youtube_dl/extractor/toutv.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 (
   8     ExtractorError,
   9     unified_strdate,
  10 )
  11
  12
  13 class TouTvIE(InfoExtractor):
  14     IE_NAME = 'tou.tv'
  15     _VALID_URL = r'https?://www\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/(?P<episode>S[0-9]+E[0-9]+)))'
  16
  17     _TEST = {
  18         'url': 'http://www.tou.tv/30-vies/S04E41',
  19         'file': '30-vies_S04E41.mp4',
  20         'info_dict': {
  21             'title': '30 vies Saison 4 / Épisode 41',
  22             'description': 'md5:da363002db82ccbe4dafeb9cab039b09',
  23             'age_limit': 8,
  24             'uploader': 'Groupe des Nouveaux Médias',
  25             'duration': 1296,
  26             'upload_date': '20131118',
  27             'thumbnail': 'http://static.tou.tv/medias/images/2013-11-18_19_00_00_30VIES_0341_01_L.jpeg',
  28         },
  29         'params': {
  30             'skip_download': True,  # Requires rtmpdump
  31         },
  32         'skip': 'Only available in Canada'
  33     }
  34
  35     def _real_extract(self, url):
  36         mobj = re.match(self._VALID_URL, url)
  37         video_id = mobj.group('id')
  38         webpage = self._download_webpage(url, video_id)
  39
  40         mediaId = self._search_regex(
  41             r'"idMedia":\s*"([^"]+)"', webpage, 'media ID')
  42
  43         streams_url = 'http://release.theplatform.com/content.select?pid=' + mediaId
  44         streams_doc = self._download_xml(
  45             streams_url, video_id, note='Downloading stream list')
  46
  47         video_url = next(n.text
  48                          for n in streams_doc.findall('.//choice/url')
  49                          if '//ad.doubleclick' not in n.text)
  50         if video_url.endswith('/Unavailable.flv'):
  51             raise ExtractorError(
  52                 'Access to this video is blocked from outside of Canada',
  53                 expected=True)
  54
  55         duration_str = self._html_search_meta(
  56             'video:duration', webpage, 'duration')
  57         duration = int(duration_str) if duration_str else None
  58         upload_date_str = self._html_search_meta(
  59             'video:release_date', webpage, 'upload date')
  60         upload_date = unified_strdate(upload_date_str) if upload_date_str else None
  61
  62         return {
  63             'id': video_id,
  64             'title': self._og_search_title(webpage),
  65             'url': video_url,
  66             'description': self._og_search_description(webpage),
  67             'uploader': self._dc_search_uploader(webpage),
  68             'thumbnail': self._og_search_thumbnail(webpage),
  69             'age_limit': self._media_rating_search(webpage),
  70             'duration': duration,
  71             'upload_date': upload_date,
  72             'ext': 'mp4',
  73         }