Merge remote-tracking branch 'rzhxeo/crunchyroll'
[youtube-dl] / youtube_dl / extractor / toutv.py
1 # coding: utf-8
2 import re
3
4 from .common import InfoExtractor
5 from ..utils import (
6     ExtractorError,
7     unified_strdate,
8 )
9
10
11 class TouTvIE(InfoExtractor):
12     IE_NAME = u'tou.tv'
13     _VALID_URL = r'https?://www\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/(?P<episode>S[0-9]+E[0-9]+)))'
14
15     _TEST = {
16         u'url': u'http://www.tou.tv/30-vies/S04E41',
17         u'file': u'30-vies_S04E41.mp4',
18         u'info_dict': {
19             u'title': u'30 vies Saison 4 / Épisode 41',
20             u'description': u'md5:da363002db82ccbe4dafeb9cab039b09',
21             u'age_limit': 8,
22             u'uploader': u'Groupe des Nouveaux Médias',
23             u'duration': 1296,
24             u'upload_date': u'20131118',
25             u'thumbnail': u'http://static.tou.tv/medias/images/2013-11-18_19_00_00_30VIES_0341_01_L.jpeg',
26         },
27         u'params': {
28             u'skip_download': True,  # Requires rtmpdump
29         },
30         u'skip': 'Only available in Canada'
31     }
32
33     def _real_extract(self, url):
34         mobj = re.match(self._VALID_URL, url)
35         video_id = mobj.group('id')
36         webpage = self._download_webpage(url, video_id)
37
38         mediaId = self._search_regex(
39             r'"idMedia":\s*"([^"]+)"', webpage, u'media ID')
40
41         streams_url = u'http://release.theplatform.com/content.select?pid=' + mediaId
42         streams_doc = self._download_xml(
43             streams_url, video_id, note=u'Downloading stream list')
44
45         video_url = next(n.text
46                          for n in streams_doc.findall('.//choice/url')
47                          if u'//ad.doubleclick' not in n.text)
48         if video_url.endswith('/Unavailable.flv'):
49             raise ExtractorError(
50                 u'Access to this video is blocked from outside of Canada',
51                 expected=True)
52
53         duration_str = self._html_search_meta(
54             'video:duration', webpage, u'duration')
55         duration = int(duration_str) if duration_str else None
56         upload_date_str = self._html_search_meta(
57             'video:release_date', webpage, u'upload date')
58         upload_date = unified_strdate(upload_date_str) if upload_date_str else None
59
60         return {
61             'id': video_id,
62             'title': self._og_search_title(webpage),
63             'url': video_url,
64             'description': self._og_search_description(webpage),
65             'uploader': self._dc_search_uploader(webpage),
66             'thumbnail': self._og_search_thumbnail(webpage),
67             'age_limit': self._media_rating_search(webpage),
68             'duration': duration,
69             'upload_date': upload_date,
70             'ext': 'mp4',
71         }