debian/copyright: Fix missing-license-paragraph-in-dep5-copyright.

[youtubedl] / youtube_dl / extractor / sohu.py

diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py
index 77bb0a8dc3b5555e28eda831ca11c2d5eff96f79..07f514a46246657206ae3fd31e19b1d2932e6f15 100644 (file)
--- a/youtube_dl/extractor/sohu.py
+++ b/youtube_dl/extractor/sohu.py
@@ -1,4 +1,5 @@
 # encoding: utf-8
+from __future__ import unicode_literals
 
 import json
 import re
@@ -8,50 +9,56 @@ from ..utils import ExtractorError
 
 
 class SohuIE(InfoExtractor):
-    _VALID_URL = r'https?://tv\.sohu\.com/\d+?/n(?P<id>\d+)\.shtml.*?'
+    _VALID_URL = r'https?://(?P<mytv>my\.)?tv\.sohu\.com/.+?/(?(mytv)|n)(?P<id>\d+)\.shtml.*?'
 
     _TEST = {
-        u'url': u'http://tv.sohu.com/20130724/n382479172.shtml#super',
-        u'file': u'382479172.mp4',
-        u'md5': u'bde8d9a6ffd82c63a1eefaef4eeefec7',
-        u'info_dict': {
-            u'title': u'MV：Far East Movement《The Illest》',
+        'url': 'http://tv.sohu.com/20130724/n382479172.shtml#super',
+        'md5': 'bde8d9a6ffd82c63a1eefaef4eeefec7',
+        'info_dict': {
+            'id': '382479172',
+            'ext': 'mp4',
+            'title': 'MV：Far East Movement《The Illest》',
         },
+        'skip': 'Only available from China',
     }
 
     def _real_extract(self, url):
 
-        def _fetch_data(vid_id):
-            base_data_url = u'http://hot.vrs.sohu.com/vrs_flash.action?vid='
+        def _fetch_data(vid_id, mytv=False):
+            if mytv:
+                base_data_url = 'http://my.tv.sohu.com/play/videonew.do?vid='
+            else:
+                base_data_url = 'http://hot.vrs.sohu.com/vrs_flash.action?vid='
             data_url = base_data_url + str(vid_id)
             data_json = self._download_webpage(
                 data_url, video_id,
-                note=u'Downloading JSON data for ' + str(vid_id))
+                note='Downloading JSON data for ' + str(vid_id))
             return json.loads(data_json)
 
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
+        mytv = mobj.group('mytv') is not None
 
         webpage = self._download_webpage(url, video_id)
         raw_title = self._html_search_regex(r'(?s)<title>(.+?)</title>',
-                                            webpage, u'video title')
+                                            webpage, 'video title')
         title = raw_title.partition('-')[0].strip()
 
-        vid = self._html_search_regex(r'var vid="(\d+)"', webpage,
-                                      u'video path')
-        data = _fetch_data(vid)
+        vid = self._html_search_regex(r'var vid ?= ?["\'](\d+)["\']', webpage,
+                                      'video path')
+        data = _fetch_data(vid, mytv)
 
         QUALITIES = ('ori', 'super', 'high', 'nor')
         vid_ids = [data['data'][q + 'Vid']
                    for q in QUALITIES
                    if data['data'][q + 'Vid'] != 0]
         if not vid_ids:
-            raise ExtractorError(u'No formats available for this video')
+            raise ExtractorError('No formats available for this video')
 
         # For now, we just pick the highest available quality
         vid_id = vid_ids[-1]
 
-        format_data = data if vid == vid_id else _fetch_data(vid_id)
+        format_data = data if vid == vid_id else _fetch_data(vid_id, mytv)
         part_count = format_data['data']['totalBlocks']
         allot = format_data['allot']
         prot = format_data['prot']
@@ -64,7 +71,7 @@ class SohuIE(InfoExtractor):
                         (allot, prot, clipsURL[i], su[i]))
             part_str = self._download_webpage(
                 part_url, video_id,
-                note=u'Downloading part %d of %d' % (i+1, part_count))
+                note='Downloading part %d of %d' % (i + 1, part_count))
 
             part_info = part_str.split('|')
             video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3])