[xhamster] use determine_ext

[youtube-dl] / youtube_dl / extractor / xhamster.py

diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index 00135092623f61a86bae99862fbf6b788a85be76..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,
-
+    unescapeHTML,
+    determine_ext,
     ExtractorError,
 )
 
@@ -11,6 +12,16 @@ from ..utils import (
 class XHamsterIE(InfoExtractor):
     """Information Extractor for xHamster"""
     _VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P<id>[0-9]+)/.*\.html'
+    _TEST = {
+        u'url': u'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
+        u'file': u'1509445.flv',
+        u'md5': u'9f48e0e8d58e3076bb236ff412ab62fa',
+        u'info_dict': {
+            u"upload_date": u"20121014", 
+            u"uploader_id": u"Ruseful2011", 
+            u"title": u"FemaleAgent Shy beauty takes the bait"
+        }
+    }
 
     def _real_extract(self,url):
         mobj = re.match(self._VALID_URL, url)
@@ -26,15 +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_extension = video_url.split('.')[-1]
 
         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:
@@ -52,9 +64,9 @@ class XHamsterIE(InfoExtractor):
         return [{
             'id':       video_id,
             'url':      video_url,
-            'ext':      video_extension,
+            'ext':      determine_ext(video_url),
             'title':    video_title,
-            # 'description': video_description,
+            'description': video_description,
             'upload_date': video_upload_date,
             'uploader_id': video_uploader_id,
             'thumbnail': video_thumbnail