From ce34e9ce5ec5cc403cf407ce8046b6271835cd6c Mon Sep 17 00:00:00 2001 From: rzhxeo Date: Fri, 23 Aug 2013 16:33:41 +0200 Subject: [PATCH 1/2] XHamsterIE: Fix video extension Cut off GET parameter --- youtube_dl/extractor/xhamster.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 0f1feeffd7..5bedc25ce6 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -36,7 +36,7 @@ def _real_extract(self,url): video_url = compat_urllib_parse.unquote(mobj.group('file')) else: video_url = mobj.group('server')+'/key='+mobj.group('file') - video_extension = video_url.split('.')[-1] + video_extension = video_url.split('.')[-1].split('?')[0] video_title = self._html_search_regex(r'(?P<title>.+?) - xHamster\.com', webpage, u'title') From 4353cf51a0d5a812ab8a6bda59be7c58149fb40e Mon Sep 17 00:00:00 2001 From: rzhxeo Date: Fri, 23 Aug 2013 16:40:20 +0200 Subject: [PATCH 2/2] XHamsterIE: Add video description --- youtube_dl/extractor/xhamster.py | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 5bedc25ce6..0fd0775834 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -3,7 +3,7 @@ from .common import InfoExtractor from ..utils import ( compat_urllib_parse, - + unescapeHTML, ExtractorError, ) @@ -41,10 +41,12 @@ def _real_extract(self,url): video_title = self._html_search_regex(r'(?P<title>.+?) - xHamster\.com', webpage, u'title') - # Can't see the description anywhere in the UI - # video_description = self._html_search_regex(r'Description: (?P[^<]+)', - # webpage, u'description', fatal=False) - # if video_description: video_description = unescapeHTML(video_description) + # Only a few videos have an description + mobj = re.search('Description: (?P[^<]+)', webpage) + if mobj: + video_description = unescapeHTML(mobj.group('description')) + else: + video_description = None mobj = re.search(r'hint=\'(?P[0-9]{4})-(?P[0-9]{2})-(?P[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage) if mobj: @@ -64,7 +66,7 @@ def _real_extract(self,url): 'url': video_url, 'ext': video_extension, 'title': video_title, - # 'description': video_description, + 'description': video_description, 'upload_date': video_upload_date, 'uploader_id': video_uploader_id, 'thumbnail': video_thumbnail