[ie/dropbox] Fix password-protected video extraction (#11636)
[yt-dlp3.git] / yt_dlp / extractor / canalalpha.py
blob3a0df95450ef3bedbfb86a43bdd7450dae5d6218
1 from .common import InfoExtractor
2 from ..utils import (
3 clean_html,
4 dict_get,
5 try_get,
6 unified_strdate,
10 class CanalAlphaIE(InfoExtractor):
11 _VALID_URL = r'https?://(?:www\.)?canalalpha\.ch/play/[^/]+/[^/]+/(?P<id>\d+)/?.*'
13 _TESTS = [{
14 'url': 'https://www.canalalpha.ch/play/le-journal/episode/24520/jeudi-28-octobre-2021',
15 'info_dict': {
16 'id': '24520',
17 'ext': 'mp4',
18 'title': 'Jeudi 28 octobre 2021',
19 'description': 'md5:d30c6c3e53f8ad40d405379601973b30',
20 'thumbnail': 'https://static.canalalpha.ch/poster/journal/journal_20211028.jpg',
21 'upload_date': '20211028',
22 'duration': 1125,
24 'params': {'skip_download': True},
25 }, {
26 'url': 'https://www.canalalpha.ch/play/le-journal/topic/24512/la-poste-fait-de-neuchatel-un-pole-cryptographique',
27 'info_dict': {
28 'id': '24512',
29 'ext': 'mp4',
30 'title': 'La Poste fait de Neuchâtel un pôle cryptographique',
31 'description': 'md5:4ba63ae78a0974d1a53d6703b6e1dedf',
32 'thumbnail': 'https://static.canalalpha.ch/poster/news/news_39712.jpg',
33 'upload_date': '20211028',
34 'duration': 138,
36 'params': {'skip_download': True},
37 }, {
38 'url': 'https://www.canalalpha.ch/play/eureka/episode/24484/ces-innovations-qui-veulent-rendre-lagriculture-plus-durable',
39 'info_dict': {
40 'id': '24484',
41 'ext': 'mp4',
42 'title': 'Ces innovations qui veulent rendre l’agriculture plus durable',
43 'description': 'md5:85d594a3b5dc6ccfc4a85aba6e73b129',
44 'thumbnail': 'https://static.canalalpha.ch/poster/magazine/magazine_10236.jpg',
45 'upload_date': '20211026',
46 'duration': 360,
48 'params': {'skip_download': True},
49 }, {
50 'url': 'https://www.canalalpha.ch/play/avec-le-temps/episode/23516/redonner-de-leclat-grace-au-polissage',
51 'info_dict': {
52 'id': '23516',
53 'ext': 'mp4',
54 'title': 'Redonner de l\'éclat grâce au polissage',
55 'description': 'md5:0d8fbcda1a5a4d6f6daa3165402177e1',
56 'thumbnail': 'https://static.canalalpha.ch/poster/magazine/magazine_9990.png',
57 'upload_date': '20210726',
58 'duration': 360,
60 'params': {'skip_download': True},
61 }, {
62 'url': 'https://www.canalalpha.ch/play/le-journal/topic/33500/encore-des-mesures-deconomie-dans-le-jura',
63 'info_dict': {
64 'id': '33500',
65 'ext': 'mp4',
66 'title': 'Encore des mesures d\'économie dans le Jura',
67 'description': 'md5:938b5b556592f2d1b9ab150268082a80',
68 'thumbnail': 'https://static.canalalpha.ch/poster/news/news_46665.jpg',
69 'upload_date': '20240411',
70 'duration': 105,
74 def _real_extract(self, url):
75 video_id = self._match_id(url)
76 webpage = self._download_webpage(url, video_id)
77 data_json = self._parse_json(self._search_regex(
78 r'window\.__SERVER_STATE__\s?=\s?({(?:(?!};)[^"]|"([^"]|\\")*")+})\s?;',
79 webpage, 'data_json'), video_id)['1']['data']['data']
80 manifests = try_get(data_json, lambda x: x['video']['manifests'], expected_type=dict) or {}
81 subtitles = {}
82 formats = [{
83 'url': video['$url'],
84 'ext': 'mp4',
85 'width': try_get(video, lambda x: x['res']['width'], expected_type=int),
86 'height': try_get(video, lambda x: x['res']['height'], expected_type=int),
87 } for video in try_get(data_json, lambda x: x['video']['mp4'], expected_type=list) or [] if video.get('$url')]
88 if manifests.get('hls'):
89 fmts, subs = self._extract_m3u8_formats_and_subtitles(
90 manifests['hls'], video_id, m3u8_id='hls', fatal=False)
91 formats.extend(fmts)
92 self._merge_subtitles(subs, target=subtitles)
93 if manifests.get('dash'):
94 fmts, subs = self._extract_mpd_formats_and_subtitles(
95 manifests['dash'], video_id, mpd_id='dash', fatal=False)
96 formats.extend(fmts)
97 self._merge_subtitles(subs, target=subtitles)
98 return {
99 'id': video_id,
100 'title': data_json.get('title').strip(),
101 'description': clean_html(dict_get(data_json, ('longDesc', 'shortDesc'))),
102 'thumbnail': data_json.get('poster'),
103 'upload_date': unified_strdate(dict_get(data_json, ('webPublishAt', 'featuredAt', 'diffusionDate'))),
104 'duration': try_get(data_json, lambda x: x['video']['duration'], expected_type=int),
105 'formats': formats,
106 'subtitles': subtitles,