Merge pull request #7045 from remitamine/ign

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

diff --git a/youtube_dl/extractor/vidzi.py b/youtube_dl/extractor/vidzi.py
index 7d93dd301d059213b4ebb4d392ec965fefa23188..2ba9f31dfcd95587540324608753470104a25f6e 100644 (file)
--- a/youtube_dl/extractor/vidzi.py
+++ b/youtube_dl/extractor/vidzi.py
@@ -1,30 +1,38 @@
-import re
+# coding: utf-8
+from __future__ import unicode_literals
+
 from .common import InfoExtractor
 
+
 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↭',
         },
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        
-        webpage = self._download_webpage('http://vidzi.tv/' + video_id, video_id)
-        video_url = self._html_search_regex(r'{\s*file\s*:\s*"([^"]+)"\s*}', webpage, u'vidzi url')
-        title = self._html_search_regex(r'<Title>([^<]+)<\/Title>', webpage, u'vidzi title')
-        
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        video_host = self._html_search_regex(
+            r'id=\'vplayer\'><img src="http://(.*?)/i', webpage,
+            'video host')
+        video_hash = self._html_search_regex(
+            r'\|([a-z0-9]+)\|hls\|type', webpage, 'video_hash')
+        ext = self._html_search_regex(
+            r'\|tracks\|([a-z0-9]+)\|', webpage, 'video ext')
+        video_url = 'http://' + video_host + '/' + video_hash + '/v.' + ext
+        title = self._html_search_regex(
+            r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title')
+
         return {
             'id': video_id,
             'title': title,
             'url': video_url,
-            'ext': 'mp4',
         }
-        
\ No newline at end of file