diff options
author | Sergey M․ <dstftw@gmail.com> | 2014-06-22 01:20:40 +0700 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2014-06-22 01:20:40 +0700 |
commit | d2824416aa9cc43d92a44a820026378cae70ca9f (patch) | |
tree | 61a2ff100a228efc09b54615442b4039026f430a | |
parent | 18061bbab046ef0c237b955bb86b7bed3aa97256 (diff) |
[firstpost] Fix title extraction and add description
-rw-r--r-- | youtube_dl/extractor/firstpost.py | 7 |
1 files changed, 6 insertions, 1 deletions
diff --git a/youtube_dl/extractor/firstpost.py b/youtube_dl/extractor/firstpost.py index eccd8dde9..0993af1c9 100644 --- a/youtube_dl/extractor/firstpost.py +++ b/youtube_dl/extractor/firstpost.py @@ -15,6 +15,7 @@ class FirstpostIE(InfoExtractor): 'id': '1025403', 'ext': 'mp4', 'title': 'India to launch indigenous aircraft carrier INS Vikrant today', + 'description': 'md5:feef3041cb09724e0bdc02843348f5f4', } } @@ -22,13 +23,16 @@ class FirstpostIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + page = self._download_webpage(url, video_id) + title = self._html_search_meta('twitter:title', page, 'title') + description = self._html_search_meta('twitter:description', page, 'title') + data = self._download_xml( 'http://www.firstpost.com/getvideoxml-%s.xml' % video_id, video_id, 'Downloading video XML') item = data.find('./playlist/item') thumbnail = item.find('./image').text - title = item.find('./title').text formats = [ { @@ -42,6 +46,7 @@ class FirstpostIE(InfoExtractor): return { 'id': video_id, 'title': title, + 'description': description, 'thumbnail': thumbnail, 'formats': formats, } |