Merge pull request #8348 from remitamine/dfxp2srt-text
[youtube-dl] / youtube_dl / extractor / vidzi.py
index 82d2179e9a72d2527aacda2b781881b1e8fdcc1b..7c6e98026823e0df415664ad0b4d6995c9e2f673 100644 (file)
@@ -1,33 +1,39 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import smuggle_url
 
 
 class VidziIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?vidzi\.tv/(?P<id>\w+)'
     _TEST = {
-        'url': 'http://vidzi.tv/m1chxrwq7bx9',
-        'md5': '5c4c4a8ca2281a199c8eefe8f411d630',
+        'url': 'http://vidzi.tv/cghql9yq6emu.html',
+        'md5': '4f16c71ca0c8c8635ab6932b5f3f1660',
         'info_dict': {
-            'id': 'm1chxrwq7bx9',
+            'id': 'cghql9yq6emu',
             'ext': 'mp4',
-            'title': 'Watch Cadbury Dream Factory S01E04 HDTV x264 FiHTV mp4',
+            'title': 'youtube-dl test video  1\\\\2\'3/4<5\\\\6ä7↭',
+            'uploader': 'vidzi.tv',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
         },
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        
+
         webpage = self._download_webpage(url, video_id)
-        video_url = self._html_search_regex(
-            r'{\s*file\s*:\s*"([^"]+)"\s*}', webpage, 'video url')
         title = self._html_search_regex(
-            r'<Title>([^<]+)<\/Title>', webpage, 'title')
-        
+            r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title')
+
+        # Vidzi now uses jwplayer, which can be handled by GenericIE
         return {
+            '_type': 'url_transparent',
             'id': video_id,
             'title': title,
-            'url': video_url,
-            'ext': 'mp4',
+            'url': smuggle_url(url, {'to_generic': True}),
+            'ie_key': 'Generic',
         }
-        
\ No newline at end of file