Compare commits

...

7 Commits

Author SHA1 Message Date
msramalho
73f17407c0 reverting library dependencies 2024-01-23 18:09:56 +00:00
msramalho
95d249f5d0 min py to 3.10 2024-01-23 13:01:38 +00:00
msramalho
ccb8c1f5c7 min python to 3.8 2024-01-23 12:50:55 +00:00
msramalho
e525ff24b1 lint 2024-01-23 12:45:45 +00:00
msramalho
699b4ebdd8 fix lib dependencies in pypi version 2024-01-23 12:41:25 +00:00
msramalho
8d1a86a7fa fix captcha processing 2024-01-23 12:41:14 +00:00
msramalho
b01dbe6299 fix vk_api dependency changes 2024-01-23 11:56:49 +00:00
13 changed files with 1691 additions and 1121 deletions

View File

@@ -30,7 +30,7 @@ jobs:
strategy:
fail-fast: false
matrix:
python: ['3.7', '3.10']
python: ['3.10']
task: # --show-capture=no on purpose, -s for captchas
- name: Test
run: |

View File

@@ -7,7 +7,7 @@ sphinx:
build:
os: "ubuntu-22.04"
tools:
python: "3.8"
python: "3.10"
python:
install:

View File

@@ -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 .

View File

@@ -4,7 +4,6 @@ verify_ssl = true
name = "pypi"
[packages]
vk-api = ">=11.9.9"
yt-dlp = ">=2023.2.17"
flake8 = "*"
mypy = ">=0.961"
@@ -30,6 +29,8 @@ 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 = "*"
[dev-packages]
sphinx-copybutton = "==0.5.0"

2663
Pipfile.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -20,7 +20,7 @@ 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
@@ -89,7 +89,7 @@ see [docs] for all available functions.
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 +97,11 @@ 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
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

View File

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

View File

@@ -1,19 +1,94 @@
#
# These requirements were autogenerated by pipenv
# To regenerate from the project's Pipfile, run:
#
# pipenv lock --requirements
#
# -i https://pypi.org/simple
brotli>=1.0.9; platform_python_implementation >= 'CPython'
certifi>=2022.12.7; python_version >= '3.6'
charset-normalizer>=3.0.1; python_version >= '3.6'
idna>=3.4; python_version >= '3.5'
mutagen>=1.46.0; python_version >= '3.7'
pycryptodomex>=3.17; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
requests>=2.28.2; python_version >= '3.7' and python_version < '4'
urllib3>=1.26.14; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4, 3.5'
vk-api>=11.9.9
websockets>=10.4; python_version >= '3.7'
yt-dlp>=2023.2.17
aiohttp==3.9.1
aiosignal==1.3.1
alabaster==0.7.16
async-timeout==4.0.3
attrs==23.2.0
Babel==2.14.0
beautifulsoup4==4.12.3
black==24.1a1
bleach==6.0.0
Brotli==1.1.0
certifi==2023.11.17
cffi==1.16.0
charset-normalizer==3.3.2
click==8.1.7
colorama==0.4.6
commonmark==0.9.1
coverage==7.4.0
cryptography==42.0.0
docutils==0.18.1
exceptiongroup==1.2.0
flake8==7.0.0
frozenlist==1.4.1
furo==2023.3.27
idna==3.6
imagesize==1.4.1
importlib-metadata==7.0.1
iniconfig==2.0.0
isort==6.0.0b2
jaraco.classes==3.3.0
jeepney==0.8.0
Jinja2==3.1.3
keyring==24.3.0
livereload==2.6.3
markdown-it-py==2.2.0
MarkupSafe==2.1.4
mccabe==0.7.0
mdit-py-plugins==0.3.5
mdurl==0.1.2
more-itertools==10.2.0
multidict==6.0.4
mutagen==1.47.0
mypy==1.8.0
mypy-extensions==1.0.0
myst-parser==0.18.1
nh3==0.2.15
packaging==23.2
pathspec==0.12.1
pkginfo==1.9.6
platformdirs==4.1.0
pluggy==1.3.0
py==1.11.0
pycodestyle==2.11.1
pycparser==2.21
pycryptodomex==3.20.0
pyflakes==3.2.0
Pygments==2.17.2
pyparsing==3.0.9
pytest==8.0.0rc2
pytest-cov==4.1.0
pytest-sphinx==0.5.0
python-dotenv==1.0.1
pytz==2022.1
PyYAML==6.0.1
readme-renderer==42.0
requests==2.31.0
requests-toolbelt==1.0.0
rfc3986==2.0.0
rich==13.7.0
SecretStorage==3.3.3
six==1.16.0
snowballstemmer==2.2.0
soupsieve==2.5
Sphinx==5.0.2
sphinx-autobuild==2021.3.14
sphinx-autodoc-typehints==1.19.1
sphinx-basic-ng==1.0.0b2
sphinx-copybutton==0.5.2
sphinxcontrib-applehelp==1.0.8
sphinxcontrib-devhelp==1.0.6
sphinxcontrib-htmlhelp==2.0.5
sphinxcontrib-jsmath==1.0.1
sphinxcontrib-qthelp==1.0.7
sphinxcontrib-serializinghtml==1.1.10
tomli==2.0.1
tornado==6.4
twine==4.0.2
typing_extensions==4.9.0
urllib3==2.1.0
vk-api @ git+https://github.com/python273/vk_api.git@77b5a0d51a6bbf54d59554332f28a488615fbd6c
webencodings==0.5.1
websockets==12.0
yarl==1.9.4
yt-dlp==2024.1.22.232713.dev0
zipp==3.17.0

View File

@@ -57,7 +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",

View File

@@ -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"]) == 17
assert len(res[0]["payload"]) == 18
assert len(res[0]["attachments"].keys()) == 1
assert list(res[0]["attachments"].keys()) == ["photo"]
assert len(res[0]["attachments"]["photo"]) == 9
@@ -93,7 +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"]) == 17
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())
@@ -128,7 +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

View File

@@ -339,7 +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,

View File

@@ -17,7 +17,7 @@ def captcha_handler(captcha):
key = input(
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

View File

@@ -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 = "26"
_PATCH = "28"
# 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 = ""