yt_dlp/extractor/wat.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_str
   3 from ..utils import (
   4     ExtractorError,
   5     int_or_none,
   6     try_get,
   7     unified_strdate,
   8 )
   9
  10
  11 class WatIE(InfoExtractor):
  12     _VALID_URL = r'(?:wat:|https?://(?:www\.)?wat\.tv/video/.*-)(?P<id>[0-9a-z]+)'
  13     IE_NAME = 'wat.tv'
  14     _TESTS = [
  15         {
  16             'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html',
  17             'info_dict': {
  18                 'id': '11713067',
  19                 'ext': 'mp4',
  20                 'title': 'Soupe de figues à l\'orange et aux épices',
  21                 'description': 'Retrouvez l\'émission "Petits plats en équilibre", diffusée le 18 août 2014.',
  22                 'upload_date': '20140819',
  23                 'duration': 120,
  24             },
  25             'params': {
  26                 # m3u8 download
  27                 'skip_download': True,
  28             },
  29             'expected_warnings': ['HTTP Error 404'],
  30             'skip': 'This content is no longer available',
  31         },
  32         {
  33             'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html',
  34             'md5': 'b16574df2c3cd1a36ca0098f2a791925',
  35             'info_dict': {
  36                 'id': '11713075',
  37                 'ext': 'mp4',
  38                 'title': 'Grégory Lemarchal, une voix d\'ange depuis 10 ans (1/3)',
  39                 'upload_date': '20140816',
  40             },
  41             'expected_warnings': ["Ce contenu n'est pas disponible pour l'instant."],
  42             'skip': 'This content is no longer available',
  43         },
  44     ]
  45     _GEO_BYPASS = False
  46
  47     def _real_extract(self, url):
  48         video_id = self._match_id(url)
  49         video_id = video_id if video_id.isdigit() and len(video_id) > 6 else compat_str(int(video_id, 36))
  50
  51         # 'contentv4' is used in the website, but it also returns the related
  52         # videos, we don't need them
  53         # video_data = self._download_json(
  54         #     'http://www.wat.tv/interface/contentv4s/' + video_id, video_id)
  55         video_data = self._download_json(
  56             'https://mediainfo.tf1.fr/mediainfocombo/' + video_id,
  57             video_id, query={'context': 'MYTF1', 'pver': '4020003'})
  58         video_info = video_data['media']
  59
  60         error_desc = video_info.get('error_desc')
  61         if error_desc:
  62             if video_info.get('error_code') == 'GEOBLOCKED':
  63                 self.raise_geo_restricted(error_desc, video_info.get('geoList'))
  64             raise ExtractorError(error_desc, expected=True)
  65
  66         title = video_info['title']
  67
  68         formats = []
  69         subtitles = {}
  70
  71         def extract_formats(manifest_urls):
  72             for f, f_url in manifest_urls.items():
  73                 if not f_url:
  74                     continue
  75                 if f in ('dash', 'mpd'):
  76                     fmts, subs = self._extract_mpd_formats_and_subtitles(
  77                         f_url.replace('://das-q1.tf1.fr/', '://das-q1-ssl.tf1.fr/'),
  78                         video_id, mpd_id='dash', fatal=False)
  79                 elif f == 'hls':
  80                     fmts, subs = self._extract_m3u8_formats_and_subtitles(
  81                         f_url, video_id, 'mp4',
  82                         'm3u8_native', m3u8_id='hls', fatal=False)
  83                 else:
  84                     continue
  85                 formats.extend(fmts)
  86                 self._merge_subtitles(subs, target=subtitles)
  87
  88         delivery = video_data.get('delivery') or {}
  89         extract_formats({delivery.get('format'): delivery.get('url')})
  90         if not formats:
  91             if delivery.get('drm'):
  92                 self.report_drm(video_id)
  93             manifest_urls = self._download_json(
  94                 'http://www.wat.tv/get/webhtml/' + video_id, video_id, fatal=False)
  95             if manifest_urls:
  96                 extract_formats(manifest_urls)
  97
  98         return {
  99             'id': video_id,
 100             'title': title,
 101             'thumbnail': video_info.get('preview'),
 102             'upload_date': unified_strdate(try_get(
 103                 video_data, lambda x: x['mediametrie']['chapters'][0]['estatS4'])),
 104             'duration': int_or_none(video_info.get('duration')),
 105             'formats': formats,
 106             'subtitles': subtitles,
 107         }