        logger.debug(f'uploadf: uploaded file {gd_file["id"]} successfully in folder={upload_to}')
+        gd_file = (
+            self.service.files()
+            .create(supportsAllDrives=True, body=file_metadata, media_body=media, fields="id")
+            .execute()
+        )
+        logger.debug(f"uploadf: uploaded file {gd_file['id']} successfully in folder={upload_to}")
 
     # must be implemented even if unused
-    def uploadf(self, file: IO[bytes], key: str, **kwargs: dict) -> bool: pass
+    def uploadf(self, file: IO[bytes], key: str, **kwargs: dict) -> bool:
+        pass
 
-    def _get_id_from_parent_and_name(self, parent_id: str,
-                                     name: str,
-                                     retries: int = 1,
-                                     sleep_seconds: int = 10,
-                                     use_mime_type: bool = False,
-                                     raise_on_missing: bool = True,
-                                     use_cache=False):
+    def _get_id_from_parent_and_name(
+        self,
+        parent_id: str,
+        name: str,
+        retries: int = 1,
+        sleep_seconds: int = 10,
+        use_mime_type: bool = False,
+        raise_on_missing: bool = True,
+        use_cache=False,
+    ):
         """
         Retrieves the id of a folder or file from its @name and the @parent_id folder
         Optionally does multiple @retries and sleeps @sleep_seconds between them
@@ -134,32 +135,39 @@ class GDriveStorage(Storage):
         debug_header: str = f"[searching {name=} in {parent_id=}]"
         query_string = f"'{parent_id}' in parents and name = '{name}' and trashed = false "
         if use_mime_type:
-            query_string += f" and mimeType='application/vnd.google-apps.folder' "
+            query_string += " and mimeType='application/vnd.google-apps.folder' "
 
         for attempt in range(retries):
-            results = self.service.files().list(
-                # both below for Google Shared Drives
-                supportsAllDrives=True,
-                includeItemsFromAllDrives=True,
-                q=query_string,
-                spaces='drive',  # ie not appDataFolder or photos
-                fields='files(id, name)'
-            ).execute()
-            items = results.get('files', [])
+            results = (
+                self.service.files()
+                .list(
+                    # both below for Google Shared Drives
+                    supportsAllDrives=True,
+                    includeItemsFromAllDrives=True,
+                    q=query_string,
+                    spaces="drive",  # ie not appDataFolder or photos
+                    fields="files(id, name)",
+                )
+                .execute()
+            )
+            items = results.get("files", [])
 
             if len(items) > 0:
-                logger.debug(f"{debug_header} found {len(items)} matches, returning last of {','.join([i['id'] for i in items])}")
-                _id = items[-1]['id']
-                if use_cache: self.api_cache[cache_key] = _id
+                logger.debug(
+                    f"{debug_header} found {len(items)} matches, returning last of {','.join([i['id'] for i in items])}"
+                )
+                _id = items[-1]["id"]
+                if use_cache:
+                    self.api_cache[cache_key] = _id
                 return _id
             else:
-                logger.debug(f'{debug_header} not found, attempt {attempt+1}/{retries}.')
+                logger.debug(f"{debug_header} not found, attempt {attempt + 1}/{retries}.")
                 if attempt < retries - 1:
-                    logger.debug(f'sleeping for {sleep_seconds} second(s)')
+                    logger.debug(f"sleeping for {sleep_seconds} second(s)")
                     time.sleep(sleep_seconds)
 
         if raise_on_missing:
-            raise ValueError(f'{debug_header} not found after {retries} attempt(s)')
+            raise ValueError(f"{debug_header} not found after {retries} attempt(s)")
         return None
 
     def _mkdir(self, name: str, parent_id: str):
@@ -167,12 +175,7 @@ class GDriveStorage(Storage):
         Creates a new GDrive folder @name inside folder @parent_id
         Returns id of the created folder
         """
-        logger.debug(f'Creating new folder with {name=} inside {parent_id=}')
-        file_metadata = {
-            'name': [name],
-            'mimeType': 'application/vnd.google-apps.folder',
-            'parents': [parent_id]
-        }
-        gd_folder = self.service.files().create(supportsAllDrives=True, body=file_metadata, fields='id').execute()
-        return gd_folder.get('id')
-
+        logger.debug(f"Creating new folder with {name=} inside {parent_id=}")
+        file_metadata = {"name": [name], "mimeType": "application/vnd.google-apps.folder", "parents": [parent_id]}
+        gd_folder = self.service.files().create(supportsAllDrives=True, body=file_metadata, fields="id").execute()
+        return gd_folder.get("id")

src/auto_archiver/modules/generic_extractor/__init__.py

@@ -1 +1 @@
-from .generic_extractor import GenericExtractor
+from .generic_extractor import GenericExtractor

src/auto_archiver/modules/generic_extractor/__manifest__.py

@@ -15,6 +15,9 @@ supported by `yt-dlp`, such as YouTube, Facebook, and others. It provides functi
 for retrieving videos, subtitles, comments, and other metadata, and it integrates with
 the broader archiving framework.
 
+For a full list of video platforms supported by `yt-dlp`, see the
+[official documentation](https://github.com/yt-dlp/yt-dlp/blob/master/supportedsites.md)
+
 ### Features
 - Supports downloading videos and playlists.
 - Retrieves metadata like titles, descriptions, upload dates, and durations.
@@ -71,10 +74,27 @@ If you are having issues with the extractor, you can review the version of `yt-d
             "default": "inf",
             "help": "Use to limit the number of videos to download when a channel or long page is being extracted. 'inf' means no limit.",
         },
+        "bguils_po_token_method": {
+            "default": "auto",
+            "help": "Set up a Proof of origin token provider. This process has additional requirements. See [authentication](https://auto-archiver.readthedocs.io/en/latest/how_to/authentication_how_to.html) for more information.",
+            "choices": ["auto", "script", "disabled"],
+        },
+        "extractor_args": {
+            "default": {},
+            "help": "Additional arguments to pass to the yt-dlp extractor. See https://github.com/yt-dlp/yt-dlp/blob/master/README.md#extractor-arguments.",
+            "type": "json_loader",
+        },
         "ytdlp_update_interval": {
             "default": 5,
             "help": "How often to check for yt-dlp updates (days). If positive, will check and update yt-dlp every [num] days. Set it to -1 to disable, or 0 to always update on every run.",
             "type": "int",
         },
+        "ytdlp_args": {
+            "default": "",
+            "help": "Additional arguments to pass to yt-dlp, e.g. --no-check-certificate or --plugin-dirs.\
+See yt-dlp documentation here for more information: https://github.com/yt-dlp/yt-dlp?tab=readme-ov-file#general-options\
+Note: this is not to be confused with 'extractor_args' which are specific to the extractor itself.",
+            "type": "str",
+        },
     },
 }

src/auto_archiver/modules/generic_extractor/bluesky.py

@@ -4,15 +4,16 @@ from auto_archiver.core.extractor import Extractor
 from auto_archiver.core.metadata import Metadata, Media
 from .dropin import GenericDropin, InfoExtractor
 
-class Bluesky(GenericDropin):
 
+class Bluesky(GenericDropin):
     def create_metadata(self, post: dict, ie_instance: InfoExtractor, archiver: Extractor, url: str) -> Metadata:
         result = Metadata()
         result.set_url(url)
         result.set_title(post["record"]["text"])
         result.set_timestamp(post["record"]["createdAt"])
         for k, v in self._get_post_data(post).items():
-            if v: result.set(k, v)
+            if v:
+                result.set(k, v)
 
         # download if embeds present (1 video XOR >=1 images)
         for media in self._download_bsky_embeds(post, archiver):
@@ -23,12 +24,12 @@ class Bluesky(GenericDropin):
 
     def extract_post(self, url: str, ie_instance: InfoExtractor) -> dict:
         # TODO: If/when this PR (https://github.com/yt-dlp/yt-dlp/pull/12098) is merged on ytdlp, remove the comments and delete the code below
-        handle, video_id = ie_instance._match_valid_url(url).group('handle', 'id')
+        handle, video_id = ie_instance._match_valid_url(url).group("handle", "id")
         return ie_instance._extract_post(handle=handle, post_id=video_id)
 
     def _download_bsky_embeds(self, post: dict, archiver: Extractor) -> list[Media]:
         """
-        Iterates over image(s) or video in a Bluesky post and downloads them        
+        Iterates over image(s) or video in a Bluesky post and downloads them
         """
         media = []
         embed = post.get("record", {}).get("embed", {})
@@ -37,16 +38,15 @@ class Bluesky(GenericDropin):
 
         media_url = "https://bsky.social/xrpc/com.atproto.sync.getBlob?cid={}&did={}"
         for image_media in image_medias:
-            url = media_url.format(image_media['image']['ref']['$link'], post['author']['did'])
+            url = media_url.format(image_media["image"]["ref"]["$link"], post["author"]["did"])
             image_media = archiver.download_from_url(url)
             media.append(Media(image_media))
         for video_media in video_medias:
-            url = media_url.format(video_media['ref']['$link'], post['author']['did'])
+            url = media_url.format(video_media["ref"]["$link"], post["author"]["did"])
             video_media = archiver.download_from_url(url)
             media.append(Media(video_media))
         return media
 
-
     def _get_post_data(self, post: dict) -> dict:
         """
         Extracts relevant information returned by the .getPostThread api call (excluding text/created_at): author, mentions, tags, links.
@@ -74,4 +74,4 @@ class Bluesky(GenericDropin):
             res["tags"] = tags
         if links:
             res["links"] = links
-        return res
+        return res

src/auto_archiver/modules/generic_extractor/dropin.py

@@ -1,12 +1,14 @@
+from typing import Type
 from yt_dlp.extractor.common import InfoExtractor
 from auto_archiver.core.metadata import Metadata
 from auto_archiver.core.extractor import Extractor
 
+
 class GenericDropin:
     """Base class for dropins for the generic extractor.
-    
+
     In many instances, an extractor will exist in ytdlp, but it will only process videos.
-    Dropins can be created and used to make use of the already-written private code of a 
+    Dropins can be created and used to make use of the already-written private code of a
     specific extractor from ytdlp.
 
