[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 94d2536798026fef4c36a64c1aa41b9ca6de3336..c4ae4d88eb0f64dd24d63c7e882ab49552a962c2 100644 (file)
--- a/youtube_dl/extractor/ynet.py
+++ b/youtube_dl/extractor/ynet.py
@@ -2,46 +2,51 @@
 from __future__ import unicode_literals
 
 import re
-import base64
 import json
 
 from .common import InfoExtractor
-from youtube_dl.utils import compat_urllib_parse_urlparse, 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'
-    _TEST = {
-        'url': 'http://hot.ynet.co.il/home/0,7340,L-11659-99244,00.html',
-        'info_dict': {
-            'id': 'L-11659-99244',
-            'ext': 'flv',
-            'title': 'md5:3dba12d2837ee2ad9652cc64af652b16',
-            'thumbnail': 'http://hot.ynet.co.il/PicServer4/2014/09/23/5606015/AMERICAN_COMMUNE1_T.jpg',
+    _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',
+            'info_dict': {
+                'id': 'L-11659-99244',
+                'ext': 'flv',
+                'title': 'איש לא יודע מאיפה באנו',
+                'thumbnail': r're:^https?://.*\.jpg',
+            }
+        }, {
+            'url': 'http://hot.ynet.co.il/home/0,7340,L-8859-84418,00.html',
+            'info_dict': {
+                'id': 'L-8859-84418',
+                'ext': 'flv',
+                'title': "צפו: הנשיקה הלוהטת של תורגי' ויוליה פלוטקין",
+                'thumbnail': r're:^https?://.*\.jpg',
+            }
         }
-    }
+    ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        
-        id = mobj.group('id')
-        
-        webpage = self._download_webpage(url, id)
-
-        content = compat_urllib_parse.unquote_plus(self._og_search_video_url(webpage).decode('utf-8'))
-
-        player_url = re.match('(http.*\.swf)\?' ,content).group(1)
-        
-        config = json.loads(re.match('.*config\=(.*)' ,content).group(1))
-                
-        f4m_url = config['clip']['url']    
-
-        title = re.sub(': Video$', '', self._og_search_title(webpage))
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        content = compat_urllib_parse_unquote_plus(self._og_search_video_url(webpage))
+        config = json.loads(self._search_regex(r'config=({.+?})$', 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': id,
+            'id': video_id,
             'title': title,
-            'formats': self._extract_f4m_formats(f4m_url, id),
+            'formats': formats,
             'thumbnail': self._og_search_thumbnail(webpage),
-            'player_url': player_url,
         }
-