Compare commits

...

6 Commits

Author SHA1 Message Date
Chris Caruso
5970310f87
Merge 7f7356078c into b83ca24eb7 2024-11-10 09:19:38 +05:30
sepro
b83ca24eb7
[core] Catch broken Cryptodome installations (#11486)
Authored by: seproDev
2024-11-10 00:53:49 +01:00
bashonly
240a7d43c8
[build] Pin websockets version to >=13.0,<14 (#11488)
websockets 14.0 causes CI test failures (a lot more of them)

Authored by: bashonly
2024-11-09 23:46:47 +00:00
bashonly
f13df591d4
[build] Enable attestations for trusted publishing (#11420)
Reverts 428ffb75aa

Authored by: bashonly
2024-11-09 23:26:02 +00:00
Chris Caruso
7f7356078c fixed import formatting, trailing whitespace 2024-08-05 16:58:38 -07:00
Chris Caruso
0cc88e810b updated elpais extractor 2024-08-05 16:54:27 -07:00
7 changed files with 79 additions and 70 deletions

View File

@ -504,7 +504,8 @@ jobs:
- windows32
runs-on: ubuntu-latest
steps:
- uses: actions/download-artifact@v4
- name: Download artifacts
uses: actions/download-artifact@v4
with:
path: artifact
pattern: build-bin-*

View File

@ -28,3 +28,20 @@ jobs:
actions: write # For cleaning up cache
id-token: write # mandatory for trusted publishing
secrets: inherit
publish_pypi:
needs: [release]
if: vars.MASTER_PYPI_PROJECT != ''
runs-on: ubuntu-latest
permissions:
id-token: write # mandatory for trusted publishing
steps:
- name: Download artifacts
uses: actions/download-artifact@v4
with:
path: dist
name: build-pypi
- name: Publish to PyPI
uses: pypa/gh-action-pypi-publish@release/v1
with:
verbose: true

View File

@ -41,3 +41,20 @@ jobs:
actions: write # For cleaning up cache
id-token: write # mandatory for trusted publishing
secrets: inherit
publish_pypi:
needs: [release]
if: vars.NIGHTLY_PYPI_PROJECT != ''
runs-on: ubuntu-latest
permissions:
id-token: write # mandatory for trusted publishing
steps:
- name: Download artifacts
uses: actions/download-artifact@v4
with:
path: dist
name: build-pypi
- name: Publish to PyPI
uses: pypa/gh-action-pypi-publish@release/v1
with:
verbose: true

View File

@ -2,10 +2,6 @@ name: Release
on:
workflow_call:
inputs:
prerelease:
required: false
default: true
type: boolean
source:
required: false
default: ''
@ -18,6 +14,10 @@ on:
required: false
default: ''
type: string
prerelease:
required: false
default: true
type: boolean
workflow_dispatch:
inputs:
source:
@ -278,11 +278,20 @@ jobs:
make clean-cache
python -m build --no-isolation .
- name: Upload artifacts
if: github.event_name != 'workflow_dispatch'
uses: actions/upload-artifact@v4
with:
name: build-pypi
path: |
dist/*
compression-level: 0
- name: Publish to PyPI
if: github.event_name == 'workflow_dispatch'
uses: pypa/gh-action-pypi-publish@release/v1
with:
verbose: true
attestations: false # Currently doesn't work w/ reusable workflows (breaks nightly)
publish:
needs: [prepare, build]

View File

@ -52,7 +52,7 @@ default = [
"pycryptodomex",
"requests>=2.32.2,<3",
"urllib3>=1.26.17,<3",
"websockets>=13.0",
"websockets>=13.0,<14",
]
curl-cffi = [
"curl-cffi==0.5.10; os_name=='nt' and implementation_name=='cpython'",

View File

@ -24,7 +24,7 @@ try:
from Crypto.Cipher import AES, PKCS1_OAEP, Blowfish, PKCS1_v1_5 # noqa: F401
from Crypto.Hash import CMAC, SHA1 # noqa: F401
from Crypto.PublicKey import RSA # noqa: F401
except ImportError:
except (ImportError, OSError):
__version__ = f'broken {__version__}'.strip()

