Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/telemb.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import remove_start
   8
   9
  10 class TeleMBIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?telemb\.be/(?P<display_id>.+?)_d_(?P<id>\d+)\.html'
  12     _TESTS = [
  13         {
  14             'url': 'http://www.telemb.be/mons-cook-with-danielle-des-cours-de-cuisine-en-anglais-_d_13466.html',
  15             'md5': 'f45ea69878516ba039835794e0f8f783',
  16             'info_dict': {
  17                 'id': '13466',
  18                 'display_id': 'mons-cook-with-danielle-des-cours-de-cuisine-en-anglais-',
  19                 'ext': 'mp4',
  20                 'title': 'Mons - Cook with Danielle : des cours de cuisine en anglais ! - Les reportages',
  21                 'description': 'md5:bc5225f47b17c309761c856ad4776265',
  22                 'thumbnail': r're:^http://.*\.(?:jpg|png)$',
  23             }
  24         },
  25         {
  26             # non-ASCII characters in download URL
  27             'url': 'http://telemb.be/les-reportages-havre-incendie-mortel_d_13514.html',
  28             'md5': '6e9682736e5ccd4eab7f21e855350733',
  29             'info_dict': {
  30                 'id': '13514',
  31                 'display_id': 'les-reportages-havre-incendie-mortel',
  32                 'ext': 'mp4',
  33                 'title': 'Havré - Incendie mortel - Les reportages',
  34                 'description': 'md5:5e54cb449acb029c2b7734e2d946bd4a',
  35                 'thumbnail': r're:^http://.*\.(?:jpg|png)$',
  36             }
  37         },
  38     ]
  39
  40     def _real_extract(self, url):
  41         mobj = re.match(self._VALID_URL, url)
  42         video_id = mobj.group('id')
  43         display_id = mobj.group('display_id')
  44
  45         webpage = self._download_webpage(url, display_id)
  46
  47         formats = []
  48         for video_url in re.findall(r'file\s*:\s*"([^"]+)"', webpage):
  49             fmt = {
  50                 'url': video_url,
  51                 'format_id': video_url.split(':')[0]
  52             }
  53             rtmp = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+))/(?P<playpath>mp4:.+)$', video_url)
  54             if rtmp:
  55                 fmt.update({
  56                     'play_path': rtmp.group('playpath'),
  57                     'app': rtmp.group('app'),
  58                     'player_url': 'http://p.jwpcdn.com/6/10/jwplayer.flash.swf',
  59                     'page_url': 'http://www.telemb.be',
  60                     'preference': -1,
  61                 })
  62             formats.append(fmt)
  63         self._sort_formats(formats)
  64
  65         title = remove_start(self._og_search_title(webpage), 'TéléMB : ')
  66         description = self._html_search_regex(
  67             r'<meta property="og:description" content="(.+?)" />',
  68             webpage, 'description', fatal=False)
  69         thumbnail = self._og_search_thumbnail(webpage)
  70
  71         return {
  72             'id': video_id,
  73             'display_id': display_id,
  74             'title': title,
  75             'description': description,
  76             'thumbnail': thumbnail,
  77             'formats': formats,
  78         }