     The dropin should be able to handle the following methods:
@@ -23,26 +25,26 @@ class GenericDropin:
 
     """
 
+    extractor: Type[Extractor] = None
+
     def extract_post(self, url: str, ie_instance: InfoExtractor):
         """
         This method should return the post data from the url.
         """
         raise NotImplementedError("This method should be implemented in the subclass")
-    
 
     def create_metadata(self, post: dict, ie_instance: InfoExtractor, archiver: Extractor, url: str) -> Metadata:
         """
         This method should create a Metadata object from the post data.
         """
         raise NotImplementedError("This method should be implemented in the subclass")
-    
 
     def skip_ytdlp_download(self, url: str, ie_instance: InfoExtractor):
         """
         This method should return True if you want to skip the ytdlp download method.
         """
         return False
-    
+
     def keys_to_clean(self, video_data: dict, info_extractor: InfoExtractor):
         """
         This method should return a list of strings (keys) to clean from the video_data dict.
@@ -50,9 +52,25 @@ class GenericDropin:
         E.g. ["uploader", "uploader_id", "tiktok_specific_field"]
         """
         return []
-    
+
     def download_additional_media(self, video_data: dict, info_extractor: InfoExtractor, metadata: Metadata):
         """
         This method should download any additional media from the post.
         """
-        return metadata
+        return metadata
+
+    def suitable(self, url, info_extractor: InfoExtractor):
+        """
+        A method to allow dropins to override their InfoExtractor's 'suitable' method.
+        Dropins should override this method and return True if the url is suitable for the extractor
+        (based on being able to parse other URLs). See the `suitable_extractors` method in the
+        `GenericExtractor` class for how this is implemented.
+
+        The default behaviour of this method is to return the result of the InfoExtractor's 'suitable' method.
+
+        ### Example: An example of where this is useful is for the FacebookIE extractor in yt-dlp. By default,
+        it's 'suitable' method only returns True for video URLs. However, we can override this method in the
+        Facebook dropin to return True for all Facebook URLs (photo/post types). This way, the Facebook dropin
+        can be used for all Facebook URLs.
+        """
+        return info_extractor.suitable(url)

src/auto_archiver/modules/generic_extractor/facebook.py

@@ -1,18 +1,154 @@
+import re
 from .dropin import GenericDropin
+from auto_archiver.core.metadata import Metadata
+from yt_dlp.extractor.facebook import FacebookIE
+
+# TODO: Remove if / when  https://github.com/yt-dlp/yt-dlp/pull/12275 is merged
+from yt_dlp.utils import (
+    clean_html,
+    get_element_by_id,
+    traverse_obj,
+    get_first,
+    merge_dicts,
+    int_or_none,
+    parse_count,
+)
+
+
+def _extract_metadata(self, webpage, video_id):
+    post_data = [
+        self._parse_json(j, video_id, fatal=False)
+        for j in re.findall(r"data-sjs>({.*?ScheduledServerJS.*?})</script>", webpage)
+    ]
+    post = (
+        traverse_obj(
+            post_data,
+            (..., "require", ..., ..., ..., "__bbox", "require", ..., ..., ..., "__bbox", "result", "data"),
+            expected_type=dict,
+        )
+        or []
+    )
+    media = traverse_obj(
+        post,
+        (
+            ...,
+            "attachments",
+            ...,
+            lambda k, v: (k == "media" and str(v["id"]) == video_id and v["__typename"] == "Video"),
+        ),
+        expected_type=dict,
+    )
+    title = get_first(media, ("title", "text"))
+    description = get_first(media, ("creation_story", "comet_sections", "message", "story", "message", "text"))
+    page_title = title or self._html_search_regex(
+        (
+            r'<h2\s+[^>]*class="uiHeaderTitle"[^>]*>(?P<content>[^<]*)</h2>',
+            r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(?P<content>.*?)</span>',
+            self._meta_regex("og:title"),
+            self._meta_regex("twitter:title"),
+            r"<title>(?P<content>.+?)</title>",
+        ),
+        webpage,
+        "title",
+        default=None,
+        group="content",
+    )
+    description = description or self._html_search_meta(
+        ["description", "og:description", "twitter:description"], webpage, "description", default=None
+    )
+    uploader_data = (
+        get_first(media, ("owner", {dict}))
+        or get_first(
+            post, ("video", "creation_story", "attachments", ..., "media", lambda k, v: k == "owner" and v["name"])
+        )
+        or get_first(post, (..., "video", lambda k, v: k == "owner" and v["name"]))
+        or get_first(post, ("node", "actors", ..., {dict}))
+        or get_first(post, ("event", "event_creator", {dict}))
+        or get_first(post, ("video", "creation_story", "short_form_video_context", "video_owner", {dict}))
+        or {}
+    )
+    uploader = uploader_data.get("name") or (
+        clean_html(get_element_by_id("fbPhotoPageAuthorName", webpage))
+        or self._search_regex(
+            (r'ownerName\s*:\s*"([^"]+)"', *self._og_regexes("title")), webpage, "uploader", fatal=False
+        )
+    )
+    timestamp = int_or_none(self._search_regex(r'<abbr[^>]+data-utime=["\'](\d+)', webpage, "timestamp", default=None))
+    thumbnail = self._html_search_meta(["og:image", "twitter:image"], webpage, "thumbnail", default=None)
+    # some webpages contain unretrievable thumbnail urls
+    # like https://lookaside.fbsbx.com/lookaside/crawler/media/?media_id=10155168902769113&get_thumbnail=1
+    # in https://www.facebook.com/yaroslav.korpan/videos/1417995061575415/
+    if thumbnail and not re.search(r"\.(?:jpg|png)", thumbnail):
+        thumbnail = None
+    info_dict = {
+        "description": description,
+        "uploader": uploader,
+        "uploader_id": uploader_data.get("id"),
+        "timestamp": timestamp,
+        "thumbnail": thumbnail,
+        "view_count": parse_count(
+            self._search_regex(
+                (r'\bviewCount\s*:\s*["\']([\d,.]+)', r'video_view_count["\']\s*:\s*(\d+)'),
+                webpage,
+                "view count",
+                default=None,
+            )
+        ),
+        "concurrent_view_count": get_first(
+            post, (("video", (..., ..., "attachments", ..., "media")), "liveViewerCount", {int_or_none})
+        ),
+        **traverse_obj(
+            post,
+            (
+                lambda _, v: video_id in v["url"],
+                "feedback",
+                {
+                    "like_count": ("likers", "count", {int}),
+                    "comment_count": ("total_comment_count", {int}),
+                    "repost_count": ("share_count_reduced", {parse_count}),
+                },
+            ),
+            get_all=False,
+        ),
+    }
+
+    info_json_ld = self._search_json_ld(webpage, video_id, default={})
+    info_json_ld["title"] = (
+        re.sub(r"\s*\|\s*Facebook$", "", title or info_json_ld.get("title") or page_title or "")
+        or (description or "").replace("\n", " ")
+        or f"Facebook video #{video_id}"
+    )
+    return merge_dicts(info_json_ld, info_dict)
 
 
 class Facebook(GenericDropin):
-    def extract_post(self, url: str, ie_instance):
-        video_id = ie_instance._match_valid_url(url).group('id')
-        ie_instance._download_webpage(
-            url.replace('://m.facebook.com/', '://www.facebook.com/'), video_id)
-        webpage = ie_instance._download_webpage(url, ie_instance._match_valid_url(url).group('id'))
+    def extract_post(self, url: str, ie_instance: FacebookIE):
+        post_id_regex = r"(?P<id>pfbid[A-Za-z0-9]+|\d+|t\.(\d+\/\d+))"
+        post_id = re.search(post_id_regex, url).group("id")
+        webpage = ie_instance._download_webpage(url.replace("://m.facebook.com/", "://www.facebook.com/"), post_id)
 
-        # TODO: fix once https://github.com/yt-dlp/yt-dlp/pull/12275 is merged
-        post_data = ie_instance._extract_metadata(webpage)
+        # TODO: For long posts, this _extract_metadata only seems to return the first 100 or so characters, followed by ...
+
+        # TODO: If/when https://github.com/yt-dlp/yt-dlp/pull/12275 is merged, uncomment next line and delete the one after
+        # post_data = ie_instance._extract_metadata(webpage, post_id)
+        post_data = _extract_metadata(ie_instance, webpage, post_id)
         return post_data
-    
-    def create_metadata(self, post: dict, ie_instance, archiver, url):
-        metadata = archiver.create_metadata(url)
-        metadata.set_title(post.get('title')).set_content(post.get('description')).set_post_data(post)
-        return metadata
+
+    def create_metadata(self, post: dict, ie_instance: FacebookIE, archiver, url):
+        result = Metadata()
+        result.set_content(post.get("description", ""))
+        result.set_title(post.get("title", ""))
+        result.set("author", post.get("uploader", ""))
+        result.set_url(url)
+        return result
+
+    def suitable(self, url, info_extractor: FacebookIE):
+        regex = r"(?:https?://(?:[\w-]+\.)?(?:facebook\.com||facebookwkhpilnemxj7asaniu7vnjjbiltxjqhye3mhbshg7kx5tfyd\.onion)/)"
+        return re.match(regex, url)
+
+    def skip_ytdlp_download(self, url: str, is_instance: FacebookIE):
+        """
+        Skip using the ytdlp download method for Facebook *photo* posts, they have a URL with an id of t.XXXXX/XXXXX
+        """
+        if re.search(r"/t.\d+/\d+", url):
+            return True

