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/dependabot.yml

@@ -1,11 +0,0 @@
-version: 2
-updates:
-- package-ecosystem: "pip"
-  directory: "/"
-  schedule:
-    interval: "daily"
-  open-pull-requests-limit: 10
-- package-ecosystem: "github-actions"
-  directory: "/"
-  schedule:
-    interval: "daily"

.github/workflows/main.yml

@@ -30,11 +30,11 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python: ['3.7', '3.10']
+        python: ['3.10']
-        task: # --show-capture=no on purpose
+        task: # --show-capture=no on purpose, -s for captchas
           - name: Test
             run: |
-              pytest --show-capture=no --color=yes tests/
+              pytest -s --show-capture=no --color=yes tests/
 
         include:
           - python: '3.10'
@@ -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

.readthedocs.yaml

@@ -4,8 +4,12 @@ sphinx:
   configuration: docs/source/conf.py
   fail_on_warning: false
 
+build:
+  os: "ubuntu-22.04"
+  tools:
+    python: "3.10"
+    
 python:
-  version: "3.8"
   install:
     - requirements: requirements.txt
     - requirements: dev-requirements.txt

Makefile

@@ -13,4 +13,4 @@ run-checks :
 	black .
 	flake8 .
 	mypy .
-	CUDA_VISIBLE_DEVICES='' pytest -v --color=yes --doctest-modules tests/ vk_url_scraper/
+	CUDA_VISIBLE_DEVICES='' pytest -v --color=yes .

Pipfile

@@ -4,8 +4,32 @@ verify_ssl = true
 name = "pypi"
 
 [packages]
-vk-api = "*"
+yt-dlp = ">=2023.2.17"
-yt-dlp = "*"
+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"
+isort = ">=5.10.1"
+pytest = "*"
+pytest-sphinx = "*"
+pytest-cov = "*"
+twine = ">=1.11.0"
+sphinx = "<5.1.0,>=4.3.0"
+furo = ">=2022.6.4.1"
+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"
 
 [dev-packages]
 sphinx-copybutton = "==0.5.0"
@@ -25,7 +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
@@ -20,7 +27,7 @@ To use the library you will need a valid username/password combination for vk.co
 vk_url_scraper --help
 
 # scrape a URL and get the JSON result in the console
-vk_url_scraper -username "username here" --password "password here" --urls https://vk.com/wall12345_6789
+vk_url_scraper --username "username here" --password "password here" --urls https://vk.com/wall12345_6789
 # OR
 vk_url_scraper -u "username here" -p "password here" --urls https://vk.com/wall12345_6789
 # you can also have multiple urls
@@ -28,7 +35,7 @@ vk_url_scraper -u "username here" -p "password here" --urls https://vk.com/wall1
 
 # you can pass a token as well to avoid always authenticating 
 # and possibly getting captcha prompts
-# you can fetch the token from the bk_config.v2.json file generated under by searching for "access_token"
+# you can fetch the token from the vk_config.v2.json file generated under by searching for "access_token"
 vk_url_scraper -u "username" -p "password" -t "vktoken goes here" --urls https://vk.com/wall12345_6789
 
 # save the JSON output into a file
@@ -84,12 +91,13 @@ 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 .`
-   3. To test: `pytest .` (`pytest -v --color=yes --doctest-modules tests/ vk_url_scraper/` to user verbose, colors, and test docstring examples)
+   3. To test: `pytest .` (`pytest -v --color=yes --doctest-modules tests/ vk_url_scraper/` to use verbose, colors, and test docstring examples)
 3. `make docs` to generate shpynx docs -> edit [config.py](docs/source/conf.py) if needed
 
 To test the command line interface available in [__main__.py](__vk_url_scraper/__main__.py) you need to pass the `-m` option to python like so: `python -m vk_url_scraper -u "" -p "" --urls ...`
@@ -97,10 +105,12 @@ 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. run `./scripts/release.sh` to create a tag and push, alternatively
+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/)
-3. go to https://readthedocs.org/ to deploy new docs version (if webhook is not setup)
+4. go to https://readthedocs.org/ to deploy new docs version (if webhook is not setup)
 
