X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/beb6d38e0a0a4091007847a27022bf08c59f971c..2b4515201a54c38e34434ea2817d606be134a7c9:/youtube_dl/extractor/firstpost.py?ds=sidebyside diff --git a/youtube_dl/extractor/firstpost.py b/youtube_dl/extractor/firstpost.py index 0993af1..e8936cb 100644 --- a/youtube_dl/extractor/firstpost.py +++ b/youtube_dl/extractor/firstpost.py @@ -1,12 +1,10 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor class FirstpostIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?firstpost\.com/[^/]+/.*-(?P[0-9]+)\.html' + _VALID_URL = r'https?://(?:www\.)?firstpost\.com/[^/]+/.*-(?P[0-9]+)\.html' _TEST = { 'url': 'http://www.firstpost.com/india/india-to-launch-indigenous-aircraft-carrier-monday-1025403.html', @@ -20,11 +18,10 @@ class FirstpostIE(InfoExtractor): } 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') + + title = self._html_search_meta('twitter:title', page, 'title', fatal=True) description = self._html_search_meta('twitter:description', page, 'title') data = self._download_xml( @@ -42,6 +39,7 @@ 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,