src/auto_archiver/modules/generic_extractor/generic_extractor.py

@@ -1,7 +1,13 @@
-import datetime, os
+import shutil
+import sys
+import datetime
+import os
 import importlib
 import subprocess
+import zipfile
+
 from typing import Generator, Type
+from urllib.request import urlretrieve
 
 import yt_dlp
 from yt_dlp.extractor.common import InfoExtractor
@@ -11,63 +17,175 @@ from loguru import logger
 
 from auto_archiver.core.extractor import Extractor
 from auto_archiver.core import Metadata, Media
+from auto_archiver.utils import get_datetime_from_str
+from .dropin import GenericDropin
+
+
+class SkipYtdlp(Exception):
+    pass
+
 
 class GenericExtractor(Extractor):
     _dropins = {}
 
     def setup(self):
-        # check for file .ytdlp-update in the secrets folder
+        self.check_for_extractor_updates()
+        self.setup_po_tokens()
+
+    def check_for_extractor_updates(self):
+        """Checks whether yt-dlp or its plugins need updating and triggers a restart if so."""
         if self.ytdlp_update_interval < 0:
             return
-        
-        use_secrets = os.path.exists('secrets')
-        path = os.path.join('secrets' if use_secrets else '', '.ytdlp-update')
-        next_update_check = None
-        if os.path.exists(path):
-            with open(path, "r") as f:
-                next_update_check = datetime.datetime.fromisoformat(f.read())
-        
-        if not next_update_check or next_update_check < datetime.datetime.now():
-            self.update_ytdlp()
 
-            next_update_check = datetime.datetime.now() + datetime.timedelta(days=self.ytdlp_update_interval)
-            with open(path, "w") as f:
-                f.write(next_update_check.isoformat())
+        update_file = os.path.join("secrets" if os.path.exists("secrets") else "", ".ytdlp-update")
+        next_check = None
+        if os.path.exists(update_file):
+            with open(update_file, "r") as f:
+                next_check = datetime.datetime.fromisoformat(f.read())
 
-    def update_ytdlp(self):
-        logger.info("Checking and updating yt-dlp...")
-        logger.info(f"Tip: change the 'ytdlp_update_interval' setting to control how often yt-dlp is updated. Set to -1 to disable or 0 to enable on every run. Current setting: {self.ytdlp_update_interval}")
-        from importlib.metadata import version as get_version
-        old_version = get_version("yt-dlp")
-        try:
-            # try and update with pip (this works inside poetry environment and in a normal virtualenv)
-            result = subprocess.run(["pip", "install", "--upgrade", "yt-dlp"], check=True, capture_output=True)
+        if next_check and next_check > datetime.datetime.now():
+            return
 
-            if "Successfully installed yt-dlp" in result.stdout.decode():
-                new_version = importlib.metadata.version("yt-dlp")
-                logger.info(f"yt-dlp successfully (from {old_version} to {new_version})")
-                importlib.reload(yt_dlp)
+        yt_dlp_updated = self.update_package("yt-dlp")
+        bgutil_updated = self.update_package("bgutil-ytdlp-pot-provider")
+
+        # Write the new timestamp
+        with open(update_file, "w") as f:
+            next_check = datetime.datetime.now() + datetime.timedelta(days=self.ytdlp_update_interval)
+            f.write(next_check.isoformat())
+
+        if yt_dlp_updated or bgutil_updated:
+            if os.environ.get("AUTO_ARCHIVER_ALLOW_RESTART", "1") != "1":
+                logger.warning("yt-dlp or plugin was updated — please restart auto-archiver manually")
             else:
-                logger.info("yt-dlp already up to date")
+                logger.warning("yt-dlp or plugin was updated — restarting auto-archiver")
+                logger.warning(" ======= RESTARTING ======= ")
+                os.execv(sys.executable, [sys.executable] + sys.argv)
+
+    def update_package(self, package_name: str) -> bool:
+        logger.info(f"Checking and updating {package_name}...")
+        from importlib.metadata import version as get_version
+
+        old_version = get_version(package_name)
+        try:
+            result = subprocess.run(["pip", "install", "--upgrade", package_name], check=True, capture_output=True)
+            if f"Successfully installed {package_name}" in result.stdout.decode():
+                new_version = importlib.metadata.version(package_name)
+                logger.info(f"{package_name} updated from {old_version} to {new_version}")
+                return True
+            logger.info(f"{package_name} already up to date")
+        except Exception as e:
+            logger.error(f"Error updating {package_name}: {e}")
+        return False
+
+    def setup_po_tokens(self) -> None:
+        """Setup Proof of Origin Token method conditionally.
+        Uses provider: https://github.com/Brainicism/bgutil-ytdlp-pot-provider.
+        """
+        in_docker = os.environ.get("RUNNING_IN_DOCKER")
+        if self.bguils_po_token_method == "disabled":
+            # This allows disabling of the PO Token generation script in the Docker implementation.
+            logger.warning("Proof of Origin Token generation is disabled.")
+            return
+
+        if self.bguils_po_token_method == "auto" and not in_docker:
+            logger.info(
+                "Proof of Origin Token method not explicitly set. "
+                "If you're running an external HTTP server separately, you can safely ignore this message. "
+                "To reduce the likelihood of bot detection, enable one of the methods described in the documentation: "
+                "https://auto-archiver.readthedocs.io/en/settings_page/installation/authentication.html#proof-of-origin-tokens"
+            )
+            return
+
+        # Either running in Docker, or "script" method is set beyond this point
+        self.setup_token_generation_script()
+
+    def setup_token_generation_script(self) -> None:
+        """This function sets up the Proof of Origin Token generation script method for
+        bgutil-ytdlp-pot-provider if enabled or in Docker."""
+        missing_tools = [tool for tool in ("node", "yarn", "npx") if shutil.which(tool) is None]
+        if missing_tools:
+            logger.error(
+                f"Cannot set up PO Token script; missing required tools: {', '.join(missing_tools)}. "
+                "Install these tools or run bgutils via Docker. "
+                "See: https://github.com/Brainicism/bgutil-ytdlp-pot-provider"
+            )
+            return
+        try:
+            from importlib.metadata import version as get_version
+
+            plugin_version = get_version("bgutil-ytdlp-pot-provider")
+            base_dir = os.path.expanduser("~/bgutil-ytdlp-pot-provider")
+            server_dir = os.path.join(base_dir, "server")
+            version_file = os.path.join(server_dir, ".VERSION")
+            transpiled_script = os.path.join(server_dir, "build", "generate_once.js")
+
+            # Skip setup if version is correct and transpiled script exists
+            if os.path.isfile(transpiled_script) and os.path.isfile(version_file):
+                with open(version_file) as vf:
+                    if vf.read().strip() == plugin_version:
+                        logger.info("PO Token script already set up and up to date.")
+            else:
+                # Remove an outdated directory and pull a new version
+                if os.path.exists(base_dir):
+                    shutil.rmtree(base_dir)
+                os.makedirs(base_dir, exist_ok=True)
+
+                zip_url = (
+                    f"https://github.com/Brainicism/bgutil-ytdlp-pot-provider/archive/refs/tags/{plugin_version}.zip"
+                )
+                zip_path = os.path.join(base_dir, f"{plugin_version}.zip")
+                logger.info(f"Downloading bgutils release zip for version {plugin_version}...")
+                urlretrieve(zip_url, zip_path)
+                with zipfile.ZipFile(zip_path, "r") as z:
+                    z.extractall(base_dir)
+                os.remove(zip_path)
+
+                extracted_root = os.path.join(base_dir, f"bgutil-ytdlp-pot-provider-{plugin_version}")
+                shutil.move(os.path.join(extracted_root, "server"), server_dir)
+                shutil.rmtree(extracted_root)
+                logger.info("Installing dependencies and transpiling PoT Generator script...")
+                subprocess.run(["yarn", "install", "--frozen-lockfile"], cwd=server_dir, check=True)
+                subprocess.run(["npx", "tsc"], cwd=server_dir, check=True)
+
+                with open(version_file, "w") as vf:
+                    vf.write(plugin_version)
+
+            script_path = os.path.join(server_dir, "build", "generate_once.js")
+            if not os.path.exists(script_path):
+                logger.error("generate_once.js not found after transpilation.")
+                return
+
+            self.extractor_args.setdefault("youtube", {})["getpot_bgutil_script"] = script_path
+            logger.info(f"PO Token script configured at: {script_path}")
 
         except Exception as e:
-            logger.error(f"Error updating yt-dlp: {e}")
+            logger.error(f"Failed to set up PO Token script: {e}")
 
     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():
-            if info_extractor.suitable(url) and info_extractor.working():
+            if not info_extractor.working():
+                continue
+
+            # check if there's a dropin and see if that declares whether it's suitable
+            dropin: GenericDropin = self.dropin_for_name(info_extractor.ie_key())
+            if dropin and dropin.suitable(url, info_extractor):
                 yield info_extractor
-        
+            elif info_extractor.suitable(url):
+                yield info_extractor
+
     def suitable(self, url: str) -> bool:
         """
         Checks for valid URLs out of all ytdlp extractors.
         Returns False for the GenericIE, which as labelled by yt-dlp: 'Generic downloader that works on some sites'
         """
         return any(self.suitable_extractors(url))
-    
-    def download_additional_media(self, video_data: dict, info_extractor: InfoExtractor, metadata: Metadata) -> Metadata:
+
+    def download_additional_media(
+        self, video_data: dict, info_extractor: InfoExtractor, metadata: Metadata
+    ) -> Metadata:
         """
         Downloads additional media like images, comments, subtitles, etc.
 
