Update upstream source from tag 'upstream/2017.11.06'

[youtubedl] / youtube_dl / extractor / ruhd.py

diff --git a/youtube_dl/extractor/ruhd.py b/youtube_dl/extractor/ruhd.py
index 55b58e5e6c09af2d211edaba256ad2ebce2a958d..3c8053a2617669cc22549f62e386ac988b33d3c6 100644 (file)
--- a/youtube_dl/extractor/ruhd.py
+++ b/youtube_dl/extractor/ruhd.py
@@ -1,13 +1,11 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8

 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import re
-

 from .common import InfoExtractor
 
 
 class RUHDIE(InfoExtractor):
 from .common import InfoExtractor
 
 
 class RUHDIE(InfoExtractor):

-    _VALID_URL = r'http://(?:www\.)?ruhd\.ru/play\.php\?vid=(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?ruhd\.ru/play\.php\?vid=(?P<id>\d+)'

     _TEST = {
         'url': 'http://www.ruhd.ru/play.php?vid=207',
         'md5': 'd1a9ec4edf8598e3fbd92bb16072ba83',
     _TEST = {
         'url': 'http://www.ruhd.ru/play.php?vid=207',
         'md5': 'd1a9ec4edf8598e3fbd92bb16072ba83',


@@ -16,24 +14,25 @@ class RUHDIE(InfoExtractor):
             'ext': 'divx',
             'title': 'КОТ бааааам',
             'description': 'классный кот)',
             'ext': 'divx',
             'title': 'КОТ бааааам',
             'description': 'классный кот)',

-            'thumbnail': 're:^http://.*\.jpg$',
+            'thumbnail': r're:^http://.*\.jpg$',

         }
     }
 
     def _real_extract(self, url):
         }
     }
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)

         webpage = self._download_webpage(url, video_id)
 
         video_url = self._html_search_regex(
             r'<param name="src" value="([^"]+)"', webpage, 'video url')
         title = self._html_search_regex(
         webpage = self._download_webpage(url, video_id)
 
         video_url = self._html_search_regex(
             r'<param name="src" value="([^"]+)"', webpage, 'video url')
         title = self._html_search_regex(

-            r'<title>([^<]+)&nbsp;&nbsp; RUHD.ru - Видео Высокого качества №1 в России!</title>', webpage, 'title')
+            r'<title>([^<]+)&nbsp;&nbsp; RUHD\.ru - Видео Высокого качества №1 в России!</title>',
+            webpage, 'title')

         description = self._html_search_regex(
         description = self._html_search_regex(

-            r'(?s)<div id="longdesc">(.+?)<span id="showlink">', webpage, 'description', fatal=False)
+            r'(?s)<div id="longdesc">(.+?)<span id="showlink">',
+            webpage, 'description', fatal=False)

         thumbnail = self._html_search_regex(
         thumbnail = self._html_search_regex(

-            r'<param name="previewImage" value="([^"]+)"', webpage, 'thumbnail', fatal=False)
+            r'<param name="previewImage" value="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)

         if thumbnail:
             thumbnail = 'http://www.ruhd.ru' + thumbnail
 
         if thumbnail:
             thumbnail = 'http://www.ruhd.ru' + thumbnail