X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ftoutv.py;h=4797d1310aaeec2664d822c052f26be5ea5210af;hb=4080530624eda994d535e1a01c38ddd6d9aa3805;hp=73ea67da90fb3215e984a68fc577d8125e6a6cfb;hpb=59040888112e7e5a22ef17bacc27ca88d58a5d92;p=youtube-dl diff --git a/youtube_dl/extractor/toutv.py b/youtube_dl/extractor/toutv.py index 73ea67da9..4797d1310 100644 --- a/youtube_dl/extractor/toutv.py +++ b/youtube_dl/extractor/toutv.py @@ -1,6 +1,7 @@ # coding: utf-8 +from __future__ import unicode_literals + import re -import xml.etree.ElementTree from .common import InfoExtractor from ..utils import ( @@ -10,25 +11,26 @@ from ..utils import ( class TouTvIE(InfoExtractor): - IE_NAME = u'tou.tv' + IE_NAME = 'tou.tv' _VALID_URL = r'https?://www\.tou\.tv/(?P[a-zA-Z0-9_-]+(?:/(?PS[0-9]+E[0-9]+)))' _TEST = { - u'url': u'http://www.tou.tv/30-vies/S04E41', - u'file': u'30-vies_S04E41.mp4', - u'info_dict': { - u'title': u'30 vies Saison 4 / Épisode 41', - u'description': u'md5:da363002db82ccbe4dafeb9cab039b09', - u'age_limit': 8, - u'uploader': u'Groupe des Nouveaux Médias', - u'duration': 1296, - u'upload_date': u'20131118', - u'thumbnail': u'http://static.tou.tv/medias/images/2013-11-18_19_00_00_30VIES_0341_01_L.jpeg', + 'url': 'http://www.tou.tv/30-vies/S04E41', + 'info_dict': { + 'id': '30-vies_S04E41', + 'ext': 'mp4', + 'title': '30 vies Saison 4 / Épisode 41', + 'description': 'md5:da363002db82ccbe4dafeb9cab039b09', + 'age_limit': 8, + 'uploader': 'Groupe des Nouveaux Médias', + 'duration': 1296, + 'upload_date': '20131118', + 'thumbnail': 'http://static.tou.tv/medias/images/2013-11-18_19_00_00_30VIES_0341_01_L.jpeg', }, - u'params': { - u'skip_download': True, # Requires rtmpdump + 'params': { + 'skip_download': True, # Requires rtmpdump }, - u'xskip': 'Only available in Canada' + 'skip': 'Only available in Canada' } def _real_extract(self, url): @@ -37,28 +39,25 @@ class TouTvIE(InfoExtractor): webpage = self._download_webpage(url, video_id) mediaId = self._search_regex( - r'"idMedia":\s*"([^"]+)"', webpage, u'media ID') + r'"idMedia":\s*"([^"]+)"', webpage, 'media ID') - # TODO test from de - streams_url = u'http://release.theplatform.com/content.select?pid=' + mediaId - streams_webpage = self._download_webpage( - streams_url, video_id, note=u'Downloading stream list') + streams_url = 'http://release.theplatform.com/content.select?pid=' + mediaId + streams_doc = self._download_xml( + streams_url, video_id, note='Downloading stream list') - streams_doc = xml.etree.ElementTree.fromstring( - streams_webpage.encode('utf-8')) video_url = next(n.text for n in streams_doc.findall('.//choice/url') - if u'//ad.doubleclick' not in n.text) + if '//ad.doubleclick' not in n.text) if video_url.endswith('/Unavailable.flv'): raise ExtractorError( - u'Access to this video is blocked from outside of Canada', + 'Access to this video is blocked from outside of Canada', expected=True) duration_str = self._html_search_meta( - 'video:duration', webpage, u'duration') + 'video:duration', webpage, 'duration') duration = int(duration_str) if duration_str else None upload_date_str = self._html_search_meta( - 'video:release_date', webpage, u'upload date') + 'video:release_date', webpage, 'upload date') upload_date = unified_strdate(upload_date_str) if upload_date_str else None return {