@@ -76,7 +194,7 @@ class GenericExtractor(Extractor):
 
         # Just get the main thumbnail. More thumbnails are available in
         # video_data['thumbnails'] should they be required
-        thumbnail_url = video_data.get('thumbnail')
+        thumbnail_url = video_data.get("thumbnail")
         if thumbnail_url:
             try:
                 cover_image_path = self.download_from_url(thumbnail_url)
@@ -99,15 +217,65 @@ class GenericExtractor(Extractor):
         Clean up the ytdlp generic video data to make it more readable and remove unnecessary keys that ytdlp adds
         """
 
-        base_keys = ['formats', 'thumbnail', 'display_id', 'epoch', 'requested_downloads',
-                     'duration_string', 'thumbnails', 'http_headers', 'webpage_url_basename', 'webpage_url_domain',
-                     'extractor', 'extractor_key', 'playlist', 'playlist_index', 'duration_string', 'protocol', 'requested_subtitles',
-                     'format_id', 'acodec', 'vcodec', 'ext', 'epoch', '_has_drm', 'filesize', 'audio_ext', 'video_ext', 'vbr', 'abr',
-                     'resolution', 'dynamic_range', 'aspect_ratio', 'cookies', 'format', 'quality', 'preference', 'artists',
-                     'channel_id', 'subtitles', 'tbr', 'url', 'original_url', 'automatic_captions', 'playable_in_embed', 'live_status',
-                     '_format_sort_fields', 'chapters', 'requested_formats', 'format_note',
-                     'audio_channels', 'asr', 'fps', 'was_live', 'is_live', 'heatmap', 'age_limit', 'stretched_ratio']
-        
+        base_keys = [
+            "formats",
+            "thumbnail",
+            "display_id",
+            "epoch",
+            "requested_downloads",
+            "duration_string",
+            "thumbnails",
+            "http_headers",
+            "webpage_url_basename",
+            "webpage_url_domain",
+            "extractor",
+            "extractor_key",
+            "playlist",
+            "playlist_index",
+            "duration_string",
+            "protocol",
+            "requested_subtitles",
+            "format_id",
+            "acodec",
+            "vcodec",
+            "ext",
+            "epoch",
+            "_has_drm",
+            "filesize",
+            "audio_ext",
+            "video_ext",
+            "vbr",
+            "abr",
+            "resolution",
+            "dynamic_range",
+            "aspect_ratio",
+            "cookies",
+            "format",
+            "quality",
+            "preference",
+            "artists",
+            "channel_id",
+            "subtitles",
+            "tbr",
+            "url",
+            "original_url",
+            "automatic_captions",
+            "playable_in_embed",
+            "live_status",
+            "_format_sort_fields",
+            "chapters",
+            "requested_formats",
+            "format_note",
+            "audio_channels",
+            "asr",
+            "fps",
+            "was_live",
+            "is_live",
+            "heatmap",
+            "age_limit",
+            "stretched_ratio",
+        ]
+
         dropin = self.dropin_for_name(info_extractor.ie_key())
         if dropin:
             try:
@@ -116,8 +284,8 @@ class GenericExtractor(Extractor):
                 pass
 
         return base_keys
-    
-    def add_metadata(self, video_data: dict, info_extractor: InfoExtractor, url:str, result: Metadata) -> Metadata:
+
+    def add_metadata(self, video_data: dict, info_extractor: InfoExtractor, url: str, result: Metadata) -> Metadata:
         """
         Creates a Metadata object from the given video_data
         """
@@ -126,29 +294,43 @@ class GenericExtractor(Extractor):
         result = self.download_additional_media(video_data, info_extractor, result)
 
         # keep both 'title' and 'fulltitle', but prefer 'title', falling back to 'fulltitle' if it doesn't exist
-        result.set_title(video_data.pop('title', video_data.pop('fulltitle', "")))
-        result.set_url(url)
-        if "description" in video_data: result.set_content(video_data["description"])
+        if not result.get_title():
+            result.set_title(video_data.pop("title", video_data.pop("fulltitle", "")))
+
+        if not result.get("url"):
+            result.set_url(url)
+
+        if "description" in video_data and not result.get("content"):
+            result.set_content(video_data["description"])
         # extract comments if enabled
         if self.comments:
-            result.set("comments", [{
-                "text": c["text"],
-                "author": c["author"], 
-                "timestamp": datetime.datetime.fromtimestamp(c.get("timestamp"), tz = datetime.timezone.utc)
-            } for c in video_data.get("comments", [])])
+            result.set(
+                "comments",
+                [
+                    {
+                        "text": c["text"],
+                        "author": c["author"],
+                        "timestamp": datetime.datetime.fromtimestamp(c.get("timestamp"), tz=datetime.timezone.utc),
+                    }
+                    for c in video_data.get("comments", [])
+                ],
+            )
 
         # then add the common metadata
-        if timestamp := video_data.pop("timestamp", None):
-            timestamp = datetime.datetime.fromtimestamp(timestamp, tz = datetime.timezone.utc).isoformat()
+        timestamp = video_data.pop("timestamp", None)
+        if timestamp and not result.get("timestamp"):
+            timestamp = datetime.datetime.fromtimestamp(timestamp, tz=datetime.timezone.utc).isoformat()
             result.set_timestamp(timestamp)
-        if upload_date := video_data.pop("upload_date", None):
-            upload_date = datetime.datetime.strptime(upload_date, '%Y%m%d').replace(tzinfo=datetime.timezone.utc)
+
+        upload_date = video_data.pop("upload_date", None)
+        if upload_date and not result.get("upload_date"):
+            upload_date = get_datetime_from_str(upload_date, "%Y%m%d").replace(tzinfo=datetime.timezone.utc)
             result.set("upload_date", upload_date)
-        
+
         # then clean away any keys we don't want
         for clean_key in self.keys_to_clean(info_extractor, video_data):
             video_data.pop(clean_key, None)
-        
+
         # then add the rest of the video data
         for k, v in video_data.items():
             if v:
@@ -166,25 +348,28 @@ class GenericExtractor(Extractor):
 
         if not dropin:
             # TODO: add a proper link to 'how to create your own dropin'
-            logger.debug(f"""Could not find valid dropin for {info_extractor.IE_NAME}.
+            logger.debug(f"""Could not find valid dropin for {info_extractor.ie_key()}.
                      Why not try creating your own, and make sure it has a valid function called 'create_metadata'. Learn more: https://auto-archiver.readthedocs.io/en/latest/user_guidelines.html#""")
             return False
-        
+
         post_data = dropin.extract_post(url, ie_instance)
-        return dropin.create_metadata(post_data, ie_instance, self, url)
-
-    def get_metadata_for_video(self, data: dict, info_extractor: Type[InfoExtractor], url: str, ydl: yt_dlp.YoutubeDL) -> Metadata:
+        result = dropin.create_metadata(post_data, ie_instance, self, url)
+        return self.add_metadata(post_data, info_extractor, url, result)
 
+    def get_metadata_for_video(
+        self, data: dict, info_extractor: Type[InfoExtractor], url: str, ydl: yt_dlp.YoutubeDL
+    ) -> Metadata:
         # this time download
-        ydl.params['getcomments'] = self.comments
-        #TODO: for playlist or long lists of videos, how to download one at a time so they can be stored before the next one is downloaded?
+        ydl.params["getcomments"] = self.comments
+        # TODO: for playlist or long lists of videos, how to download one at a time so they can be stored before the next one is downloaded?
         data = ydl.extract_info(url, ie_key=info_extractor.ie_key(), download=True)
         if "entries" in data:
             entries = data.get("entries", [])
             if not len(entries):
-                logger.warning('YoutubeDLArchiver could not find any video')
+                logger.warning("YoutubeDLArchiver could not find any video")
                 return False
-        else: entries = [data]
+        else:
+            entries = [data]
 
         result = Metadata()
 
@@ -192,17 +377,18 @@ class GenericExtractor(Extractor):
             try:
                 filename = ydl.prepare_filename(entry)
                 if not os.path.exists(filename):
-                    filename = filename.split('.')[0] + '.mkv'
+                    filename = filename.split(".")[0] + ".mkv"
 
                 new_media = Media(filename)
                 for x in ["duration", "original_url", "fulltitle", "description", "upload_date"]:
-                    if x in entry: new_media.set(x, entry[x])
+                    if x in entry:
+                        new_media.set(x, entry[x])
 
                 # read text from subtitles if enabled
                 if self.subtitles:
-                    for lang, val in (data.get('requested_subtitles') or {}).items():
-                        try:    
-                            subs = pysubs2.load(val.get('filepath'), encoding="utf-8")
+                    for lang, val in (data.get("requested_subtitles") or {}).items():
+                        try:
+                            subs = pysubs2.load(val.get("filepath"), encoding="utf-8")
                             text = " ".join([line.text for line in subs])
                             new_media.set(f"subtitles_{lang}", text)
                         except Exception as e:
@@ -212,8 +398,8 @@ class GenericExtractor(Extractor):
                 logger.error(f"Error processing entry {entry}: {e}")
 
         return self.add_metadata(data, info_extractor, url, result)
-    
-    def dropin_for_name(self, dropin_name: str, additional_paths = [], package=__package__) -> Type[InfoExtractor]:
+
+    def dropin_for_name(self, dropin_name: str, additional_paths=[], package=__package__) -> GenericDropin:
         dropin_name = dropin_name.lower()
 
         if dropin_name == "generic":
@@ -221,8 +407,10 @@ class GenericExtractor(Extractor):
             return None
 
         dropin_class_name = dropin_name.title()
+
         def _load_dropin(dropin):
             dropin_class = getattr(dropin, dropin_class_name)()
+            dropin.extractor = self
             return self._dropins.setdefault(dropin_name, dropin_class)
 
         try:
@@ -244,7 +432,7 @@ class GenericExtractor(Extractor):
                 return _load_dropin(dropin)
             except (FileNotFoundError, ModuleNotFoundError):
                 pass
-        
+
         # fallback to loading the dropins within auto-archiver
         try:
             return _load_dropin(importlib.import_module(f".{dropin_name}", package=package))
@@ -256,43 +444,53 @@ class GenericExtractor(Extractor):
     def download_for_extractor(self, info_extractor: InfoExtractor, url: str, ydl: yt_dlp.YoutubeDL) -> Metadata:
         """
         Tries to download the given url using the specified extractor
-        
+
         It first tries to use ytdlp directly to download the video. If the post is not a video, it will then try to
         use the extractor's _extract_post method to get the post metadata if possible.
         """
         # when getting info without download, we also don't need the comments
-        ydl.params['getcomments'] = False
+        ydl.params["getcomments"] = False
         result = False
 
         dropin_submodule = self.dropin_for_name(info_extractor.ie_key())
 
         try:
-            if dropin_submodule and dropin_submodule.skip_ytdlp_download(info_extractor, url):
-                raise Exception(f"Skipping using ytdlp to download files for {info_extractor.ie_key()}")
+            if dropin_submodule and dropin_submodule.skip_ytdlp_download(url, info_extractor):
+                logger.debug(f"Skipping using ytdlp to download files for {info_extractor.ie_key()}")
+                raise SkipYtdlp()
 