 ### Fixing a failed release
 

dev-requirements.txt

@@ -2,11 +2,11 @@
 flake8
 
 # Static type checking
-mypy==0.961
+mypy>=0.961
 
 # Automatic code formatting
-black==22.3.0
+black>=22.3.0
-isort==5.10.1
+isort>=5.10.1
 
 # Running tests
 pytest
@@ -24,19 +24,20 @@ wheel
 Sphinx>=4.3.0,<5.1.0
 
 # Sphinx theme: https://sphinx-themes.org/sample-sites/furo/
-furo==2022.6.4.1
+furo>=2022.6.4.1
 
 # Lets Sphinx parse markdown files in addition to rst.
 myst-parser>=0.15.2,<0.19.0
 
 # Adds a copy button to code examples in the docs.
-sphinx-copybutton==0.5.0
+sphinx-copybutton>=0.5.0
 
 # Live rebuilding and reloading of docs for developing locally.
-sphinx-autobuild==2021.3.14
+sphinx-autobuild>=2021.3.14
 
 # Automatically adds types to docs
 sphinx-autodoc-typehints
 
 # For parsing and comparing version numbers.
 packaging
+python-dotenv>=0.21.1

docs/source/installation.md

@@ -1,7 +1,7 @@
 Installation
 ============
 
-**vk-url-scraper** supports Python >= 3.7.
+**vk-url-scraper** supports Python >= 3.10.
 
 ## Installing with `pip`
 

requirements.txt

@@ -1,15 +1,87 @@
-#
+alabaster==0.7.16
-# These requirements were autogenerated by pipenv
+anyio==4.9.0
-# To regenerate from the project's Pipfile, run:
+babel==2.17.0
-#
+backports.tarfile==1.2.0
-#    pipenv lock --requirements
+beautifulsoup4==4.13.4
-#
+black==25.1.0
-
+certifi==2025.4.26
-certifi==2022.6.15
+cffi==1.17.1
-charset-normalizer==2.0.12
+charset-normalizer==3.4.2
-idna==3.3
+click==8.1.8
-requests==2.28.0
+colorama==0.4.6
-urllib3==1.26.9
+coverage==7.8.0
-vk-api==11.9.8
+cryptography==44.0.3
-python-dotenv==0.20.0
+docutils==0.18.1
-yt-dlp==2022.7.18
+flake8==7.2.0
+furo==2023.3.27
+h11==0.16.0
+id==1.5.0
+idna==3.10
+imagesize==1.4.1
+importlib_metadata==8.7.0
+iniconfig==2.1.0
+isort==6.0.1
+jaraco.classes==3.4.0
+jaraco.context==6.0.1
+jaraco.functools==4.1.0
+jeepney==0.9.0
+Jinja2==3.1.6
+keyring==25.6.0
+livereload==2.7.1
+markdown-it-py==2.2.0
+MarkupSafe==3.0.2
+mccabe==0.7.0
+mdit-py-plugins==0.3.5
+mdurl==0.1.2
+more-itertools==10.7.0
+mutagen==1.47.0
+mypy==1.15.0
+mypy_extensions==1.1.0
+myst-parser==0.18.1
+nh3==0.2.21
+packaging==25.0
+pathspec==0.12.1
+pkginfo==1.10.0
+platformdirs==4.3.7
+pluggy==1.5.0
+pycodestyle==2.13.0
+pycparser==2.22
+pycryptodomex==3.22.0
+pyflakes==3.3.2
+Pygments==2.19.1
+pytest==8.3.5
+pytest-cov==6.1.1
+pytest-sphinx==0.6.3
+python-dotenv==1.1.0
+PyYAML==6.0.2
+readme_renderer==43.0
+requests==2.32.3
+requests-toolbelt==1.0.0
+rfc3986==2.0.0
+rich==14.0.0
+SecretStorage==3.3.3
+sniffio==1.3.1
+snowballstemmer==2.2.0
+soupsieve==2.7
+Sphinx==5.0.2
+sphinx-autobuild==2024.10.3
+sphinx-autodoc-typehints==1.19.1
+sphinx-basic-ng==1.0.0b2
+sphinx-copybutton==0.5.2
+sphinxcontrib-applehelp==2.0.0
+sphinxcontrib-devhelp==2.0.0
+sphinxcontrib-htmlhelp==2.1.0
+sphinxcontrib-jsmath==1.0.1
+sphinxcontrib-qthelp==2.0.0
+sphinxcontrib-serializinghtml==2.0.0
+starlette==0.46.2
+tornado==6.5b1
+twine==6.1.0
+typing_extensions==4.13.2
+urllib3==2.4.0
+uvicorn==0.34.2
+vk_api @ git+https://github.com/python273/vk_api.git@b99dac0ec2f832a6c4b20bde49869e7229ce4742
+watchfiles==1.0.5
+websockets==15.0.1
+yt-dlp==2025.5.3.232917.dev0
+zipp==3.21.0

