X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/415fdb62500dca2e22067a05008dfbf87c75b662..d018d3313032e12968a6add6800e51d412e2f602:/youtube_dl/extractor/firstpost.py?ds=sidebyside diff --git a/youtube_dl/extractor/firstpost.py b/youtube_dl/extractor/firstpost.py index eccd8dd..298227d 100644 --- a/youtube_dl/extractor/firstpost.py +++ b/youtube_dl/extractor/firstpost.py @@ -1,7 +1,5 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor @@ -15,12 +13,16 @@ class FirstpostIE(InfoExtractor): 'id': '1025403', 'ext': 'mp4', 'title': 'India to launch indigenous aircraft carrier INS Vikrant today', + 'description': 'md5:feef3041cb09724e0bdc02843348f5f4', } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) + page = self._download_webpage(url, video_id) + + title = self._html_search_meta('twitter:title', page, 'title', fatal=True) + description = self._html_search_meta('twitter:description', page, 'title') data = self._download_xml( 'http://www.firstpost.com/getvideoxml-%s.xml' % video_id, video_id, @@ -28,7 +30,6 @@ class FirstpostIE(InfoExtractor): item = data.find('./playlist/item') thumbnail = item.find('./image').text - title = item.find('./title').text formats = [ { @@ -38,10 +39,12 @@ class FirstpostIE(InfoExtractor): 'height': int(details.find('./height').text.strip()), } for details in item.findall('./source/file_details') if details.find('./file').text ] + self._sort_formats(formats) return { 'id': video_id, 'title': title, + 'description': description, 'thumbnail': thumbnail, 'formats': formats, }