Merge branch 'ceskatelevizesrt' of https://github.com/oskar456/youtube-dl into oskar4...

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

diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py
index 0e7d4dff2770b6c286c4e873e036fc137bc0ccfa..129de6cf3ddc03292d00d2c7e0b147aedb85066b 100644 (file)
--- a/youtube_dl/extractor/vk.py
+++ b/youtube_dl/extractor/vk.py
@@ -5,14 +5,17 @@ import re
 import json
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_str,
+    compat_urllib_parse,
+    compat_urllib_request,
+)
 from ..utils import (
     ExtractorError,
-    compat_urllib_request,
-    compat_urllib_parse,
-    compat_str,
+    orderedSet,
     unescapeHTML,
     unified_strdate,
-    orderedSet)
+)
 
 
 class VKIE(InfoExtractor):
@@ -121,7 +124,7 @@ class VKIE(InfoExtractor):
         }
 
         request = compat_urllib_request.Request('https://login.vk.com/?act=login',
-            compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+                                                compat_urllib_parse.urlencode(login_form).encode('utf-8'))
         login_page = self._download_webpage(request, None, note='Logging in as %s' % username)
 
         if re.search(r'onLoginFailed', login_page):
@@ -142,12 +145,14 @@ class VKIE(InfoExtractor):
 
         ERRORS = {
             r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
-                'Video %s has been removed from public access due to rightholder complaint.',
+            'Video %s has been removed from public access due to rightholder complaint.',
+
             r'<!>Please log in or <':
-                'Video %s is only available for registered users, '
-                'use --username and --password options to provide account credentials.',
-            '<!>Unknown error':
-                'Video %s does not exist.'
+            'Video %s is only available for registered users, '
+            'use --username and --password options to provide account credentials.',
+
+            r'<!>Unknown error':
+            'Video %s does not exist.'
         }
 
         for error_re, error_msg in ERRORS.items():
@@ -159,6 +164,15 @@ class VKIE(InfoExtractor):
             self.to_screen('Youtube video detected')
             return self.url_result(m_yt.group(1), 'Youtube')
 
+        m_rutube = re.search(
+            r'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page)
+        assert m_rutube
+        if m_rutube is not None:
+            self.to_screen('rutube video detected')
+            rutube_url = self._proto_relative_url(
+                m_rutube.group(1).replace('\\', ''))
+            return self.url_result(rutube_url)
+
         m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.*?});', info_page)
         if m_opts:
             m_opts_url = re.search(r"url\s*:\s*'([^']+)", m_opts.group(1))
@@ -175,7 +189,7 @@ class VKIE(InfoExtractor):
         upload_date = None
         mobj = re.search(r'id="mv_date_wrap".*?Added ([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
         if mobj is not None:
-            x = mobj.group(1) + ' ' + mobj.group(2)
+            mobj.group(1) + ' ' + mobj.group(2)
             upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
 
         formats = [{
@@ -210,7 +224,10 @@ class VKUserVideosIE(InfoExtractor):
     def _real_extract(self, url):
         page_id = self._match_id(url)
         page = self._download_webpage(url, page_id)
-        video_ids = orderedSet(m.group(1) for m in re.finditer(r'href="/video([0-9_]+)"', page))
-        url_entries = [self.url_result('http://vk.com/video' + video_id, 'VK', video_id=video_id)
-                       for video_id in video_ids]
+        video_ids = orderedSet(
+            m.group(1) for m in re.finditer(r'href="/video([0-9_]+)"', page))
+        url_entries = [
+            self.url_result(
+                'http://vk.com/video' + video_id, 'VK', video_id=video_id)
+            for video_id in video_ids]
         return self.playlist_result(url_entries, page_id)