archival notification

migrate gh artifact actions to v4

.github/actions/setup-venv/action.yml

@@ -31,7 +31,7 @@ runs:
         # Get the exact Python version to use in the cache key.
         echo "PYTHON_VERSION=$(python --version)" >> $GITHUB_ENV
 
-    - uses: actions/cache@v2
+    - uses: actions/cache@v4
       id: virtualenv-cache
       with:
         path: .venv

.github/workflows/main.yml

@@ -79,10 +79,11 @@ jobs:
         run: |
           . .venv/bin/activate
           ${{ matrix.task.run }}
+        continue-on-error: ${{ matrix.task.name != 'Build' }}
 
       - name: Upload package distribution files
         if: matrix.task.name == 'Build'
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: package
           path: dist
@@ -117,7 +118,7 @@ jobs:
           echo "TAG=${GITHUB_REF#refs/tags/}" >> $GITHUB_ENV
 
       - name: Download package distribution files
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4
         with:
           name: package
           path: dist

Pipfile

@@ -5,6 +5,15 @@ name = "pypi"
 
 [packages]
 yt-dlp = ">=2023.2.17"
+certifi = ">=2023.7.22"
+charset-normalizer = ">=3.0.1"
+idna = ">=3.4"
+mutagen = ">=1.46.0"
+pycryptodomex = ">=3.17"
+requests = ">=2.28.2"
+urllib3 = ">=1.26.14"
+websockets = ">=10.4"
+vk-api = {ref = "b99dac0ec2f832a6c4b20bde49869e7229ce4742", git = "git+https://github.com/python273/vk_api.git"}
 flake8 = "*"
 mypy = ">=0.961"
 black = ">=22.3.0"
@@ -19,19 +28,8 @@ myst-parser = "<0.19.0,>=0.15.2"
 sphinx-copybutton = ">=0.5.0"
 sphinx-autobuild = ">=2021.3.14"
 sphinx-autodoc-typehints = "*"
+packaging = "*"
 python-dotenv = ">=0.21.1"
-brotli = ">=1.0.9"
-certifi = ">=2023.7.22"
-charset-normalizer = ">=3.0.1"
-idna = ">=3.4"
-mutagen = ">=1.46.0"
-pycryptodomex = ">=3.17"
-requests = ">=2.28.2"
-urllib3 = ">=1.26.14"
-websockets = ">=10.4"
-# vk-api = {ref = "77b5a0d51a6bbf54d59554332f28a488615fbd6c", git = "git+https://github.com/python273/vk_api.git"}
-# vk-api = "*"
-vk-api = {ref = "b99dac0ec2f832a6c4b20bde49869e7229ce4742", git = "git+https://github.com/python273/vk_api.git"}
 
 [dev-packages]
 sphinx-copybutton = "==0.5.0"
@@ -51,7 +49,7 @@ sphinx-autodoc-typehints = "*"
 python-dotenv = "*"
 
 [requires]
-python_version = "3.9"
+python_version = "3.11"
 
 [pipenv]
 allow_prereleases = true

README.md

@@ -1,6 +1,7 @@
 # vk-url-scraper
 Python library to scrape data, and especially media links like videos and photos, from vk.com URLs.
 
+> This repo has been archived because it relies on a fixed git commit of the vk_api library which we can no longer publish to pypi, see [issue](https://github.com/bellingcat/vk-url-scraper/issues/66). You can still install the latest install. This archived state may change if a solution is found to publish the library to pypi again.
 
 [![PyPI version](https://badge.fury.io/py/vk-url-scraper.svg)](https://badge.fury.io/py/vk-url-scraper)
 [![PyPI download month](https://img.shields.io/pypi/dm/vk-url-scraper.svg)](https://pypi.python.org/pypi/vk-url-scraper/)
@@ -12,6 +13,12 @@ You can use it via the [command line](#command-line-usage) or as a [python libra
 ## Installation
 You can install the most recent release from [pypi](https://pypi.org/project/vk-url-scraper/) via `pip install vk-url-scraper`.
 
+Currently you need to manually unsintall and re-install one dependency (as it is installed from github and not pypi):
+```bash
+pip uninstall vk-api
+pip install git+https://github.com/python273/vk_api.git@b99dac0ec2f832a6c4b20bde49869e7229ce4742
+```
+
 To use the library you will need a valid username/password combination for vk.com. 
 
