X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fustream.py;h=e4bb3b949081d7e3c9a74632975ca633870a4a38;hb=7c360e3a04f09b912f51034c7778eb2297872e86;hp=74c82587f802acc82e3025235a4bfe92725e8111;hpb=ef66b0c6effb9d8741807abb12b059560c97c8da;p=youtube-dl diff --git a/youtube_dl/extractor/ustream.py b/youtube_dl/extractor/ustream.py index 74c82587f..e4bb3b949 100644 --- a/youtube_dl/extractor/ustream.py +++ b/youtube_dl/extractor/ustream.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import json import re @@ -9,49 +11,56 @@ from ..utils import ( class UstreamIE(InfoExtractor): - _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P\d+)' - IE_NAME = u'ustream' + _VALID_URL = r'https?://www\.ustream\.tv/(?Precorded|embed)/(?P\d+)' + IE_NAME = 'ustream' _TEST = { - u'url': u'http://www.ustream.tv/recorded/20274954', - u'file': u'20274954.flv', - u'md5': u'088f151799e8f572f84eb62f17d73e5c', - u'info_dict': { - u"uploader": u"Young Americans for Liberty", - u"title": u"Young Americans for Liberty February 7, 2012 2:28 AM" - } + 'url': 'http://www.ustream.tv/recorded/20274954', + 'file': '20274954.flv', + 'md5': '088f151799e8f572f84eb62f17d73e5c', + 'info_dict': { + "uploader": "Young Americans for Liberty", + "title": "Young Americans for Liberty February 7, 2012 2:28 AM", + }, } def _real_extract(self, url): m = re.match(self._VALID_URL, url) + if m.group('type') == 'embed': + video_id = m.group('videoID') + webpage = self._download_webpage(url, video_id) + desktop_video_id = self._html_search_regex(r'ContentVideoIds=\["([^"]*?)"\]', webpage, 'desktop_video_id') + desktop_url = 'http://www.ustream.tv/recorded/' + desktop_video_id + return self.url_result(desktop_url, 'Ustream') + video_id = m.group('videoID') - video_url = u'http://tcdn.ustream.tv/video/%s' % video_id + video_url = 'http://tcdn.ustream.tv/video/%s' % video_id webpage = self._download_webpage(url, video_id) self.report_extraction(video_id) video_title = self._html_search_regex(r'data-title="(?P.+)"', - webpage, u'title') + webpage, 'title') uploader = self._html_search_regex(r'data-content-type="channel".*?>(?P<uploader>.*?)</a>', - webpage, u'uploader', fatal=False, flags=re.DOTALL) + webpage, 'uploader', fatal=False, flags=re.DOTALL) thumbnail = self._html_search_regex(r'<link rel="image_src" href="(?P<thumb>.*?)"', - webpage, u'thumbnail', fatal=False) - - info = { - 'id': video_id, - 'url': video_url, - 'ext': 'flv', - 'title': video_title, - 'uploader': uploader, - 'thumbnail': thumbnail, - } - return info + webpage, 'thumbnail', fatal=False) + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'flv', + 'title': video_title, + 'uploader': uploader, + 'thumbnail': thumbnail, + } + class UstreamChannelIE(InfoExtractor): _VALID_URL = r'https?://www\.ustream\.tv/channel/(?P<slug>.+)' - IE_NAME = u'ustream:channel' + IE_NAME = 'ustream:channel' def _real_extract(self, url): m = re.match(self._VALID_URL, url)