yt_dlp/extractor/telemb.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import remove_start
   5
   6
   7 class TeleMBIE(InfoExtractor):
   8     _WORKING = False
   9     _VALID_URL = r'https?://(?:www\.)?telemb\.be/(?P<display_id>.+?)_d_(?P<id>\d+)\.html'
  10     _TESTS = [
  11         {
  12             'url': 'http://www.telemb.be/mons-cook-with-danielle-des-cours-de-cuisine-en-anglais-_d_13466.html',
  13             'md5': 'f45ea69878516ba039835794e0f8f783',
  14             'info_dict': {
  15                 'id': '13466',
  16                 'display_id': 'mons-cook-with-danielle-des-cours-de-cuisine-en-anglais-',
  17                 'ext': 'mp4',
  18                 'title': 'Mons - Cook with Danielle : des cours de cuisine en anglais ! - Les reportages',
  19                 'description': 'md5:bc5225f47b17c309761c856ad4776265',
  20                 'thumbnail': r're:^http://.*\.(?:jpg|png)$',
  21             },
  22         },
  23         {
  24             # non-ASCII characters in download URL
  25             'url': 'http://telemb.be/les-reportages-havre-incendie-mortel_d_13514.html',
  26             'md5': '6e9682736e5ccd4eab7f21e855350733',
  27             'info_dict': {
  28                 'id': '13514',
  29                 'display_id': 'les-reportages-havre-incendie-mortel',
  30                 'ext': 'mp4',
  31                 'title': 'Havré - Incendie mortel - Les reportages',
  32                 'description': 'md5:5e54cb449acb029c2b7734e2d946bd4a',
  33                 'thumbnail': r're:^http://.*\.(?:jpg|png)$',
  34             },
  35         },
  36     ]
  37
  38     def _real_extract(self, url):
  39         mobj = self._match_valid_url(url)
  40         video_id = mobj.group('id')
  41         display_id = mobj.group('display_id')
  42
  43         webpage = self._download_webpage(url, display_id)
  44
  45         formats = []
  46         for video_url in re.findall(r'file\s*:\s*"([^"]+)"', webpage):
  47             fmt = {
  48                 'url': video_url,
  49                 'format_id': video_url.split(':')[0],
  50             }
  51             rtmp = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+))/(?P<playpath>mp4:.+)$', video_url)
  52             if rtmp:
  53                 fmt.update({
  54                     'play_path': rtmp.group('playpath'),
  55                     'app': rtmp.group('app'),
  56                     'player_url': 'http://p.jwpcdn.com/6/10/jwplayer.flash.swf',
  57                     'page_url': 'http://www.telemb.be',
  58                     'preference': -10,
  59                 })
  60             formats.append(fmt)
  61
  62         title = remove_start(self._og_search_title(webpage), 'TéléMB : ')
  63         description = self._html_search_regex(
  64             r'<meta property="og:description" content="(.+?)" />',
  65             webpage, 'description', fatal=False)
  66         thumbnail = self._og_search_thumbnail(webpage)
  67
  68         return {
  69             'id': video_id,
  70             'display_id': display_id,
  71             'title': title,
  72             'description': description,
  73             'thumbnail': thumbnail,
  74             'formats': formats,
  75         }