 ## Command line usage
@@ -84,8 +91,9 @@ see [docs] for all available functions.
 ## Development
 (more info in [CONTRIBUTING.md](CONTRIBUTING.md)).
 
-1. setup dev environment with `pip install -r dev-requirements.txt` or `pipenv install -r dev-requirements.txt`
+1. setup dev environment with `pipenv install --dev`
-1. setup environment with `pip install -r requirements.txt` or `pipenv install -r requirements.txt`
+1. setup environment with `pipenv install -r requirements.txt`
+1. Activate the environment with `pipenv shell` (or prepend `pipenv run` to all commands)
 2. To run all checks to `make run-checks` (fixes style) or individually
    1. To fix style: `black .` and `isort .` -> `flake8 .` to validate lint
    2. To do type checking: `mypy .`
@@ -98,6 +106,7 @@ To test the command line interface available in [__main__.py](__vk_url_scraper/_
 ## Releasing new version
 1. edit [version.py](vk_url_scraper/version.py) with proper versioning
 2. make sure to run `pipenv run pip freeze > requirements.txt` if you manage libs with pipenv
+   1. if the hardcoded version of [vk_api](https://github.com/python273/vk_api) is still being used, then you must comment/remove that line from the generated requirements file and instruct users to manually install the version from the source as pypi does not allow repo/commit tags. Additionally, add the latest released version, currently `vk-api==11.9.9`. 
 3. run `./scripts/release.sh` to create a tag and push, alternatively
    1. `git tag vx.y.z` to tag version
    2. `git push origin vx.y.z` -> this will trigger workflow and put project on [pypi](https://pypi.org/project/vk-url-scraper/)