View File

@ -1,5 +1,9 @@
from .common import InfoExtractor
from ..utils import strip_jsonp, unified_strdate
from ..utils import (
str_or_none,
traverse_obj,
url_or_none,
)
class ElPaisIE(InfoExtractor):
@ -7,34 +11,24 @@ class ElPaisIE(InfoExtractor):
IE_DESC = 'El País'
_TESTS = [{
'url': 'http://blogs.elpais.com/la-voz-de-inaki/2014/02/tiempo-nuevo-recetas-viejas.html',
'md5': '98406f301f19562170ec071b83433d55',
'info_dict': {
'id': 'tiempo-nuevo-recetas-viejas',
'ext': 'mp4',
'title': 'Tiempo nuevo, recetas viejas',
'description': 'De lunes a viernes, a partir de las ocho de la mañana, Iñaki Gabilondo nos cuenta su visión de la actualidad nacional e internacional.',
'upload_date': '20140206',
},
}, {
'url': 'http://elcomidista.elpais.com/elcomidista/2016/02/24/articulo/1456340311_668921.html#?id_externo_nwl=newsletter_diaria20160303t',
'md5': '3bd5b09509f3519d7d9e763179b013de',
'info_dict': {
'id': '1456340311_668921',
'ext': 'mp4',
'title': 'Cómo hacer el mejor café con cafetera italiana',
'description': 'Que sí, que las cápsulas son cómodas. Pero si le pides algo más a la vida, quizá deberías aprender a usar bien la cafetera italiana. No tienes más que ver este vídeo y seguir sus siete normas básicas.',
'upload_date': '20160303',
},
}, {
'url': 'http://elpais.com/elpais/2017/01/26/ciencia/1485456786_417876.html',
'md5': '9c79923a118a067e1a45789e1e0b0f9c',
'md5': 'cd8cba33f974f69ed82df788ad43eef8',
'info_dict': {
'id': '1485456786_417876',
'ext': 'mp4',
'title': 'Hallado un barco de la antigua Roma que naufragó en Baleares hace 1.800 años',
'description': 'La nave portaba cientos de ánforas y se hundió cerca de la isla de Cabrera por razones desconocidas',
'upload_date': '20170127',
'description': 'Un submarinista contempla el pecio de Cabrera, que contiene cientos de ánforas',
'thumbnail': 'https://imagenes.elpais.com/resizer/v2/https%3A%2F%2Fep01.epimg.net%2Felpais%2Fimagenes%2F2017%2F01%2F26%2Fciencia%2F1485456786_417876_1485523827_noticia_fotograma.jpg?auth=b9ed873402809633a5ac8bc154dcd13e468547d34bbd82e0808f9e2813eb7542&width=1960&height=1103&smart=true',
},
}, {
'url': 'https://elpais.com/gastronomia/el-comidista/2024-07-16/la-ensalada-de-pasta-mas-verde.html',
'md5': '3db968bf1d29b8fa723fd8cfb30d5d28',
'info_dict': {
'id': 'la-ensalada-de-pasta-mas-verde',
'ext': 'mp4',
'title': 'La ensalada de pasta más verde | EL COMIDISTA',
'description': 'La ensalada de pasta más verde | EL COMIDISTA',
'thumbnail': 'https://imagenes.elpais.com/resizer/v2/B4O2NY6B2FCE7KWOMO2CJH7FYQ.png?auth=bea914a842eba835a6ea92169acb94b977c5fe3a4564b2b69ef27ac9e7199668&width=1960&height=1103&smart=true',
},
}, {
'url': 'http://epv.elpais.com/epv/2017/02/14/programa_la_voz_de_inaki/1487062137_075943.html',
@ -42,51 +36,22 @@ class ElPaisIE(InfoExtractor):
'id': '1487062137_075943',
'ext': 'mp4',
'title': 'Disyuntivas',
'description': 'md5:a0fb1485c4a6a8a917e6f93878e66218',
'upload_date': '20170214',
},
'params': {
'skip_download': True,
'description': 'md5:0d538b71b6c2ec519fd7899811fb3f23',
'thumbnail': 'https://imagenes.elpais.com/resizer/v2/https%3A%2F%2Fep01.epimg.net%2Felpais%2Fimagenes%2F2017%2F02%2F14%2Fvideos%2F1487058850_493037_1487059369_noticia_fotograma.jpg?auth=1e1691499249851785dadbec92da3bfacdfef6cf6404845599c0c9295271d9e4&width=1960&height=1103&smart=true',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
prefix = self._html_search_regex(
r'var\s+url_cache\s*=\s*"([^"]+)";', webpage, 'URL prefix')
id_multimedia = self._search_regex(
r"id_multimedia\s*=\s*'([^']+)'", webpage, 'ID multimedia', default=None)
if id_multimedia:
url_info = self._download_json(
'http://elpais.com/vdpep/1/?pepid=' + id_multimedia, video_id, transform_source=strip_jsonp)
video_suffix = url_info['mp4']
else:
video_suffix = self._search_regex(
r"(?:URLMediaFile|urlVideo_\d+)\s*=\s*url_cache\s*\+\s*'([^']+)'", webpage, 'video URL')
video_url = prefix + video_suffix
thumbnail_suffix = self._search_regex(
r"(?:URLMediaStill|urlFotogramaFijo_\d+)\s*=\s*url_cache\s*\+\s*'([^']+)'",
webpage, 'thumbnail URL', default=None)
thumbnail = (
None if thumbnail_suffix is None
else prefix + thumbnail_suffix) or self._og_search_thumbnail(webpage)
title = self._html_search_regex(
(r"tituloVideo\s*=\s*'([^']+)'",
r'<h2 class="entry-header entry-title.*?>(.*?)</h2>',
r'<h1[^>]+class="titulo"[^>]*>([^<]+)'),
webpage, 'title', default=None) or self._og_search_title(webpage)
upload_date = unified_strdate(self._search_regex(
r'<p class="date-header date-int updated"\s+title="([^"]+)">',
webpage, 'upload date', default=None) or self._html_search_meta(
'datePublished', webpage, 'timestamp'))
video_info = self._search_json_ld(webpage, video_id)
return {
'id': video_id,
'url': video_url,
'title': title,
'description': self._og_search_description(webpage),
'thumbnail': thumbnail,
'upload_date': upload_date,
**traverse_obj(video_info, {
'title': ('title', {str_or_none}),
'url': ('url'),
'thumbnail': ('thumbnails', 0, 'url', {url_or_none}),
'description': ('description', {str_or_none}),
}),
}