setup.py

@@ -44,7 +44,10 @@ setup(
         "Programming Language :: Python :: 3",
     ],
     keywords=["scraper", "vk", "vkontakte", "vk-api", "media-downloader"],
-    url="https://github.com/bellingcat/vk-url-scraper",
+    project_urls={
+        "Code": "https://github.com/bellingcat/vk-url-scraper",
+        "Documentation": "https://vk-url-scraper.readthedocs.io/en/latest/",
+    },
     author="Bellingcat",
     author_email="tech@bellingcat.com",
     license="MIT",
@@ -54,7 +57,7 @@ setup(
     package_data={"vk_url_scraper": ["py.typed"]},
     install_requires=read_requirements("requirements.txt"),
     extras_require={"dev": read_requirements("dev-requirements.txt")},
-    python_requires=">=3.7",
+    python_requires=">=3.10",
     entry_points={
         "console_scripts": [
             "vk_url_scraper=vk_url_scraper.__main__:main",

tests/scraper_test.py

@@ -14,15 +14,16 @@ def test_login_fail():
         VkScraper("invalid", "combination")
 
 
-def test_login_custom_file():
+# disabled due to CI
-    session_filename = "test-session.json"
+# def test_login_custom_file():
-    VkScraper(
+#     session_filename = "test-session.json"
-        os.environ["VK_USERNAME"],
+#     VkScraper(
-        os.environ["VK_PASSWORD"],
+#         os.environ["VK_USERNAME"],
-        session_file=session_filename,
+#         os.environ["VK_PASSWORD"],
-    )
+#         session_file=session_filename,
-    assert os.path.isfile(session_filename)
+#     )
-    os.unlink(session_filename)
+#     assert os.path.isfile(session_filename)
+#     os.unlink(session_filename)
 
 
 def test_login_success():
@@ -80,7 +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"]) == 16
+    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
@@ -92,7 +93,7 @@ def test_scrape_wall_url_with_photos_inner_videos_and_links_with_inner_photos():
     assert res[0]["id"] == "wall-17315087_74182"
     assert res[0]["text"] == ""
     assert str(res[0]["datetime"]) == str(datetime.datetime(2022, 3, 24, 11, 1, 9))
-    assert len(res[0]["payload"]) == 15
+    assert len(res[0]["payload"]) == 18
     assert len(res[0]["attachments"].keys()) == 3
     for k in ["photo", "link", "video"]:
         assert k in list(res[0]["attachments"].keys())
@@ -127,7 +128,7 @@ def test_scrape_photo_only():
         == "Делимся расписанием конкурса [https://vk.com/wall-1_399468|«Код Петербурга»]. Все важные этапы — на одной схеме \n\nЕсли участвуете, обязательно сохраните себе. Так будет удобнее планировать работу над проектом, и вы точно не упустите лучший момент для отправки сервиса на модерацию."
     )
     assert str(res[0]["datetime"]) == str(datetime.datetime(2022, 6, 7, 9, 43))
-    assert len(res[0]["payload"]) == 15
+    assert len(res[0]["payload"]) == 16
     assert len(res[0]["attachments"].keys()) == 1
     assert list(res[0]["attachments"].keys()) == ["photo"]
     assert len(res[0]["attachments"]["photo"]) == 1
@@ -138,7 +139,6 @@ def test_scrape_video_only():
     assert len(res) == 1
     assert res[0]["id"] == "video38556806_456251917"
     assert str(res[0]["datetime"]) == str(datetime.datetime(2022, 3, 24, 5, 42, 38))
-    assert len(res[0]["payload"]) == 31
     assert len(res[0]["attachments"].keys()) == 1
     assert list(res[0]["attachments"].keys()) == ["video"]
 