requirements.txt

@@ -1,103 +1,87 @@
-aiohttp==3.9.1
-aiosignal==1.3.1
 alabaster==0.7.16
-anyio==4.4.0
+anyio==4.9.0
-async-timeout==4.0.3
+babel==2.17.0
-attrs==23.2.0
-Babel==2.15.0
 backports.tarfile==1.2.0
-beautifulsoup4==4.13.0b2
+beautifulsoup4==4.13.4
-black==24.4.2
+black==25.1.0
-bleach==6.0.0
+certifi==2025.4.26
-Brotli==1.1.0
+cffi==1.17.1
-certifi==2024.7.4
+charset-normalizer==3.4.2
-cffi==1.17.0rc1
+click==8.1.8
-charset-normalizer==3.3.2
-click==8.1.7
 colorama==0.4.6
-commonmark==0.9.1
+coverage==7.8.0
-coverage==7.6.0
+cryptography==44.0.3
-cryptography==42.0.8
 docutils==0.18.1
-exceptiongroup==1.2.2
+flake8==7.2.0
-flake8==7.1.0
-frozenlist==1.4.1
 furo==2023.3.27
-h11==0.14.0
+h11==0.16.0
-idna==3.7
+id==1.5.0
+idna==3.10
 imagesize==1.4.1
-importlib_metadata==8.0.0
+importlib_metadata==8.7.0
-iniconfig==2.0.0
+iniconfig==2.1.0
-isort==6.0.0b2
+isort==6.0.1
 jaraco.classes==3.4.0
-jaraco.context==5.3.0
+jaraco.context==6.0.1
-jaraco.functools==4.0.1
+jaraco.functools==4.1.0
-jeepney==0.8.0
+jeepney==0.9.0
-Jinja2==3.1.4
+Jinja2==3.1.6
-keyring==25.2.1
+keyring==25.6.0
-livereload==2.6.3
+livereload==2.7.1
 markdown-it-py==2.2.0
-MarkupSafe==2.1.5
+MarkupSafe==3.0.2
 mccabe==0.7.0
 mdit-py-plugins==0.3.5
 mdurl==0.1.2
-more-itertools==10.3.0
+more-itertools==10.7.0
-multidict==6.0.4
 mutagen==1.47.0
-mypy==1.10.1
+mypy==1.15.0
-mypy-extensions==1.0.0
+mypy_extensions==1.1.0
 myst-parser==0.18.1
-nh3==0.2.18
+nh3==0.2.21
-packaging==24.1
+packaging==25.0
 pathspec==0.12.1
 pkginfo==1.10.0
-platformdirs==4.2.2
+platformdirs==4.3.7
 pluggy==1.5.0
-py==1.11.0
+pycodestyle==2.13.0
-pycodestyle==2.12.0
 pycparser==2.22
-pycryptodomex==3.20.0
+pycryptodomex==3.22.0
-pyflakes==3.2.0
+pyflakes==3.3.2
-Pygments==2.18.0
+Pygments==2.19.1
-pyparsing==3.0.9
+pytest==8.3.5
-pytest==8.2.2
+pytest-cov==6.1.1
-pytest-cov==5.0.0
 pytest-sphinx==0.6.3
-python-dotenv==1.0.1
+python-dotenv==1.1.0
-pytz==2022.1
+PyYAML==6.0.2
-PyYAML==6.0.2rc1
 readme_renderer==43.0
 requests==2.32.3
 requests-toolbelt==1.0.0
 rfc3986==2.0.0
-rich==13.7.1
+rich==14.0.0
 SecretStorage==3.3.3
-six==1.16.0
 sniffio==1.3.1
 snowballstemmer==2.2.0
-soupsieve==2.5
+soupsieve==2.7
 Sphinx==5.0.2
-sphinx-autobuild==2024.4.16
+sphinx-autobuild==2024.10.3
 sphinx-autodoc-typehints==1.19.1
 sphinx-basic-ng==1.0.0b2
 sphinx-copybutton==0.5.2
-sphinxcontrib-applehelp==1.0.8
+sphinxcontrib-applehelp==2.0.0
-sphinxcontrib-devhelp==1.0.6
+sphinxcontrib-devhelp==2.0.0
-sphinxcontrib-htmlhelp==2.0.5
+sphinxcontrib-htmlhelp==2.1.0
 sphinxcontrib-jsmath==1.0.1
-sphinxcontrib-qthelp==1.0.7
+sphinxcontrib-qthelp==2.0.0
-sphinxcontrib-serializinghtml==1.1.10
+sphinxcontrib-serializinghtml==2.0.0
-starlette==0.37.2
+starlette==0.46.2
-tomli==2.0.1
+tornado==6.5b1
-tornado==6.4
+twine==6.1.0
-twine==5.1.1
+typing_extensions==4.13.2
-typing_extensions==4.12.2
+urllib3==2.4.0
-urllib3==2.2.2
+uvicorn==0.34.2
-uvicorn==0.30.1
+vk_api @ git+https://github.com/python273/vk_api.git@b99dac0ec2f832a6c4b20bde49869e7229ce4742
-vk-api @ git+https://github.com/python273/vk_api.git@b99dac0ec2f832a6c4b20bde49869e7229ce4742
+watchfiles==1.0.5
-watchfiles==0.22.0
+websockets==15.0.1
-webencodings==0.5.1
+yt-dlp==2025.5.3.232917.dev0
-websockets==12.0
+zipp==3.21.0
-yarl==1.9.4
-yt-dlp==2024.7.15.232803.dev0
-zipp==3.19.2

tests/scraper_test.py

@@ -81,7 +81,7 @@ def test_scrape_wall_url_with_photos():
         == "Хабаровск\nАллея героев\nПомолимся об укокоении воинов:\nАлександра, Игоря, Эдуарда, \nДионисия, Евгения, Александра, Артемия, Иннокентия, Андрея."
     )
     assert str(res[0]["datetime"]) == str(datetime.datetime(2022, 6, 15, 10, 37, 24))
-    assert len(res[0]["payload"]) == 18
+    assert len(res[0]["payload"]) == 19
     assert len(res[0]["attachments"].keys()) == 1
     assert list(res[0]["attachments"].keys()) == ["photo"]
     assert len(res[0]["attachments"]["photo"]) == 9

vk_url_scraper/version.py

@@ -2,7 +2,7 @@ _MAJOR = "0"
 _MINOR = "3"
 # On main and in a nightly release the patch should be one ahead of the last
 # released build.
-_PATCH = "29"
+_PATCH = "34"
 # This is mainly for nightly builds which have the suffix ".dev$DATE". See
 # https://semver.org/#is-v123-a-semantic-version for the semantics.
 _SUFFIX = ""