X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/33cd347759d6d999325ebf3c69b7ed5692c343b2..eed74133841b43ce901ee0dd31c7dad5a234bd48:/youtube_dl/extractor/tutv.py diff --git a/youtube_dl/extractor/tutv.py b/youtube_dl/extractor/tutv.py index 4e404fb..d516b64 100644 --- a/youtube_dl/extractor/tutv.py +++ b/youtube_dl/extractor/tutv.py @@ -1,20 +1,22 @@ +from __future__ import unicode_literals + import base64 import re from .common import InfoExtractor -from ..utils import ( - compat_parse_qs, -) +from ..utils import compat_parse_qs + class TutvIE(InfoExtractor): - _VALID_URL=r'https?://(?:www\.)?tu\.tv/videos/(?P[^/?]+)' + _VALID_URL = r'https?://(?:www\.)?tu\.tv/videos/(?P[^/?]+)' _TEST = { - u'url': u'http://tu.tv/videos/noah-en-pabellon-cuahutemoc', - u'file': u'2742556.flv', - u'md5': u'5eb766671f69b82e528dc1e7769c5cb2', - u'info_dict': { - u"title": u"Noah en pabellon cuahutemoc" - } + 'url': 'http://tu.tv/videos/robots-futbolistas', + 'md5': '627c7c124ac2a9b5ab6addb94e0e65f7', + 'info_dict': { + 'id': '2973058', + 'ext': 'flv', + 'title': 'Robots futbolistas', + }, } def _real_extract(self, url): @@ -22,18 +24,14 @@ class TutvIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - internal_id = self._search_regex(r'codVideo=([0-9]+)', webpage, u'internal video ID') + internal_id = self._search_regex(r'codVideo=([0-9]+)', webpage, 'internal video ID') - data_url = u'http://tu.tv/flvurl.php?codVideo=' + str(internal_id) - data_content = self._download_webpage(data_url, video_id, note=u'Downloading video info') - data = compat_parse_qs(data_content) - video_url = base64.b64decode(data['kpt'][0]).decode('utf-8') - ext = video_url.partition(u'?')[0].rpartition(u'.')[2] + data_content = self._download_webpage( + 'http://tu.tv/flvurl.php?codVideo=%s' % internal_id, video_id, 'Downloading video info') + video_url = base64.b64decode(compat_parse_qs(data_content)['kpt'][0]).decode('utf-8') - info = { + return { 'id': internal_id, 'url': video_url, - 'ext': ext, 'title': self._og_search_title(webpage), } - return [info]