             # don't download since it can be a live stream
             data = ydl.extract_info(url, ie_key=info_extractor.ie_key(), download=False)
-            if data.get('is_live', False) and not self.livestreams:
+            if data.get("is_live", False) and not self.livestreams:
                 logger.warning("Livestream detected, skipping due to 'livestreams' configuration setting")
                 return False
             # it's a valid video, that the youtubdedl can download out of the box
             result = self.get_metadata_for_video(data, info_extractor, url, ydl)
 
         except Exception as e:
-            if info_extractor.ie_key() == "generic":
+            if info_extractor.IE_NAME == "generic":
                 # don't clutter the logs with issues about the 'generic' extractor not having a dropin
                 return False
 
-            logger.debug(f'Issue using "{info_extractor.IE_NAME}" extractor to download video (error: {repr(e)}), attempting to use extractor to get post data instead')
+            if not isinstance(e, SkipYtdlp):
+                logger.debug(
+                    f'Issue using "{info_extractor.IE_NAME}" extractor to download video (error: {repr(e)}), attempting to use dropin to get post data instead'
+                )
+
             try:
                 result = self.get_metadata_for_post(info_extractor, url, ydl)
             except (yt_dlp.utils.DownloadError, yt_dlp.utils.ExtractorError) as post_e:
-                logger.error(f'Error downloading metadata for post: {post_e}')
+                logger.error("Error downloading metadata for post: {error}", error=str(post_e))
                 return False
             except Exception as generic_e:
-                logger.debug(f'Attempt to extract using ytdlp extractor "{info_extractor.IE_NAME}" failed:  \n  {repr(generic_e)}', exc_info=True)
+                logger.debug(
+                    'Attempt to extract using ytdlp extractor "{name}" failed:  \n  {error}',
+                    name=info_extractor.IE_NAME,
+                    error=str(generic_e),
+                    exc_info=True,
+                )
                 return False
-        
+
         if result:
             extractor_name = "yt-dlp"
             if info_extractor:
@@ -308,43 +506,70 @@ 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
+        # 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 = [
+            "-o",
+            os.path.join(self.tmp_dir, "%(id)s.%(ext)s"),
+            "--quiet",
+            "--no-playlist" if not self.allow_playlist else "--yes-playlist",
+            "--write-subs" if self.subtitles else "--no-write-subs",
+            "--write-auto-subs" if self.subtitles else "--no-write-auto-subs",
+            "--live-from-start" if self.live_from_start else "--no-live-from-start",
+        ]
+
+        # proxy handling
+        if self.proxy:
+            ydl_options.extend(["--proxy", self.proxy])
+
+        # max_downloads handling
+        if self.max_downloads != "inf":
+            ydl_options.extend(["--max-downloads", str(self.max_downloads)])
+            ydl_options.extend(["--playlist-end", str(self.max_downloads)])
 
-        ydl_options = {'outtmpl': os.path.join(self.tmp_dir, f'%(id)s.%(ext)s'), 
-                       'quiet': False, 'noplaylist': not self.allow_playlist ,
-                       'writesubtitles': self.subtitles,'writeautomaticsub': self.subtitles,
-                       "live_from_start": self.live_from_start, "proxy": self.proxy,
-                       "max_downloads": self.max_downloads, "playlistend": self.max_downloads}
-        
         # set up auth
         auth = self.auth_for_site(url, extract_cookies=False)
-
-        # order of importance: username/pasword -> api_key -> cookie -> cookies_from_browser -> cookies_file
+        # order of importance: username/password -> 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}')
-                ydl_options['username'] = auth['username']
-                ydl_options['password'] = auth['password']
-            elif 'cookie' in auth:
-                logger.debug(f'Using provided auth cookie for {url}')
-                yt_dlp.utils.std_headers['cookie'] = auth['cookie']
-            elif 'cookies_from_browser' in auth:
-                logger.debug(f'Using extracted cookies from browser {auth["cookies_from_browser"]} for {url}')
-                ydl_options['cookiesfrombrowser'] = auth['cookies_from_browser']
-            elif 'cookies_file' in auth:
-                logger.debug(f'Using cookies from file {auth["cookies_file"]} for {url}')
-                ydl_options['cookiefile'] = auth['cookies_file']
+            if "username" in auth and "password" in auth:
+                logger.debug(f"Using provided auth username and password for {url}")
+                ydl_options.extend(("--username", auth["username"]))
+                ydl_options.extend(("--password", auth["password"]))
+            elif "cookie" in auth:
+                logger.debug(f"Using provided auth cookie for {url}")
+                yt_dlp.utils.std_headers["cookie"] = auth["cookie"]
+            elif "cookies_from_browser" in auth:
+                logger.debug(f"Using extracted cookies from browser {auth['cookies_from_browser']} for {url}")
+                ydl_options.extend(("--cookies-from-browser", auth["cookies_from_browser"]))
+            elif "cookies_file" in auth:
+                logger.debug(f"Using cookies from file {auth['cookies_file']} for {url}")
+                ydl_options.extend(("--cookies", auth["cookies_file"]))
 
-        ydl = yt_dlp.YoutubeDL(ydl_options) # allsubtitles and subtitleslangs not working as expected, so default lang is always "en"
+        # Applying user-defined extractor_args
+        if self.extractor_args:
+            for key, args in self.extractor_args.items():
+                logger.debug(f"Setting extractor_args: {key}")
+                if isinstance(args, dict):
+                    arg_str = ";".join(f"{k}={v}" for k, v in args.items())
+                else:
+                    arg_str = str(args)
+                ydl_options.extend(["--extractor-args", f"{key}:{arg_str}"])
+
+        if self.ytdlp_args:
+            logger.debug("Adding additional ytdlp arguments: {self.ytdlp_args}")
+            ydl_options += self.ytdlp_args.split(" ")
+
+        *_, validated_options = yt_dlp.parse_options(ydl_options)
+        ydl = yt_dlp.YoutubeDL(
+            validated_options
+        )  # allsubtitles and subtitleslangs not working as expected, so default lang is always "en"
 
         for info_extractor in self.suitable_extractors(url):
             result = self.download_for_extractor(info_extractor, url, ydl)
             if result:
                 return result
 
-
         return False

src/auto_archiver/modules/generic_extractor/tiktok.py

@@ -0,0 +1,83 @@
+import requests
+from loguru import logger
+
+from yt_dlp.extractor.tiktok import TikTokIE, TikTokLiveIE, TikTokVMIE, TikTokUserIE
+
+from auto_archiver.core import Metadata, Media
+from datetime import datetime, timezone
+from .dropin import GenericDropin
+
+
+class Tiktok(GenericDropin):
+    """
+    TikTok droping for the Generic Extractor that uses an unofficial API if/when ytdlp fails.
+    It's useful for capturing content that requires a login, like sensitive content.
+    """
+
+    TIKWM_ENDPOINT = "https://www.tikwm.com/api/?url={url}"
+
+    def suitable(self, url, info_extractor) -> bool:
+        """This dropin (which uses Tikvm) is suitable for *all* Tiktok type URLs - videos, lives, VMs, and users.
+        Return the 'suitable' method from the TikTokIE class."""
+        return any(extractor().suitable(url) for extractor in (TikTokIE, TikTokLiveIE, TikTokVMIE, TikTokUserIE))
+
+    def extract_post(self, url: str, ie_instance):
+        logger.debug(f"Using Tikwm API to attempt to download tiktok video from {url=}")
+
+        endpoint = self.TIKWM_ENDPOINT.format(url=url)
+
+        r = requests.get(endpoint)
+        if r.status_code != 200:
+            raise ValueError(f"unexpected status code '{r.status_code}' from tikwm.com for {url=}:")
+
+        try:
+            json_response = r.json()
+        except ValueError:
+            raise ValueError(f"failed to parse JSON response from tikwm.com for {url=}")
+
+        if not json_response.get("msg") == "success" or not (api_data := json_response.get("data", {})):
+            raise ValueError(f"failed to get a valid response from tikwm.com for {url=}: {repr(json_response)}")
+
+        # tries to get the non-watermarked version first
+        video_url = api_data.pop("play", api_data.pop("wmplay", None))
+        if not video_url:
+            raise ValueError(f"no valid video URL found in response from tikwm.com for {url=}")
+
+        api_data["video_url"] = video_url
+        return api_data
+
+    def keys_to_clean(self, video_data: dict, info_extractor):
+        return ["video_url", "title", "create_time", "author", "cover", "origin_cover", "ai_dynamic_cover", "duration"]
+
+    def create_metadata(self, post: dict, ie_instance, archiver, url):
+        # prepare result, start by downloading video
+        result = Metadata()
+        video_url = post.pop("video_url")
+
+        # get the cover if possible
+        cover_url = post.pop("origin_cover", post.pop("cover", post.pop("ai_dynamic_cover", None)))
+        if cover_url and (cover_downloaded := archiver.download_from_url(cover_url)):
+            result.add_media(Media(cover_downloaded))
+
+        # get the video or fail
+        video_downloaded = archiver.download_from_url(video_url, f"vid_{post.get('id', '')}")
+        if not video_downloaded:
+            logger.error(f"failed to download video from {video_url}")
+            return False
+        video_media = Media(video_downloaded)
+        if duration := post.get("duration", None):
+            video_media.set("duration", duration)
+        result.add_media(video_media)
+
+        # add remaining metadata
+        result.set_title(post.get("title", ""))
+
+        if created_at := post.get("create_time", None):
+            result.set_timestamp(datetime.fromtimestamp(created_at, tz=timezone.utc))
+
+        if author := post.get("author", None):
+            result.set("author", author)
+
+        result.set("api_data", post)
+
+        return result

src/auto_archiver/modules/generic_extractor/truth.py

@@ -9,11 +9,11 @@ from dateutil.parser import parse as parse_dt
 
 from .dropin import GenericDropin
 
-class Truth(GenericDropin):
 
