diff options
| author | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2013-08-23 17:21:30 +0200 |
|---|---|---|
| committer | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2013-08-23 17:21:30 +0200 |
| commit | 53b0f3e4e290016ccc0a905ec8a18efb5bd9af8a (patch) | |
| tree | b6d544818a93862cda4182e8efbd74a1323b00b7 | |
| parent | d4051a8e051a06ddeab905a4b5fcc7ddb70952bf (diff) | |
| parent | 4353cf51a0d5a812ab8a6bda59be7c58149fb40e (diff) | |
| download | youtube-dl-53b0f3e4e290016ccc0a905ec8a18efb5bd9af8a.tar.gz youtube-dl-53b0f3e4e290016ccc0a905ec8a18efb5bd9af8a.tar.xz youtube-dl-53b0f3e4e290016ccc0a905ec8a18efb5bd9af8a.zip | |
Merge pull request #1301 from rzhxeo/xhamster
XHamsterIE: Fix video extension and add video description
| -rw-r--r-- | youtube_dl/extractor/xhamster.py | 16 |
1 files changed, 9 insertions, 7 deletions
diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 0f1feeffd..0fd077583 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -3,7 +3,7 @@ import re from .common import InfoExtractor from ..utils import ( compat_urllib_parse, - + unescapeHTML, ExtractorError, ) @@ -36,15 +36,17 @@ class XHamsterIE(InfoExtractor): 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'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, u'title') - # Can't see the description anywhere in the UI - # video_description = self._html_search_regex(r'<span>Description: </span>(?P<description>[^<]+)', - # webpage, u'description', fatal=False) - # if video_description: video_description = unescapeHTML(video_description) + # Only a few videos have an description + mobj = re.search('<span>Description: </span>(?P<description>[^<]+)', webpage) + if mobj: + video_description = unescapeHTML(mobj.group('description')) + else: + video_description = None mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage) if mobj: @@ -64,7 +66,7 @@ class XHamsterIE(InfoExtractor): '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 |