[youtube] Fix extraction.

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

diff --git a/youtube_dl/extractor/ynet.py b/youtube_dl/extractor/ynet.py
index 66d53962a58c9d78cede366ecc684dd5fe3a3472..c4ae4d88eb0f64dd24d63c7e882ab49552a962c2 100644 (file)
--- a/youtube_dl/extractor/ynet.py
+++ b/youtube_dl/extractor/ynet.py
@@ -5,50 +5,48 @@ import re
 import json
 
 from .common import InfoExtractor
-from ..utils import compat_urllib_parse
+from ..compat import compat_urllib_parse_unquote_plus
 
 
 class YnetIE(InfoExtractor):
-    _VALID_URL = r'http://.*ynet\.co\.il/.*/0,7340,(?P<id>L(?:-[0-9]+)+),00\.html'
+    _VALID_URL = r'https?://(?:.+?\.)?ynet\.co\.il/(?:.+?/)?0,7340,(?P<id>L(?:-[0-9]+)+),00\.html'
     _TESTS = [
         {
             'url': 'http://hot.ynet.co.il/home/0,7340,L-11659-99244,00.html',
-            'md5': '002b44ee2f33d50363a1c153bed524cf',
             'info_dict': {
                 'id': 'L-11659-99244',
                 'ext': 'flv',
                 'title': 'איש לא יודע מאיפה באנו',
-                'thumbnail': 're:^https?://.*\.jpg',
+                'thumbnail': r're:^https?://.*\.jpg',
             }
         }, {
             'url': 'http://hot.ynet.co.il/home/0,7340,L-8859-84418,00.html',
-            'md5': '6455046ae1b48cf7e2b7cae285e53a16',
             'info_dict': {
                 'id': 'L-8859-84418',
                 'ext': 'flv',
                 'title': "צפו: הנשיקה הלוהטת של תורגי' ויוליה פלוטקין",
-                'thumbnail': 're:^https?://.*\.jpg',
+                'thumbnail': r're:^https?://.*\.jpg',
             }
         }
     ]
 
     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)
 
-        content = compat_urllib_parse.unquote_plus(self._og_search_video_url(webpage))
+        content = compat_urllib_parse_unquote_plus(self._og_search_video_url(webpage))
         config = json.loads(self._search_regex(r'config=({.+?})$', content, 'video config'))
         f4m_url = config['clip']['url']
         title = self._og_search_title(webpage)
         m = re.search(r'ynet - HOT -- (["\']+)(?P<title>.+?)\1', title)
         if m:
             title = m.group('title')
+        formats = self._extract_f4m_formats(f4m_url, video_id)
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
             'title': title,
-            'formats': self._extract_f4m_formats(f4m_url, video_id),
+            'formats': formats,
             'thumbnail': self._og_search_thumbnail(webpage),
-        }
\ No newline at end of file
+        }