mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-06-27 17:08:32 +00:00
Code Issues Projects Releases Wiki Activity

Merge 09908fc8e3 into 06c1a8cdff

Browse Source
This commit is contained in:
doe1080 2025-06-26 17:03:12 -07:00 committed by GitHub
commit 8a83c6bac9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 114 additions and 89 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
test/test_InfoExtractor.py
View File

@ -224,8 +224,15 @@ def test_search_json_ld_realworld(self):
} }
</script>''', </script>''',
{ {
'timestamp': 1636523400,
'title': 'md5:91fe569e952e4d146485740ae927662b', 'title': 'md5:91fe569e952e4d146485740ae927662b',
'categories': ['Κοινωνία'],
'creators': ['Ant1news'],
'description': 'md5:16756d0a18f33bf550e683d134a72f3c',
'modified_timestamp': 1636523573,
'release_timestamp': 1636523400,
'tags': 'count:6',
'thumbnails': [{'url': 'https://ant1media.azureedge.net/imgHandler/1100/a635c968-be71-447c-bf9c-80d843ece21e.jpg'}],
'uploader': 'Ant1news',
}, },
{'expected_type': 'NewsArticle'}, {'expected_type': 'NewsArticle'},
), ),

174
yt_dlp/extractor/allocine.py
View File

@ -1,124 +1,132 @@
import json
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
int_or_none, extract_attributes,
qualities, make_archive_id,
remove_end, str_or_none,
strip_or_none, )
try_get, from ..utils.traversal import (
unified_timestamp, find_element,
url_basename, require,
traverse_obj,
) )
class AllocineIE(InfoExtractor): class AllocineIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?:article|video|film)/(?:fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=|video-)(?P<id>[0-9]+)(?:\.html)?' IE_NAME = 'allocine'
IE_DESC = 'AlloCiné'
_VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?:article|video|film)/(?:fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=|video-)(?P<id>\d+)(?:\.html)?'
_TESTS = [{ _TESTS = [{
'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html', 'url': 'https://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html',
'md5': '0c9fcf59a841f65635fa300ac43d8269',
'info_dict': { 'info_dict': {
'id': '19546517', 'id': 'x8a20c7',
'display_id': '18635087',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Astérix - Le Domaine des Dieux Teaser VF', 'title': 'Teaser Astérix - Le Domaine des Dieux : les Romains font grève !',
'description': 'md5:4a754271d9c6f16c72629a8a993ee884', 'age_limit': 0,
'thumbnail': r're:http://.*\.jpg', 'creators': 'count:1',
'duration': 39, 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'timestamp': 1404273600, 'display_id': '18635087',
'duration': 40,
'like_count': int,
'modified_date': '20140702',
'modified_timestamp': 1404270000,
'release_date': '20140702',
'release_timestamp': 1404270000,
'tags': [],
'thumbnail': r're:https?://.+\.jpg',
'timestamp': 1404259200,
'upload_date': '20140702', 'upload_date': '20140702',
'uploader': 'AlloCiné',
'uploader_id': 'x5rjhv',
'view_count': int, 'view_count': int,
'_old_archive_ids': ['allocine 19546517'],
}, },
'add_ie': ['Dailymotion'],
}, { }, {
'url': 'http://www.allocine.fr/video/player_gen_cmedia=19540403&cfilm=222257.html', 'url': 'https://www.allocine.fr/video/player_gen_cmedia=19540403&cfilm=222257.html',
'md5': 'd0cdce5d2b9522ce279fdfec07ff16e0',
'info_dict': { 'info_dict': {
'id': '19540403', 'id': 'x8a48qo',
'display_id': '19540403',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Planes 2 Bande-annonce VF', 'title': 'Planes 2 Bande-annonce VF',
'description': 'Regardez la bande annonce du film Planes 2 (Planes 2 Bande-annonce VF). Planes 2, un film de Roberts Gannaway', 'age_limit': 0,
'thumbnail': r're:http://.*\.jpg', 'description': 'md5:3bb65456b814081d264318e661166268',
'duration': 69, 'display_id': '19540403',
'timestamp': 1385659800, 'duration': 69.0,
'like_count': int,
'tags': [],
'thumbnail': r're:https?://.+\.jpg',
'timestamp': 1385656200,
'upload_date': '20131128', 'upload_date': '20131128',
'uploader': 'Allociné',
'uploader_id': 'x5rjhv',
'view_count': int, 'view_count': int,
'_old_archive_ids': ['allocine 19540403'],
}, },
'add_ie': ['Dailymotion'],
}, { }, {
'url': 'http://www.allocine.fr/video/player_gen_cmedia=19544709&cfilm=181290.html', 'url': 'https://www.allocine.fr/video/player_gen_cmedia=19544709&cfilm=181290.html',
'md5': '101250fb127ef9ca3d73186ff22a47ce',
'info_dict': { 'info_dict': {
'id': '19544709', 'id': 'x8a1vly',
'display_id': '19544709',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Dragons 2 - Bande annonce finale VF', 'title': 'Dragons 2 - Bande annonce finale VF',
'description': 'md5:6cdd2d7c2687d4c6aafe80a35e17267a', 'age_limit': 0,
'thumbnail': r're:http://.*\.jpg', 'description': 'md5:1cda4f6c621f95fafe9c42dcac399b5f',
'duration': 144, 'display_id': '19544709',
'timestamp': 1397589900, 'duration': 144.0,
'like_count': int,
'tags': [],
'thumbnail': r're:https?://.+\.jpg',
'timestamp': 1397582700,
'upload_date': '20140415', 'upload_date': '20140415',
'uploader': 'Allociné',
'uploader_id': 'x5rjhv',
'view_count': int, 'view_count': int,
'_old_archive_ids': ['allocine 19544709'],
}, },
'add_ie': ['Dailymotion'],
}, { }, {
'url': 'http://www.allocine.fr/video/video-19550147/', 'url': 'https://www.allocine.fr/video/video-19550147/',
'md5': '3566c0668c0235e2d224fd8edb389f67',
'info_dict': { 'info_dict': {
'id': '19550147', 'id': 'x8a3u4k',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Faux Raccord N°123 - Les gaffes de Cliffhanger', 'title': 'Les gaffes de Cliffhanger',
'description': 'md5:bc734b83ffa2d8a12188d9eb48bb6354', 'age_limit': 0,
'thumbnail': r're:http://.*\.jpg', 'description': 'md5:f0f8daccb3a4687928edbc806d596b35',
'display_id': '19550147',
'duration': 346.0,
'like_count': int,
'tags': [],
'thumbnail': r're:https?://.+\.jpg',
'timestamp': 1418330280,
'upload_date': '20141211',
'uploader': 'Allociné',
'uploader_id': 'x5rjhv',
'view_count': int,
'_old_archive_ids': ['allocine 19550147'],
}, },
'add_ie': ['Dailymotion'],
}] }]
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
videos = traverse_obj(webpage, (
{find_element(cls='player player-auto-play js-player', html=True)},
{extract_attributes}, 'data-model', {json.loads}, 'videos'))
formats = [] dailymotion_id = traverse_obj(videos, (
quality = qualities(['ld', 'md', 'hd']) ..., 'idDailymotion', {str}, any, {require('Dailymotion ID')}))
old_id = traverse_obj(videos, (
model = self._html_search_regex( ..., 'id', {str_or_none}, any), default=display_id)
r'data-model="([^"]+)"', webpage, 'data model', default=None)
if model:
model_data = self._parse_json(model, display_id)
video = model_data['videos'][0]
title = video['title']
for video_url in video['sources'].values():
video_id, format_id = url_basename(video_url).split('_')[:2]
formats.append({
'format_id': format_id,
'quality': quality(format_id),
'url': video_url,
})
duration = int_or_none(video.get('duration'))
view_count = int_or_none(video.get('view_count'))
timestamp = unified_timestamp(try_get(
video, lambda x: x['added_at']['date'], str))
else:
video_id = display_id
media_data = self._download_json(
f'http://www.allocine.fr/ws/AcVisiondataV5.ashx?media={video_id}', display_id)
title = remove_end(strip_or_none(self._html_extract_title(webpage), ' - AlloCiné'))
for key, value in media_data['video'].items():
if not key.endswith('Path'):
continue
format_id = key[:-len('Path')]
formats.append({
'format_id': format_id,
'quality': quality(format_id),
'url': value,
})
duration, view_count, timestamp = [None] * 3
return { return {
'id': video_id, **self._search_json_ld(webpage, display_id),
'_old_archive_ids': [make_archive_id(self, old_id)],
'_type': 'url_transparent',
'display_id': display_id, 'display_id': display_id,
'title': title, 'ie_key': 'Dailymotion',
'description': self._og_search_description(webpage), 'url': f'https://www.dailymotion.com/video/{dailymotion_id}',
'thumbnail': self._og_search_thumbnail(webpage),
'duration': duration,
'timestamp': timestamp,
'view_count': view_count,
'formats': formats,
} }

