]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/toutv.py
Update changelog.
[youtubedl] / 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 'info_dict': {
20 'id': '30-vies_S04E41',
21 'ext': 'mp4',
22 'title': '30 vies Saison 4 / Épisode 41',
23 'description': 'md5:da363002db82ccbe4dafeb9cab039b09',
24 'age_limit': 8,
25 'uploader': 'Groupe des Nouveaux Médias',
26 'duration': 1296,
27 'upload_date': '20131118',
28 'thumbnail': 'http://static.tou.tv/medias/images/2013-11-18_19_00_00_30VIES_0341_01_L.jpeg',
29 },
30 'params': {
31 'skip_download': True, # Requires rtmpdump
32 },
33 'skip': 'Only available in Canada'
34 }
35
36 def _real_extract(self, url):
37 mobj = re.match(self._VALID_URL, url)
38 video_id = mobj.group('id')
39 webpage = self._download_webpage(url, video_id)
40
41 mediaId = self._search_regex(
42 r'"idMedia":\s*"([^"]+)"', webpage, 'media ID')
43
44 streams_url = 'http://release.theplatform.com/content.select?pid=' + mediaId
45 streams_doc = self._download_xml(
46 streams_url, video_id, note='Downloading stream list')
47
48 video_url = next(n.text
49 for n in streams_doc.findall('.//choice/url')
50 if '//ad.doubleclick' not in n.text)
51 if video_url.endswith('/Unavailable.flv'):
52 raise ExtractorError(
53 'Access to this video is blocked from outside of Canada',
54 expected=True)
55
56 duration_str = self._html_search_meta(
57 'video:duration', webpage, 'duration')
58 duration = int(duration_str) if duration_str else None
59 upload_date_str = self._html_search_meta(
60 'video:release_date', webpage, 'upload date')
61 upload_date = unified_strdate(upload_date_str) if upload_date_str else None
62
63 return {
64 'id': video_id,
65 'title': self._og_search_title(webpage),
66 'url': video_url,
67 'description': self._og_search_description(webpage),
68 'uploader': self._dc_search_uploader(webpage),
69 'thumbnail': self._og_search_thumbnail(webpage),
70 'age_limit': self._media_rating_search(webpage),
71 'duration': duration,
72 'upload_date': upload_date,
73 'ext': 'mp4',
74 }