+class Truth(GenericDropin):
     def extract_post(self, url, ie_instance: InfoExtractor) -> dict:
         video_id = ie_instance._match_id(url)
-        truthsocial_url = f'https://truthsocial.com/api/v1/statuses/{video_id}'
+        truthsocial_url = f"https://truthsocial.com/api/v1/statuses/{video_id}"
         return ie_instance._download_json(truthsocial_url, video_id)
 
     def skip_ytdlp_download(self, url, ie_instance: Type[InfoExtractor]) -> bool:
@@ -22,31 +22,42 @@ class Truth(GenericDropin):
     def create_metadata(self, post: dict, ie_instance: InfoExtractor, archiver: Extractor, url: str) -> Metadata:
         """
         Creates metadata from a truth social post
-        
+
         Only used for posts that contain no media. ytdlp.TruthIE extractor can handle posts with media
-        
+
         Format is:
-        
+
         {'id': '109598702184774628', 'created_at': '2022-12-29T19:51:18.161Z', 'in_reply_to_id': None, 'quote_id': None, 'in_reply_to_account_id': None, 'sensitive': False, 'spoiler_text': '', 'visibility': 'public', 'language': 'en', 'uri': 'https://truthsocial.com/@bbcnewa/109598702184774628', 'url': 'https://truthsocial.com/@bbcnewa/109598702184774628', 'content': '<p>Pele, regarded by many as football\'s greatest ever player, has died in Brazil at the age of 82. <a href="https://www.bbc.com/sport/football/42751517" rel="nofollow noopener noreferrer" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">bbc.com/sport/football/4275151</span><span class="invisible">7</span></a></p>', 'account': {'id': '107905163010312793', 'username': 'bbcnewa', 'acct': 'bbcnewa', 'display_name': 'BBC News', 'locked': False, 'bot': False, 'discoverable': True, 'group': False, 'created_at': '2022-03-05T17:42:01.159Z', 'note': '<p>News, features and analysis by the BBC</p>', 'url': 'https://truthsocial.com/@bbcnewa', 'avatar': 'https://static-assets-1.truthsocial.com/tmtg:prime-ts-assets/accounts/avatars/107/905/163/010/312/793/original/e7c07550dc22c23a.jpeg', 'avatar_static': 'https://static-assets-1.truthsocial.com/tmtg:prime-ts-assets/accounts/avatars/107/905/163/010/312/793/original/e7c07550dc22c23a.jpeg', 'header': 'https://static-assets-1.truthsocial.com/tmtg:prime-ts-assets/accounts/headers/107/905/163/010/312/793/original/a00eeec2b57206c7.jpeg', 'header_static': 'https://static-assets-1.truthsocial.com/tmtg:prime-ts-assets/accounts/headers/107/905/163/010/312/793/original/a00eeec2b57206c7.jpeg', 'followers_count': 1131, 'following_count': 3, 'statuses_count': 9, 'last_status_at': '2024-11-12', 'verified': False, 'location': '', 'website': 'https://www.bbc.com/news', 'unauth_visibility': True, 'chats_onboarded': True, 'feeds_onboarded': True, 'accepting_messages': False, 'show_nonmember_group_statuses': None, 'emojis': [], 'fields': [], 'tv_onboarded': True, 'tv_account': False}, 'media_attachments': [], 'mentions': [], 'tags': [], 'card': None, 'group': None, 'quote': None, 'in_reply_to': None, 'reblog': None, 'sponsored': False, 'replies_count': 1, 'reblogs_count': 0, 'favourites_count': 2, 'favourited': False, 'reblogged': False, 'muted': False, 'pinned': False, 'bookmarked': False, 'poll': None, 'emojis': []}
         """
 
         result = Metadata()
         result.set_url(url)
-        timestamp = post['created_at'] # format is 2022-12-29T19:51:18.161Z
+        timestamp = post["created_at"]  # format is 2022-12-29T19:51:18.161Z
         result.set_timestamp(parse_dt(timestamp))
-        result.set('description', post['content'])
-        result.set('author', post['account']['username'])
+        result.set("description", post["content"])
+        result.set("author", post["account"]["username"])
 
-        for key in ['replies_count', 'reblogs_count', 'favourites_count', ('account', 'followers_count'), ('account', 'following_count'), ('account', 'statuses_count'), ('account', 'display_name'), 'language', 'in_reply_to_account', 'replies_count']:
+        for key in [
+            "replies_count",
+            "reblogs_count",
+            "favourites_count",
+            ("account", "followers_count"),
+            ("account", "following_count"),
+            ("account", "statuses_count"),
+            ("account", "display_name"),
+            "language",
+            "in_reply_to_account",
+            "replies_count",
+        ]:
             if isinstance(key, tuple):
                 store_key = " ".join(key)
             else:
                 store_key = key
             result.set(store_key, traverse_obj(post, key))
-        
-        # add the media
-        for media in post.get('media_attachments', []):
-            filename = archiver.download_from_url(media['url'])
-            result.add_media(Media(filename), id=media.get('id'))
 
-        return result
+        # add the media
+        for media in post.get("media_attachments", []):
+            filename = archiver.download_from_url(media["url"])
+            result.add_media(Media(filename), id=media.get("id"))
+
+        return result

src/auto_archiver/modules/generic_extractor/twitter.py

@@ -1,18 +1,17 @@
-import re, mimetypes, json
-from datetime import datetime
+import re
+import mimetypes
 
 from loguru import logger
 from slugify import slugify
 
 from auto_archiver.core.metadata import Metadata, Media
-from auto_archiver.utils import url as UrlUtil
+from auto_archiver.utils import url as UrlUtil, get_datetime_from_str
 from auto_archiver.core.extractor import Extractor
 
 from .dropin import GenericDropin, InfoExtractor
 
+
 class Twitter(GenericDropin):
-
-
     def choose_variant(self, variants):
         # choosing the highest quality possible
         variant, width, height = None, 0, 0
@@ -27,44 +26,48 @@ class Twitter(GenericDropin):
             else:
                 variant = var if not variant else variant
         return variant
-    
+
     def extract_post(self, url: str, ie_instance: InfoExtractor):
-        twid = ie_instance._match_valid_url(url).group('id')
+        twid = ie_instance._match_valid_url(url).group("id")
         return ie_instance._extract_status(twid=twid)
 
+    def keys_to_clean(self, video_data, info_extractor):
+        return ["user", "created_at", "entities", "favorited", "translator_type"]
+
     def create_metadata(self, tweet: dict, ie_instance: InfoExtractor, archiver: Extractor, url: str) -> Metadata:
         result = Metadata()
         try:
             if not tweet.get("user") or not tweet.get("created_at"):
-                raise ValueError(f"Error retreiving post. Are you sure it exists?")
-            timestamp = datetime.strptime(tweet["created_at"], "%a %b %d %H:%M:%S %z %Y")
+                raise ValueError("Error retreiving post. Are you sure it exists?")
+            timestamp = get_datetime_from_str(tweet["created_at"], "%a %b %d %H:%M:%S %z %Y")
         except (ValueError, KeyError) as ex:
             logger.warning(f"Unable to parse tweet: {str(ex)}\nRetreived tweet data: {tweet}")
             return False
-                
-        result\
-            .set_title(tweet.get('full_text', ''))\
-            .set_content(json.dumps(tweet, ensure_ascii=False))\
-            .set_timestamp(timestamp)
+
+        full_text = tweet.pop("full_text", "")
+        author = tweet["user"].get("name", "")
+        result.set("author", author).set_url(url)
+
+        result.set_title(f"{author} - {full_text}").set_content(full_text).set_timestamp(timestamp)
         if not tweet.get("entities", {}).get("media"):
-            logger.debug('No media found, archiving tweet text only')
+            logger.debug("No media found, archiving tweet text only")
             result.status = "twitter-ytdl"
             return result
         for i, tw_media in enumerate(tweet["entities"]["media"]):
             media = Media(filename="")
             mimetype = ""
             if tw_media["type"] == "photo":
-                media.set("src", UrlUtil.twitter_best_quality_url(tw_media['media_url_https']))
+                media.set("src", UrlUtil.twitter_best_quality_url(tw_media["media_url_https"]))
                 mimetype = "image/jpeg"
             elif tw_media["type"] == "video":
-                variant = self.choose_variant(tw_media['video_info']['variants'])
-                media.set("src", variant['url'])
-                mimetype = variant['content_type']
+                variant = self.choose_variant(tw_media["video_info"]["variants"])
+                media.set("src", variant["url"])
+                mimetype = variant["content_type"]
             elif tw_media["type"] == "animated_gif":
-                variant = tw_media['video_info']['variants'][0]
-                media.set("src", variant['url'])
-                mimetype = variant['content_type']
+                variant = tw_media["video_info"]["variants"][0]
+                media.set("src", variant["url"])
+                mimetype = variant["content_type"]
             ext = mimetypes.guess_extension(mimetype)
-            media.filename = archiver.download_from_url(media.get("src"), f'{slugify(url)}_{i}{ext}')
+            media.filename = archiver.download_from_url(media.get("src"), f"{slugify(url)}_{i}{ext}")
             result.add_media(media)
-        return result
+        return result

