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 248b7d54d3606d1c38440f3ec4e66e8d9ea0d707..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):
@@ -74,21 +77,6 @@ class VKIE(InfoExtractor):
             },
             'skip': 'Requires vk account credentials',
         },
-        {
-            # VIDEO NOW REMOVED
-            # please update if you find a video whose URL follows the same pattern
-            'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
-            'md5': 'd82c22e449f036282d1d3f7f4d276869',
-            'info_dict': {
-                'id': '166094326',
-                'ext': 'mp4',
-                'uploader': 'Киномания - лучшее из мира кино',
-                'title': 'Запах женщины (1992)',
-                'duration': 9392,
-                'upload_date': '20130914'
-            },
-            'skip': 'Requires vk account credentials',
-        },
         {
             'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
             'md5': '4d7a5ef8cf114dfa09577e57b2993202',
@@ -115,6 +103,11 @@ class VKIE(InfoExtractor):
             },
             'skip': 'Only works from Russia',
         },
+        {
+            # removed video, just testing that we match the pattern
+            'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
+            'only_matching': True,
+        },
     ]
 
     def _login(self):
@@ -131,7 +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):
@@ -152,12 +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():
@@ -169,6 +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))
@@ -185,7 +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 = [{
@@ -220,7 +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]
-        return self.playlist_result(url_entries, page_id)
\ No newline at end of file
+        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)