20
yt_dlp/extractor/common.py
View File

@ -1745,11 +1745,21 @@ def traverse_json_ld(json_ld, at_top_level=True):
'timestamp': unified_timestamp(e.get('dateCreated')), 'timestamp': unified_timestamp(e.get('dateCreated')),
}) })
elif is_type(e, 'Article', 'NewsArticle'): elif is_type(e, 'Article', 'NewsArticle'):
info.update({ info.update(**traverse_obj(e, {
'timestamp': parse_iso8601(e.get('datePublished')), 'title': ('headline', {clean_html}, filter),
'title': unescapeHTML(e.get('headline')), 'alt_title': ('alternativeHeadline', {clean_html}, filter),
'description': unescapeHTML(e.get('articleBody') or e.get('description')), 'categories': ('articleSection', {clean_html}, filter, all, filter),
}) 'creators': ('author', (None, 'name'), {clean_html}, filter, all, filter),
'description': (('description', 'articleBody'), {clean_html}, filter, any),
'modified_timestamp': ('dateModified', {parse_iso8601}),
'release_timestamp': ('datePublished', {parse_iso8601}),
'tags': ('keywords', {clean_html}, {lambda x: x.split(',')}, ..., {str.strip}, filter, all, filter),
'thumbnails': ('image', ..., {
'url': ({str}, {unescapeHTML}, {self._proto_relative_url}, {url_or_none}),
}),
'timestamp': ('dateCreated', {parse_iso8601}),
'uploader': ('publisher', 'name', {clean_html}, filter),
}))
if is_type(traverse_obj(e, ('video', 0)), 'VideoObject'): if is_type(traverse_obj(e, ('video', 0)), 'VideoObject'):
extract_video_object(e['video'][0]) extract_video_object(e['video'][0])
elif is_type(traverse_obj(e, ('subjectOf', 0)), 'VideoObject'): elif is_type(traverse_obj(e, ('subjectOf', 0)), 'VideoObject'):