yt_dlp/extractor/wat.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     int_or_none,
   5     try_get,
   6     unified_strdate,
   7 )
   8
   9
  10 class WatIE(InfoExtractor):
  11     _VALID_URL = r'(?:wat:|https?://(?:www\.)?wat\.tv/video/.*-)(?P<id>[0-9a-z]+)'
  12     IE_NAME = 'wat.tv'
  13     _TESTS = [
  14         {
  15             'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html',
  16             'info_dict': {
  17                 'id': '11713067',
  18                 'ext': 'mp4',
  19                 'title': 'Soupe de figues à l\'orange et aux épices',
  20                 'description': 'Retrouvez l\'émission "Petits plats en équilibre", diffusée le 18 août 2014.',
  21                 'upload_date': '20140819',
  22                 'duration': 120,
  23             },
  24             'params': {
  25                 # m3u8 download
  26                 'skip_download': True,
  27             },
  28             'expected_warnings': ['HTTP Error 404'],
  29             'skip': 'This content is no longer available',
  30         },
  31         {
  32             'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html',
  33             'md5': 'b16574df2c3cd1a36ca0098f2a791925',
  34             'info_dict': {
  35                 'id': '11713075',
  36                 'ext': 'mp4',
  37                 'title': 'Grégory Lemarchal, une voix d\'ange depuis 10 ans (1/3)',
  38                 'upload_date': '20140816',
  39             },
  40             'expected_warnings': ["Ce contenu n'est pas disponible pour l'instant."],
  41             'skip': 'This content is no longer available',
  42         },
  43         {
  44             'url': 'wat:14010600',
  45             'info_dict': {
  46                 'id': '14010600',
  47                 'title': 'Burger Quiz - S03 EP21 avec Eye Haidara, Anne Depétrini, Jonathan Zaccaï et Pio Marmaï',
  48                 'thumbnail': 'https://photos.tf1.fr/1280/720/burger-quiz-11-9adb79-0@1x.jpg',
  49                 'upload_date': '20230819',
  50                 'duration': 2312,
  51                 'ext': 'mp4',
  52             },
  53             'params': {'skip_download': 'm3u8'},
  54         },
  55     ]
  56     _GEO_BYPASS = False
  57
  58     def _real_extract(self, url):
  59         video_id = self._match_id(url)
  60         video_id = video_id if video_id.isdigit() and len(video_id) > 6 else str(int(video_id, 36))
  61
  62         # 'contentv4' is used in the website, but it also returns the related
  63         # videos, we don't need them
  64         # video_data = self._download_json(
  65         #     'http://www.wat.tv/interface/contentv4s/' + video_id, video_id)
  66         video_data = self._download_json(
  67             'https://mediainfo.tf1.fr/mediainfocombo/' + video_id,
  68             video_id, query={'pver': '5010000'})
  69         video_info = video_data['media']
  70
  71         error_desc = video_info.get('error_desc')
  72         if error_desc:
  73             if video_info.get('error_code') == 'GEOBLOCKED':
  74                 self.raise_geo_restricted(error_desc, video_info.get('geoList'))
  75             raise ExtractorError(error_desc, expected=True)
  76
  77         title = video_info['title']
  78
  79         formats = []
  80         subtitles = {}
  81
  82         def extract_formats(manifest_urls):
  83             for f, f_url in manifest_urls.items():
  84                 if not f_url:
  85                     continue
  86                 if f in ('dash', 'mpd'):
  87                     fmts, subs = self._extract_mpd_formats_and_subtitles(
  88                         f_url.replace('://das-q1.tf1.fr/', '://das-q1-ssl.tf1.fr/'),
  89                         video_id, mpd_id='dash', fatal=False)
  90                 elif f == 'hls':
  91                     fmts, subs = self._extract_m3u8_formats_and_subtitles(
  92                         f_url, video_id, 'mp4',
  93                         'm3u8_native', m3u8_id='hls', fatal=False)
  94                 else:
  95                     continue
  96                 formats.extend(fmts)
  97                 self._merge_subtitles(subs, target=subtitles)
  98
  99         delivery = video_data.get('delivery') or {}
 100         extract_formats({delivery.get('format'): delivery.get('url')})
 101         if not formats:
 102             if delivery.get('drm'):
 103                 self.report_drm(video_id)
 104             manifest_urls = self._download_json(
 105                 'http://www.wat.tv/get/webhtml/' + video_id, video_id, fatal=False)
 106             if manifest_urls:
 107                 extract_formats(manifest_urls)
 108
 109         return {
 110             'id': video_id,
 111             'title': title,
 112             'thumbnail': video_info.get('preview'),
 113             'upload_date': unified_strdate(try_get(
 114                 video_data, lambda x: x['mediametrie']['chapters'][0]['estatS4'])),
 115             'duration': int_or_none(video_info.get('duration')),
 116             'formats': formats,
 117             'subtitles': subtitles,
 118         }