-# coding: utf-8
-from __future__ import unicode_literals
+import json
from .common import InfoExtractor
-from ..compat import compat_str
+from ..utils import (
+ int_or_none,
+ parse_iso8601,
+ try_get,
+)
class TF1IE(InfoExtractor):
- """TF1 uses the wat.tv player."""
- _VALID_URL = r'https?://(?:(?:videos|www|lci)\.tf1|(?:www\.)?(?:tfou|ushuaiatv|histoire|tvbreizh))\.fr/(?:[^/]+/)*(?P<id>[^/?#.]+)'
+ _VALID_URL = r'https?://(?:www\.)?tf1\.fr/[^/]+/(?P<program_slug>[^/]+)/videos/(?P<id>[^/?&#]+)\.html'
_TESTS = [{
- 'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
+ 'url': 'https://www.tf1.fr/tmc/quotidien-avec-yann-barthes/videos/quotidien-premiere-partie-11-juin-2019.html',
'info_dict': {
- 'id': '10635995',
+ 'id': '13641379',
'ext': 'mp4',
- 'title': 'Citroën Grand C4 Picasso 2013 : présentation officielle',
- 'description': 'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.',
+ 'title': 'md5:f392bc52245dc5ad43771650c96fb620',
+ 'description': 'md5:a02cdb217141fb2d469d6216339b052f',
+ 'upload_date': '20190611',
+ 'timestamp': 1560273989,
+ 'duration': 1738,
+ 'series': 'Quotidien avec Yann Barthès',
+ 'tags': ['intégrale', 'quotidien', 'Replay'],
},
'params': {
# Sometimes wat serves the whole file with the --test option
'skip_download': True,
},
- 'expected_warnings': ['HTTP Error 404'],
}, {
- 'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html',
+ 'url': 'https://www.tf1.fr/tmc/burger-quiz/videos/burger-quiz-du-19-aout-2023-s03-episode-21-85585666.html',
'info_dict': {
- 'id': 'le-grand-mysterioso-chuggington-7085291-739',
+ 'id': '14010600',
'ext': 'mp4',
- 'title': 'Le grand Mystérioso - Chuggington',
- 'description': 'Le grand Mystérioso - Emery rêve qu\'un article lui soit consacré dans le journal.',
- 'upload_date': '20150103',
- },
- 'params': {
- # Sometimes wat serves the whole file with the --test option
- 'skip_download': True,
+ 'title': 'Burger Quiz - S03 EP21 avec Eye Haidara, Anne Depétrini, Jonathan Zaccaï et Pio Marmaï',
+ 'thumbnail': 'https://photos.tf1.fr/1280/720/burger-quiz-11-9adb79-0@1x.jpg',
+ 'description': 'Manu Payet recevra Eye Haidara, Anne Depétrini, Jonathan Zaccaï et Pio Marmaï.',
+ 'upload_date': '20230819',
+ 'timestamp': 1692469471,
+ 'season_number': 3,
+ 'series': 'Burger Quiz',
+ 'episode_number': 21,
+ 'season': 'Season 3',
+ 'tags': 'count:13',
+ 'episode': 'Episode 21',
+ 'duration': 2312
},
- 'skip': 'HTTP Error 410: Gone',
+ 'params': {'skip_download': 'm3u8'},
}, {
'url': 'http://www.tf1.fr/tf1/koh-lanta/videos/replay-koh-lanta-22-mai-2015.html',
'only_matching': True,
- }, {
- 'url': 'http://lci.tf1.fr/sept-a-huit/videos/sept-a-huit-du-24-mai-2015-8611550.html',
- 'only_matching': True,
}, {
'url': 'http://www.tf1.fr/hd1/documentaire/videos/mylene-farmer-d-une-icone.html',
'only_matching': True,
- }, {
- 'url': 'https://www.tf1.fr/tmc/quotidien-avec-yann-barthes/videos/quotidien-premiere-partie-11-juin-2019.html',
- 'info_dict': {
- 'id': '13641379',
- 'ext': 'mp4',
- 'title': 'md5:f392bc52245dc5ad43771650c96fb620',
- 'description': 'md5:44bc54f0a21322f5b91d68e76a544eae',
- 'upload_date': '20190611',
- },
- 'params': {
- # Sometimes wat serves the whole file with the --test option
- 'skip_download': True,
- },
}]
def _real_extract(self, url):
- video_id = self._match_id(url)
-
- webpage = self._download_webpage(url, video_id)
-
- wat_id = None
+ program_slug, slug = self._match_valid_url(url).groups()
+ video = self._download_json(
+ 'https://www.tf1.fr/graphql/web', slug, query={
+ 'id': '9b80783950b85247541dd1d851f9cc7fa36574af015621f853ab111a679ce26f',
+ 'variables': json.dumps({
+ 'programSlug': program_slug,
+ 'slug': slug,
+ })
+ })['data']['videoBySlug']
+ wat_id = video['streamId']
- data = self._parse_json(
- self._search_regex(
- r'__APOLLO_STATE__\s*=\s*({.+?})\s*(?:;|</script>)', webpage,
- 'data', default='{}'), video_id, fatal=False)
+ tags = []
+ for tag in (video.get('tags') or []):
+ label = tag.get('label')
+ if not label:
+ continue
+ tags.append(label)
- if data:
- try:
- wat_id = next(
- video.get('streamId')
- for key, video in data.items()
- if isinstance(video, dict)
- and video.get('slug') == video_id)
- if not isinstance(wat_id, compat_str) or not wat_id.isdigit():
- wat_id = None
- except StopIteration:
- pass
+ decoration = video.get('decoration') or {}
- if not wat_id:
- wat_id = self._html_search_regex(
- (r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1',
- r'(["\']?)streamId\1\s*:\s*(["\']?)(?P<id>\d+)\2'),
- webpage, 'wat id', group='id')
+ thumbnails = []
+ for source in (try_get(decoration, lambda x: x['image']['sources'], list) or []):
+ source_url = source.get('url')
+ if not source_url:
+ continue
+ thumbnails.append({
+ 'url': source_url,
+ 'width': int_or_none(source.get('width')),
+ })
- return self.url_result('wat:%s' % wat_id, 'Wat')
+ return {
+ '_type': 'url_transparent',
+ 'id': wat_id,
+ 'url': 'wat:' + wat_id,
+ 'title': video.get('title'),
+ 'thumbnails': thumbnails,
+ 'description': decoration.get('description'),
+ 'timestamp': parse_iso8601(video.get('date')),
+ 'duration': int_or_none(try_get(video, lambda x: x['publicPlayingInfos']['duration'])),
+ 'tags': tags,
+ 'series': decoration.get('programLabel'),
+ 'season_number': int_or_none(video.get('season')),
+ 'episode_number': int_or_none(video.get('episode')),
+ }
projects / yt-dlp.git / blobdiff