Imported Upstream version 2015.11.10

[youtubedl] / youtube_dl / extractor / sunporno.py

diff --git a/youtube_dl/extractor/sunporno.py b/youtube_dl/extractor/sunporno.py
index 263f09b4645fa8b6255f1216e99cab27afce2bee..e527aa97188b1860e054f8af7c7bd7a33301729e 100644 (file)
--- a/youtube_dl/extractor/sunporno.py
+++ b/youtube_dl/extractor/sunporno.py
@@ -28,27 +28,31 @@ class SunPornoIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
     }
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)

 
         webpage = self._download_webpage(url, video_id)
 
 
         webpage = self._download_webpage(url, video_id)
 

-        title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'title')
-        description = self._html_search_meta('description', webpage, 'description')
+        title = self._html_search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title')
+        description = self._html_search_meta(
+            'description', webpage, 'description')

         thumbnail = self._html_search_regex(
             r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
 
         duration = parse_duration(self._search_regex(
         thumbnail = self._html_search_regex(
             r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
 
         duration = parse_duration(self._search_regex(

-            r'Duration:\s*(\d+:\d+)\s*<', webpage, 'duration', fatal=False))
+            r'itemprop="duration">\s*(\d+:\d+)\s*<',
+            webpage, 'duration', fatal=False))

 
         view_count = int_or_none(self._html_search_regex(
 
         view_count = int_or_none(self._html_search_regex(

-            r'class="views">\s*(\d+)\s*<', webpage, 'view count', fatal=False))
+            r'class="views">(?:<noscript>)?\s*(\d+)\s*<',
+            webpage, 'view count', fatal=False))

         comment_count = int_or_none(self._html_search_regex(
         comment_count = int_or_none(self._html_search_regex(

-            r'(\d+)</b> Comments?', webpage, 'comment count', fatal=False))
+            r'(\d+)</b> Comments?',
+            webpage, 'comment count', fatal=False))

 
         formats = []
         quality = qualities(['mp4', 'flv'])
 
         formats = []
         quality = qualities(['mp4', 'flv'])

-        for video_url in re.findall(r'<source src="([^"]+)"', webpage):
+        for video_url in re.findall(r'<(?:source|video) src="([^"]+)"', webpage):

             video_ext = determine_ext(video_url)
             formats.append({
                 'url': video_url,
             video_ext = determine_ext(video_url)
             formats.append({
                 'url': video_url,