Imported Upstream version 2013.08.29

[youtubedl] / youtube_dl / extractor / xhamster.py

diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index 0f1feeffd777ccc152b1ea1c4bb15dc00dc6b494..88b8b6be09f7a8f892db8266b3e68df14e22bfe7 100644 (file)
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -3,7 +3,8 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
 from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,

-
+    unescapeHTML,
+    determine_ext,

     ExtractorError,
 )
 
     ExtractorError,
 )
 


@@ -36,15 +37,16 @@ class XHamsterIE(InfoExtractor):
             video_url = compat_urllib_parse.unquote(mobj.group('file'))
         else:
             video_url = mobj.group('server')+'/key='+mobj.group('file')
             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_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
             webpage, u'title')
 
 
         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:
 
         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:


@@ -62,9 +64,9 @@ class XHamsterIE(InfoExtractor):
         return [{
             'id':       video_id,
             'url':      video_url,
         return [{
             'id':       video_id,
             'url':      video_url,

-            'ext':      video_extension,
+            'ext':      determine_ext(video_url),

             'title':    video_title,
             'title':    video_title,

-            # 'description': video_description,
+            'description': video_description,

             'upload_date': video_upload_date,
             'uploader_id': video_uploader_id,
             'thumbnail': video_thumbnail
             'upload_date': video_upload_date,
             'uploader_id': video_uploader_id,
             'thumbnail': video_thumbnail