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