src/auto_archiver/modules/gsheet_feeder_db/__init__.py

@@ -1,2 +1,2 @@
 from .gworksheet import GWorksheet
-from .gsheet_feeder_db import GsheetsFeederDB
+from .gsheet_feeder_db import GsheetsFeederDB

src/auto_archiver/modules/gsheet_feeder_db/__manifest__.py

@@ -12,9 +12,7 @@
             "default": None,
             "help": "the id of the sheet to archive (alternative to 'sheet' config)",
         },
-        "header": {"default": 1,
-                   "type": "int",
-                   "help": "index of the header row (starts at 1)", "type": "int"},
+        "header": {"default": 1, "help": "index of the header row (starts at 1)", "type": "int"},
         "service_account": {
             "default": "secrets/service_account.json",
             "help": "service account JSON file path. Learn how to create one: https://gspread.readthedocs.io/en/latest/oauth2.html",
@@ -53,19 +51,6 @@
             "help": "if True the stored files path will include 'workbook_name/worksheet_name/...'",
             "type": "bool",
         },
-        "allow_worksheets": {
-            "default": set(),
-            "help": "(CSV) only worksheets whose name is included in allow are included (overrides worksheet_block), leave empty so all are allowed",
-        },
-        "block_worksheets": {
-            "default": set(),
-            "help": "(CSV) explicitly block some worksheets from being processed",
-        },
-        "use_sheet_names_in_stored_paths": {
-            "default": True,
-            "type": "bool",
-            "help": "if True the stored files path will include 'workbook_name/worksheet_name/...'",
-        }
     },
     "description": """
     GsheetsFeederDatabase
@@ -85,10 +70,14 @@
     - Skips redundant updates for empty or invalid data fields.
 
     ### Setup
-    - Requires a Google Service Account JSON file for authentication, which should be stored in `secrets/gsheets_service_account.json`.
-    To set up a service account, follow the instructions [here](https://gspread.readthedocs.io/en/latest/oauth2.html).
-    - Define the `sheet` or `sheet_id` configuration to specify the sheet to archive.
-    - Customize the column names in your Google sheet using the `columns` configuration.
-    - The Google Sheet can be used soley as a feeder or as a feeder and database, but note you can't currently feed into the database from an alternate feeder.
+    1. Requires a Google Service Account JSON file for authentication.
+    To set up a service account, follow the instructions in the [how to](https://auto-archiver.readthedocs.io/en/latest/how_to/gsheets_setup.html),
+    or use the script:
+    ```
+    /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/bellingcat/auto-archiver/refs/heads/main/scripts/generate_google_services.sh)"
+    ```
+    2. Create a Google sheet with the required column(s) and then define the `sheet` or `sheet_id` configuration to specify this sheet.
+    3. Customize the column names in your Google sheet using the `columns` configuration.
+    4. The Google Sheet can be used solely as a feeder or as a feeder and database, but note you can't currently feed into the database from an alternate feeder.
     """,
 }

src/auto_archiver/modules/gsheet_feeder_db/gsheet_feeder_db.py

@@ -8,6 +8,7 @@ The filtered rows are processed into `Metadata` objects.
 - validates the sheet's structure and filters rows based on input configurations.
 - Ensures only rows with valid URLs and unprocessed statuses are included.
 """
+
 import os
 from typing import Tuple, Union
 from urllib.parse import quote
@@ -19,11 +20,10 @@ from slugify import slugify
 from auto_archiver.core import Feeder, Database, Media
 from auto_archiver.core import Metadata
 from auto_archiver.modules.gsheet_feeder_db import GWorksheet
-from auto_archiver.utils.misc import calculate_file_hash, get_current_timestamp
+from auto_archiver.utils.misc import get_current_timestamp
 
 
 class GsheetsFeederDB(Feeder, Database):
-
     def setup(self) -> None:
         self.gsheets_client = gspread.service_account(filename=self.service_account)
         # TODO mv to validators
@@ -42,24 +42,28 @@ class GsheetsFeederDB(Feeder, Database):
             if not self.should_process_sheet(worksheet.title):
                 logger.debug(f"SKIPPED worksheet '{worksheet.title}' due to allow/block rules")
                 continue
-            logger.info(f'Opening worksheet {ii=}: {worksheet.title=} header={self.header}')
+            logger.info(f"Opening worksheet {ii=}: {worksheet.title=} header={self.header}")
             gw = GWorksheet(worksheet, header_row=self.header, columns=self.columns)
             if len(missing_cols := self.missing_required_columns(gw)):
-                logger.warning(f"SKIPPED worksheet '{worksheet.title}' due to missing required column(s) for {missing_cols}")
+                logger.warning(
+                    f"SKIPPED worksheet '{worksheet.title}' due to missing required column(s) for {missing_cols}"
+                )
                 continue
 
             # process and yield metadata here:
             yield from self._process_rows(gw)
-            logger.success(f'Finished worksheet {worksheet.title}')
+            logger.success(f"Finished worksheet {worksheet.title}")
 
     def _process_rows(self, gw: GWorksheet):
         for row in range(1 + self.header, gw.count_rows() + 1):
-            url = gw.get_cell(row, 'url').strip()
-            if not len(url): continue
-            original_status = gw.get_cell(row, 'status')
-            status = gw.get_cell(row, 'status', fresh=original_status in ['', None])
+            url = gw.get_cell(row, "url").strip()
+            if not len(url):
+                continue
+            original_status = gw.get_cell(row, "status")
+            status = gw.get_cell(row, "status", fresh=original_status in ["", None])
             # TODO: custom status parser(?) aka should_retry_from_status
-            if status not in ['', None]: continue
+            if status not in ["", None]:
+                continue
 
             # All checks done - archival process starts here
             m = Metadata().set_url(url)
@@ -70,10 +74,10 @@ class GsheetsFeederDB(Feeder, Database):
         # TODO: Check folder value not being recognised
         m.set_context("gsheet", {"row": row, "worksheet": gw})
 
-        if gw.get_cell_or_default(row, 'folder', "") is None:
-            folder = ''
+        if gw.get_cell_or_default(row, "folder", "") is None:
+            folder = ""
         else:
-            folder = slugify(gw.get_cell_or_default(row, 'folder', "").strip())
+            folder = slugify(gw.get_cell_or_default(row, "folder", "").strip())
         if len(folder):
             if self.use_sheet_names_in_stored_paths:
                 m.set_context("folder", os.path.join(folder, slugify(self.sheet), slugify(gw.wks.title)))
@@ -84,19 +88,15 @@ class GsheetsFeederDB(Feeder, Database):
         if len(self.allow_worksheets) and sheet_name not in self.allow_worksheets:
             # ALLOW rules exist AND sheet name not explicitly allowed
             return False
-        if len(self.block_worksheets) and sheet_name in self.block_worksheets:
-            # BLOCK rules exist AND sheet name is blocked
-            return False
-        return True
+        return not (self.block_worksheets and sheet_name in self.block_worksheets)
 
     def missing_required_columns(self, gw: GWorksheet) -> list:
         missing = []
-        for required_col in ['url', 'status']:
+        for required_col in ["url", "status"]:
             if not gw.col_exists(required_col):
                 missing.append(required_col)
         return missing
 
-
     def started(self, item: Metadata) -> None:
         logger.warning(f"STARTED {item}")
         gw, row = self._retrieve_gsheet(item)
@@ -155,14 +155,11 @@ class GsheetsFeederDB(Feeder, Database):
         if len(pdq_hashes):
             batch_if_valid("pdq_hash", ",".join(pdq_hashes))
 
-        if (screenshot := item.get_media_by_id("screenshot")) and hasattr(
-            screenshot, "urls"
-        ):
+        if (screenshot := item.get_media_by_id("screenshot")) and hasattr(screenshot, "urls"):
             batch_if_valid("screenshot", "\n".join(screenshot.urls))
 
