Merge tag 'upstream/2015.05.15'

[youtubedl] / youtube_dl / extractor / vk.py

diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py
index 918bd10988a2c49fac2fc76bb7481e1a3ed7fdf1..cc384adbf9837f35f90c64d0e8dc0396b0b601ec 100644 (file)
--- a/youtube_dl/extractor/vk.py
+++ b/youtube_dl/extractor/vk.py
@@ -5,18 +5,22 @@ import re
 import json
 
 from .common import InfoExtractor
 import json
 
 from .common import InfoExtractor

+from ..compat import (
+    compat_str,
+    compat_urllib_parse,
+    compat_urllib_request,
+)

 from ..utils import (
     ExtractorError,
 from ..utils import (
     ExtractorError,

-    compat_urllib_request,
-    compat_urllib_parse,
-    compat_str,
+    orderedSet,

     unescapeHTML,
     unescapeHTML,

+    unified_strdate,

 )
 
 
 class VKIE(InfoExtractor):
     IE_NAME = 'vk.com'
 )
 
 
 class VKIE(InfoExtractor):
     IE_NAME = 'vk.com'

-    _VALID_URL = r'https?://(?:m\.)?vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:.+?\?.*?z=)?video(?P<videoid>.*?)(?:\?|%2F|$))'
+    _VALID_URL = r'https?://(?:m\.)?vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:.+?\?.*?z=)?video(?P<videoid>[^s].*?)(?:\?|%2F|$))'

     _NETRC_MACHINE = 'vk'
 
     _TESTS = [
     _NETRC_MACHINE = 'vk'
 
     _TESTS = [


@@ -27,19 +31,21 @@ class VKIE(InfoExtractor):
                 'id': '162222515',
                 'ext': 'flv',
                 'title': 'ProtivoGunz - Хуёвая песня',
                 'id': '162222515',
                 'ext': 'flv',
                 'title': 'ProtivoGunz - Хуёвая песня',

-                'uploader': 're:Noize MC.*',
+                'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',

                 'duration': 195,
                 'duration': 195,

+                'upload_date': '20120212',

             },
         },
         {
             },
         },
         {

-            'url': 'http://vk.com/video4643923_163339118',
-            'md5': 'f79bccb5cd182b1f43502ca5685b2b36',
+            'url': 'http://vk.com/video205387401_165548505',
+            'md5': '6c0aeb2e90396ba97035b9cbde548700',

             'info_dict': {
             'info_dict': {

-                'id': '163339118',
+                'id': '165548505',

                 'ext': 'mp4',
                 '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 +58,12 @@ class VKIE(InfoExtractor):
                 'uploader': 'Vladimir Gavrin',
                 'title': 'Lin Dan',
                 'duration': 101,
                 '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',
             'url': 'http://vk.com/video-8871596_164049491',
             'md5': 'a590bcaf3d543576c9bd162812387666',
             'note': 'Only available for registered users',


@@ -64,18 +73,7 @@ class VKIE(InfoExtractor):
                 'uploader': 'Триллеры',
                 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
                 'duration': 8352,
                 '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',
         },
             },
             'skip': 'Requires vk account credentials',
         },


@@ -88,6 +86,7 @@ class VKIE(InfoExtractor):
                 'uploader': 'Киномания - лучшее из мира кино',
                 'title': ' ',
                 'duration': 7291,
                 'uploader': 'Киномания - лучшее из мира кино',
                 'title': ' ',
                 'duration': 7291,

+                'upload_date': '20140328',

             },
             'skip': 'Requires vk account credentials',
         },
             },
             'skip': 'Requires vk account credentials',
         },


@@ -100,9 +99,15 @@ class VKIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Книга Илая',
                 'duration': 6771,
                 'ext': 'mp4',
                 'title': 'Книга Илая',
                 'duration': 6771,

+                'upload_date': '20140626',

             },
             'skip': 'Only works from Russia',
         },
             },
             '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):
     ]
 
     def _login(self):


@@ -119,7 +124,7 @@ class VKIE(InfoExtractor):
         }
 
         request = compat_urllib_request.Request('https://login.vk.com/?act=login',
         }
 
         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):
         login_page = self._download_webpage(request, None, note='Logging in as %s' % username)
 
         if re.search(r'onLoginFailed', login_page):


@@ -135,18 +140,41 @@ class VKIE(InfoExtractor):
         if not video_id:
             video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
 
         if not video_id:
             video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
 

-        info_url = 'http://vk.com/al_video.php?act=show&al=1&video=%s' % video_id
+        info_url = 'http://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id

         info_page = self._download_webpage(info_url, video_id)
 
         info_page = self._download_webpage(info_url, video_id)
 

-        if re.search(r'<!>Please log in or <', info_page):
-            raise ExtractorError('This video is only available for registered users, '
-                'use --username and --password options to provide account credentials.', expected=True)
+        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.',
+
+            r'<!>Please log in or <':
+            '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.',
+
+            r'<!>Видео временно недоступно':
+            'Video %s is temporarily unavailable.',
+        }
+
+        for error_re, error_msg in ERRORS.items():
+            if re.search(error_re, info_page):
+                raise ExtractorError(error_msg % video_id, expected=True)

 
         m_yt = re.search(r'src="(http://www.youtube.com/.*?)"', info_page)
         if m_yt is not None:
             self.to_screen('Youtube video detected')
             return self.url_result(m_yt.group(1), 'Youtube')
 
 
         m_yt = re.search(r'src="(http://www.youtube.com/.*?)"', info_page)
         if m_yt is not None:
             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)
+        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))
         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))


@@ -159,6 +187,13 @@ class VKIE(InfoExtractor):
         data_json = self._search_regex(r'var vars = ({.*?});', info_page, 'vars')
         data = json.loads(data_json)
 
         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,
         formats = [{
             'format_id': k,
             'url': v,


@@ -173,5 +208,31 @@ class VKIE(InfoExtractor):
             'title': unescapeHTML(data['md_title']),
             'thumbnail': data.get('jpg'),
             'uploader': data.get('md_author'),
             '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 = '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',
+        'info_dict': {
+            'id': '205387401',
+        },
+        'playlist_mincount': 4,
+    }
+
+    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)