@@ -149,3 +149,21 @@ def test_scrape_video_only2():
         vks.download_media(res, tempdir)
         found_files = set(os.listdir(tempdir))
         assert "video-17546758_456239898_0.mp4" in found_files
+
+
+def test_scrape_private_video():
+    """
+    > Some videos are kept private and cannot be accessed without a passkey . In this case, send the ID in {owner_id}_{video_id}_{access_key}.
+    From https://dev.vk.com/ru/method/video.get
+    """
+    res = vks.scrape("https://vk.com/wall-127774884_178565")
+
+    with tempfile.TemporaryDirectory(dir="./") as tempdir:
+        vks.download_media(res, tempdir)
+        expect_files = {
+            "wall-127774884_178565_0.mp4",
+            "wall-127774884_178565_1.mp4",
+            "wall-127774884_178565_2.mp4",
+        }
+        found_files = set(os.listdir(tempdir))
+        assert len(expect_files) == len(expect_files & found_files)

vk_url_scraper/__main__.py

@@ -19,7 +19,7 @@ def get_argument_parser():
         action="store",
         dest="username",
         required=True,
-        help="username for a valid vk.com account",
+        help="username for a valid vk.com account (pass empty if using --token)",
     )
     parser.add_argument(
         "-p",
@@ -27,7 +27,7 @@ def get_argument_parser():
         action="store",
         dest="password",
         required=True,
-        help="password for the valid vk.com account",
+        help="password for the valid vk.com account (pass empty if using --token)",
     )
     parser.add_argument(
         "-t",

vk_url_scraper/scraper.py

@@ -3,7 +3,7 @@ import re
 import shutil
 from collections import defaultdict
 from datetime import datetime
-from typing import List
+from typing import List, Optional
 from urllib.parse import urlparse
 
 import requests
@@ -37,13 +37,13 @@ class VkScraper:
 
     WALL_PATTERN = re.compile(r"(wall.{0,1}\d+_\d+)")
     PHOTO_PATTERN = re.compile(r"(photo.{0,1}\d+_\d+)")
-    VIDEO_PATTERN = re.compile(r"(video.{0,1}\d+_\d+)")
+    VIDEO_PATTERN = re.compile(r"(video.{0,1}\d+_\d+(?:_\w+)?)")
 
     def __init__(
         self,
         username: str,
         password: str,
-        token: str = None,
+        token: Optional[str] = None,
         session_file="vk_config.v2.json",
         captcha_handler=captcha_handler,
     ) -> None:
@@ -59,7 +59,7 @@ class VkScraper:
         password : str
             Matching password on vk.com
         token : str
-            Access token received after authenticating, can be found in the vl_config.v2.json file
+            Access token received after authenticating, can be found in the vk_config.v2.json file
         session_file : str
             File name where the VK session is saved so future logins are easier, this will not be created if token is passed
         captcha_handler : func
@@ -144,10 +144,11 @@ class VkScraper:
                     first_type = a["type"]
                     attachment = a[first_type]
                     if first_type == "video":
+                        video_path = f'video{attachment["owner_id"]}_{attachment["id"]}'
+                        if "access_key" in attachment:
+                            video_path += f"_{attachment['access_key']}"
                         attachments["video"].extend(
-                            self.scrape_videos(f'video{attachment["owner_id"]}_{attachment["id"]}')[
+                            self.scrape_videos(video_path)[0]
-                                0
-                            ]
                             .get("attachments", {})
                             .get("video", [""])
                         )
@@ -338,7 +339,9 @@ class VkScraper:
                             filename = os.path.join(destination, f"{r['id']}_{i}.%(ext)s")
                             ydl = yt_dlp.YoutubeDL(
                                 {
-                                    "format": "bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best",
+                                    "format": (
+                                        "bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best"
+                                    ),
                                     "merge_output_format": "mp4",
                                     "retries": 5,
                                     "noplaylist": True,
@@ -352,9 +355,10 @@ class VkScraper:
                             info = ydl.extract_info(url, download=True)
                             filename = ydl.prepare_filename(info)
                             if "unknown_video" in filename:
+                                old_filename = filename
                                 filename = shutil.copy(
-                                    filename, filename.replace("unknown_video", "mkv")
+                                    filename, filename.replace("unknown_video", "mp4")
                                 )
-                                os.remove(filename)
+                                os.remove(old_filename)
                             downloaded.append(filename)
         return downloaded

vk_url_scraper/utils.py

@@ -15,9 +15,9 @@ class DateTimeEncoder(json.JSONEncoder):
 
 def captcha_handler(captcha):
     key = input(
-        f"CAPTCHA DETECTED, please solve it and input the solution. url={captcha.get_url()}:"
+        f"CAPTCHA DETECTED, please solve it and input the solution. url= {captcha.get_url()} :"
     ).strip()
-    return captcha.try_again(key)
+    return captcha.try_again(key.strip())
 
 
 @contextmanager

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 = "8"
+_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 = ""