-        if thumbnail := item.get_first_image("thumbnail"):
-            if hasattr(thumbnail, "urls"):
-                batch_if_valid("thumbnail", f'=IMAGE("{thumbnail.urls[0]}")')
+        if (thumbnail := item.get_first_image("thumbnail")) and hasattr(thumbnail, "urls"):
+            batch_if_valid("thumbnail", f'=IMAGE("{thumbnail.urls[0]}")')
 
         if browsertrix := item.get_media_by_id("browsertrix"):
             batch_if_valid("wacz", "\n".join(browsertrix.urls))
@@ -186,11 +183,12 @@ class GsheetsFeederDB(Feeder, Database):
             logger.debug(f"Unable to update sheet: {e}")
 
     def _retrieve_gsheet(self, item: Metadata) -> Tuple[GWorksheet, int]:
-
         if gsheet := item.get_context("gsheet"):
             gw: GWorksheet = gsheet.get("worksheet")
             row: int = gsheet.get("row")
         elif self.sheet_id:
-            logger.error(f"Unable to retrieve Gsheet for {item.get_url()}, GsheetDB must be used alongside GsheetFeeder.")
+            logger.error(
+                f"Unable to retrieve Gsheet for {item.get_url()}, GsheetDB must be used alongside GsheetFeeder."
+            )
 
         return gw, row

src/auto_archiver/modules/gsheet_feeder_db/gworksheet.py

@@ -5,24 +5,25 @@ class GWorksheet:
     """
     This class makes read/write operations to the a worksheet easier.
     It can read the headers from a custom row number, but the row references
-    should always include the offset of the header. 
-    eg: if header=4, row 5 will be the first with data. 
+    should always include the offset of the header.
+    eg: if header=4, row 5 will be the first with data.
     """
+
     COLUMN_NAMES = {
-        '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',
+        "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",
     }
 
     def __init__(self, worksheet, columns=COLUMN_NAMES, header_row=1):
@@ -36,7 +37,7 @@ class GWorksheet:
 
     def _check_col_exists(self, col: str):
         if col not in self.columns:
-            raise Exception(f'Column {col} is not in the configured column names: {self.columns.keys()}')
+            raise Exception(f"Column {col} is not in the configured column names: {self.columns.keys()}")
 
     def _col_index(self, col: str):
         self._check_col_exists(col)
@@ -58,7 +59,7 @@ class GWorksheet:
 
     def get_cell(self, row, col: str, fresh=False):
         """
-        returns the cell value from (row, col), 
+        returns the cell value from (row, col),
         where row can be an index (1-based) OR list of values
         as received from self.get_row(row)
         if fresh=True, the sheet is queried again for this cell
@@ -67,11 +68,11 @@ class GWorksheet:
 
         if fresh:
             return self.wks.cell(row, col_index + 1).value
-        if type(row) == int:
+        if isinstance(row, int):
             row = self.get_row(row)
 
         if col_index >= len(row):
-            return ''
+            return ""
         return row[col_index]
 
     def get_cell_or_default(self, row, col: str, default: str = None, fresh=False, when_empty_use_default=True):
@@ -83,7 +84,7 @@ class GWorksheet:
             if when_empty_use_default and val.strip() == "":
                 return default
             return val
-        except:
+        except Exception:
             return default
 
     def set_cell(self, row: int, col: str, val):
@@ -96,13 +97,9 @@ class GWorksheet:
         receives a list of [(row:int, col:str, val)] and batch updates it, the parameters are the same as in the self.set_cell() method
         """
         cell_updates = [
-            {
-                'range': self.to_a1(row, col),
-                'values': [[str(val)[0:49999]]]
-            }
-            for row, col, val in cell_updates
+            {"range": self.to_a1(row, col), "values": [[str(val)[0:49999]]]} for row, col, val in cell_updates
         ]
-        self.wks.batch_update(cell_updates, value_input_option='USER_ENTERED')
+        self.wks.batch_update(cell_updates, value_input_option="USER_ENTERED")
 
     def to_a1(self, row: int, col: str):
         # row is 1-based

src/auto_archiver/modules/hash_enricher/__init__.py

@@ -1 +1 @@
-from .hash_enricher import HashEnricher
+from .hash_enricher import HashEnricher

src/auto_archiver/modules/hash_enricher/__manifest__.py

@@ -3,16 +3,17 @@
     "type": ["enricher"],
     "requires_setup": False,
     "dependencies": {
-                          "python": ["loguru"],
+        "python": ["loguru"],
     },
     "configs": {
-            "algorithm": {"default": "SHA-256", "help": "hash algorithm to use", "choices": ["SHA-256", "SHA3-512"]},
-            # TODO add non-negative requirement to match previous implementation?
-            "chunksize": {"default": 16000000,
-                          "help": "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",
-                          'type': 'int',
-                          },
+        "algorithm": {"default": "SHA-256", "help": "hash algorithm to use", "choices": ["SHA-256", "SHA3-512"]},
+        # TODO add non-negative requirement to match previous implementation?
+        "chunksize": {
+            "default": 16000000,
+            "help": "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",
+            "type": "int",
         },
+    },
     "description": """
 Generates cryptographic hashes for media files to ensure data integrity and authenticity.
 

src/auto_archiver/modules/hash_enricher/hash_enricher.py

@@ -1,4 +1,4 @@
-""" Hash Enricher for generating cryptographic hashes of media files.
+"""Hash Enricher for generating cryptographic hashes of media files.
 
 The `HashEnricher` calculates cryptographic hashes (e.g., SHA-256, SHA3-512)
 for media files stored in `Metadata` objects. These hashes are used for
@@ -7,6 +7,7 @@ exact duplicates. The hash is computed by reading the file's bytes in chunks,
 making it suitable for handling large files efficiently.
 
 """
+
 import hashlib
 from loguru import logger
 
@@ -20,7 +21,6 @@ class HashEnricher(Enricher):
     Calculates hashes for Media instances
     """
 
-
     def enrich(self, to_enrich: Metadata) -> None:
         url = to_enrich.get_url()
         logger.debug(f"calculating media hashes for {url=} (using {self.algorithm})")
@@ -35,5 +35,6 @@ class HashEnricher(Enricher):
             hash_algo = hashlib.sha256
         elif self.algorithm == "SHA3-512":
             hash_algo = hashlib.sha3_512
-        else: return ""
+        else:
+            return ""
         return calculate_file_hash(filename, hash_algo, self.chunksize)

src/auto_archiver/modules/html_formatter/__init__.py

@@ -1 +1 @@
-from .html_formatter import HtmlFormatter
+from .html_formatter import HtmlFormatter

src/auto_archiver/modules/html_formatter/__manifest__.py

@@ -2,14 +2,13 @@
     "name": "HTML Formatter",
     "type": ["formatter"],
     "requires_setup": False,
-    "dependencies": {
-                          "python": ["hash_enricher", "loguru", "jinja2"],
-                          "bin": [""]
-    },
+    "dependencies": {"python": ["hash_enricher", "loguru", "jinja2"], "bin": [""]},
     "configs": {
-            "detect_thumbnails": {"default": True,
-                                  "help": "if true will group by thumbnails generated by thumbnail enricher by id 'thumbnail_00'",
-                                  "type": "bool"},
+        "detect_thumbnails": {
+            "default": True,
+            "help": "if true will group by thumbnails generated by thumbnail enricher by id 'thumbnail_00'",
+            "type": "bool",
         },
+    },
     "description": """ """,
 }

src/auto_archiver/modules/html_formatter/html_formatter.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
-import mimetypes, os, pathlib
+import mimetypes
+import os
+import pathlib
 from jinja2 import Environment, FileSystemLoader
 from urllib.parse import quote
 from loguru import logger
@@ -11,6 +13,7 @@ from auto_archiver.core import Metadata, Media
 from auto_archiver.core import Formatter
 from auto_archiver.utils.misc import random_str
 
+
 class HtmlFormatter(Formatter):
     environment: Environment = None
     template: any = None
@@ -21,9 +24,9 @@ class HtmlFormatter(Formatter):
         self.environment = Environment(loader=FileSystemLoader(template_dir), autoescape=True)
 
         # JinjaHelper class static methods are added as filters
-        self.environment.filters.update({
-            k: v.__func__ for k, v in JinjaHelpers.__dict__.items() if isinstance(v, staticmethod)
-        })
+        self.environment.filters.update(
+            {k: v.__func__ for k, v in JinjaHelpers.__dict__.items() if isinstance(v, staticmethod)}
+        )
 
         # Load a specific template or default to "html_template.html"
         template_name = self.config.get("template_name", "html_template.html")
@@ -36,11 +39,7 @@ class HtmlFormatter(Formatter):
             return
 
         content = self.template.render(
-            url=url,
-            title=item.get_title(),
-            media=item.media,
-            metadata=item.metadata,
-            version=__version__
+            url=url, title=item.get_title(), media=item.media, metadata=item.metadata, version=__version__
         )
 
         html_path = os.path.join(self.tmp_dir, f"formatted{random_str(24)}.html")
@@ -49,7 +48,7 @@ class HtmlFormatter(Formatter):
         final_media = Media(filename=html_path, _mimetype="text/html")
 
         # get the already instantiated hash_enricher module
-        he = self.module_factory.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}")
 

src/auto_archiver/modules/instagram_api_extractor/__manifest__.py

@@ -2,18 +2,18 @@
     "name": "Instagram API Extractor",
     "type": ["extractor"],
     "entry_point": "instagram_api_extractor::InstagramAPIExtractor",
-    "dependencies":
-        {"python": ["requests",
-                    "loguru",
-                    "retrying",
-                    "tqdm",],
-         },
+    "dependencies": {
+        "python": [
+            "requests",
+            "loguru",
+            "retrying",
+            "tqdm",
+        ],
+    },
     "requires_setup": True,
     "configs": {
-        "access_token": {"default": None,
-                         "help": "a valid instagrapi-api token"},
-        "api_endpoint": {"required": True,
-                         "help": "API endpoint to use"},
+        "access_token": {"default": None, "help": "a valid instagrapi-api token"},
+        "api_endpoint": {"required": True, "help": "API endpoint to use"},
         "full_profile": {
             "default": False,
             "type": "bool",
@@ -31,9 +31,11 @@
         },
     },
     "description": """
-Archives various types of Instagram content using the Instagrapi API.
+Archives Instagram content using a deployment of the [Instagrapi API](https://subzeroid.github.io/instagrapi/).
 
-Requires setting up an Instagrapi API deployment and providing an access token and API endpoint.
+Requires either getting a token from using a hosted [(paid) service](https://api.instagrapi.com/docs) and setting this in the configuration file.
+Alternatively you can run your own server. We have a basic script which you can use for this which can be ran locally or using Docker.
+For more information, read the [how to guide](https://auto-archiver.readthedocs.io/en/latest/how_to/run_instagrapi_server.html) on this.
 
 ### Features
 - Connects to an Instagrapi API deployment to fetch Instagram profiles, posts, stories, highlights, reels, and tagged content.