New upstream version 2016.12.01

[youtubedl] / youtube_dl / extractor / fczenit.py

diff --git a/youtube_dl/extractor/fczenit.py b/youtube_dl/extractor/fczenit.py
index f1f150ef2ce41defbcee841d86fe4f9ada34d25d..8d1010b88c83dcbfd3e71e9f20275bf6fb9c9d21 100644 (file)
--- a/youtube_dl/extractor/fczenit.py
+++ b/youtube_dl/extractor/fczenit.py
@@ -1,20 +1,19 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 

-import re
-

 from .common import InfoExtractor
 from .common import InfoExtractor

+from ..compat import compat_urlparse

 
 
 class FczenitIE(InfoExtractor):
 
 
 class FczenitIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?fc-zenit\.ru/video/gl(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?fc-zenit\.ru/video/(?P<id>[0-9]+)'

     _TEST = {
     _TEST = {

-        'url': 'http://fc-zenit.ru/video/gl6785/',
-        'md5': '458bacc24549173fe5a5aa29174a5606',
+        'url': 'http://fc-zenit.ru/video/41044/',
+        'md5': '0e3fab421b455e970fa1aa3891e57df0',

         'info_dict': {
         'info_dict': {

-            'id': '6785',
+            'id': '41044',

             'ext': 'mp4',
             'ext': 'mp4',

-            'title': '«Зенит-ТВ»: как Олег Шатов играл против «Урала»',
+            'title': 'Так пишется история: казанский разгром ЦСКА на «Зенит-ТВ»',

         },
     }
 
         },
     }
 


@@ -22,15 +21,23 @@ class FczenitIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 

-        video_title = self._html_search_regex(r'<div class=\"photoalbum__title\">([^<]+)', webpage, 'title')
+        video_title = self._html_search_regex(
+            r'<[^>]+class=\"photoalbum__title\">([^<]+)', webpage, 'title')
+
+        video_items = self._parse_json(self._search_regex(
+            r'arrPath\s*=\s*JSON\.parse\(\'(.+)\'\)', webpage, 'video items'),
+            video_id)

 
 

-        bitrates_raw = self._html_search_regex(r'bitrates:.*\n(.*)\]', webpage, 'video URL')
-        bitrates = re.findall(r'url:.?\'(.+?)\'.*?bitrate:.?([0-9]{3}?)', bitrates_raw)
+        def merge_dicts(*dicts):
+            ret = {}
+            for a_dict in dicts:
+                ret.update(a_dict)
+            return ret

 
         formats = [{
 
         formats = [{

-            'url': furl,
-            'tbr': tbr,
-        } for furl, tbr in bitrates]
+            'url': compat_urlparse.urljoin(url, video_url),
+            'tbr': int(tbr),
+        } for tbr, video_url in merge_dicts(*video_items).items()]

 
         self._sort_formats(formats)
 
 
         self._sort_formats(formats)