From 78af8eb1d14fbdc911ba87a07c124ab19c0f8843 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sun, 23 Jun 2013 22:08:28 +0200 Subject: [PATCH] [ustream] move into its own file --- youtube_dl/InfoExtractors.py | 32 +---------------------------- youtube_dl/extractor/ustream.py | 36 +++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+), 31 deletions(-) create mode 100644 youtube_dl/extractor/ustream.py diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 951fe64c0..1e6d6ce16 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -45,6 +45,7 @@ from .extractor.stanfordoc import StanfordOpenClassroomIE from .extractor.steam import SteamIE from .extractor.ted import TEDIE +from .extractor.ustream import UstreamIE from .extractor.vimeo import VimeoIE from .extractor.worldstarhiphop import WorldStarHipHopIE from .extractor.xnxx import XNXXIE @@ -69,37 +70,6 @@ -class UstreamIE(InfoExtractor): - _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P\d+)' - IE_NAME = u'ustream' - - def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('videoID') - - video_url = u'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') - - uploader = self._html_search_regex(r'data-content-type="channel".*?>(?P<uploader>.*?)</a>', - webpage, u'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 class RBMARadioIE(InfoExtractor): diff --git a/youtube_dl/extractor/ustream.py b/youtube_dl/extractor/ustream.py new file mode 100644 index 000000000..cfe3a6840 --- /dev/null +++ b/youtube_dl/extractor/ustream.py @@ -0,0 +1,36 @@ +import re + +from .common import InfoExtractor + + +class UstreamIE(InfoExtractor): + _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)' + IE_NAME = u'ustream' + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + video_id = m.group('videoID') + + video_url = u'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<title>.+)"', + webpage, u'title') + + uploader = self._html_search_regex(r'data-content-type="channel".*?>(?P<uploader>.*?)</a>', + webpage, u'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