X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvk.py;h=d9acafd70b2fa9089e6d39ce808e2ec74c9fbe76;hb=9e1a5b845586a0a5431fb72467142046d8571e6f;hp=3bcf50e280a7730c5650f93c1325718d935afd1a;hpb=6fcd6e0e21839ae4b1753995dc44d2a93f72ac1f;p=youtube-dl

diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py
index 3bcf50e28..d9acafd70 100644
--- a/youtube_dl/extractor/vk.py
+++ b/youtube_dl/extractor/vk.py
@@ -11,7 +11,8 @@ from ..utils import (
     compat_urllib_parse,
     compat_str,
     unescapeHTML,
-)
+    unified_strdate,
+    orderedSet)
 
 
 class VKIE(InfoExtractor):
@@ -29,17 +30,19 @@ class VKIE(InfoExtractor):
                 'title': 'ProtivoGunz - Хуёвая песня',
                 'uploader': 're:Noize MC.*',
                 'duration': 195,
+                'upload_date': '20120212',
             },
         },
         {
-            'url': 'http://vk.com/video4643923_163339118',
-            'md5': 'f79bccb5cd182b1f43502ca5685b2b36',
+            'url': 'http://vk.com/video205387401_165548505',
+            'md5': '6c0aeb2e90396ba97035b9cbde548700',
             'info_dict': {
-                'id': '163339118',
+                'id': '165548505',
                 'ext': 'mp4',
-                'uploader': 'Elya Iskhakova',
-                'title': 'Dream Theater - Hollow Years Live at Budokan 720*',
-                'duration': 558,
+                'uploader': 'Tom Cruise',
+                'title': 'No name',
+                'duration': 9,
+                'upload_date': '20130721'
             }
         },
         {
@@ -52,9 +55,12 @@ class VKIE(InfoExtractor):
                 'uploader': 'Vladimir Gavrin',
                 'title': 'Lin Dan',
                 'duration': 101,
+                'upload_date': '20120730',
             }
         },
         {
+            # VIDEO NOW REMOVED
+            # please update if you find a video whose URL follows the same pattern
             'url': 'http://vk.com/video-8871596_164049491',
             'md5': 'a590bcaf3d543576c9bd162812387666',
             'note': 'Only available for registered users',
@@ -64,18 +70,7 @@ class VKIE(InfoExtractor):
                 'uploader': 'Триллеры',
                 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
                 'duration': 8352,
-            },
-            'skip': 'Requires vk account credentials',
-        },
-        {
-            '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': '20121218'
             },
             'skip': 'Requires vk account credentials',
         },
@@ -88,6 +83,7 @@ class VKIE(InfoExtractor):
                 'uploader': 'Киномания - лучшее из мира кино',
                 'title': ' ',
                 'duration': 7291,
+                'upload_date': '20140328',
             },
             'skip': 'Requires vk account credentials',
         },
@@ -100,9 +96,15 @@ class VKIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Книга Илая',
                 'duration': 6771,
+                'upload_date': '20140626',
             },
             '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):
@@ -119,7 +121,7 @@ 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):
@@ -169,6 +171,13 @@ class VKIE(InfoExtractor):
         data_json = self._search_regex(r'var vars = ({.*?});', info_page, 'vars')
         data = json.loads(data_json)
 
+        # Extract upload date
+        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:
+            mobj.group(1) + ' ' + mobj.group(2)
+            upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
+
         formats = [{
             'format_id': k,
             'url': v,
@@ -183,40 +192,28 @@ class VKIE(InfoExtractor):
             'title': unescapeHTML(data['md_title']),
             'thumbnail': data.get('jpg'),
             'uploader': data.get('md_author'),
-            'duration': data.get('duration')
+            'duration': data.get('duration'),
+            'upload_date': upload_date,
         }
 
 
 class VKUserVideosIE(InfoExtractor):
     IE_NAME = 'vk.com:user-videos'
-    IE_DESC = 'All of a user\'s videos'
-    _VALID_URL = r'https?://(?:m\.)?vk\.com/videos([0-9]+)(?:m\?.*)?'
+    IE_DESC = 'vk.com:All of a user\'s videos'
+    _VALID_URL = r'https?://vk\.com/videos(?P<id>[0-9]+)(?:m\?.*)?'
     _TEMPLATE_URL = 'https://vk.com/videos'
     _TEST = {
         'url': 'http://vk.com/videos205387401',
         'playlist_mincount': 4,
     }
 
-    def extract_videos_from_page(self, page):
-        ids_in_page = []
-        for mobj in re.finditer(r'href="/video([0-9_]+)"', page):
-            if mobj.group(1) not in ids_in_page:
-                ids_in_page.append(mobj.group(1))
-        return ids_in_page
-
     def _real_extract(self, url):
-        # Extract page id
-        mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError('Invalid URL: %s' % url)
-
-        # Download page and get video ids
-        page_id = mobj.group(1)
+        page_id = self._match_id(url)
         page = self._download_webpage(url, page_id)
-        video_ids = self.extract_videos_from_page(page)
-
-        self._downloader.to_screen('[vk] User videos %s: Found %i videos' % (page_id, len(video_ids)))
-
-        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)