aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/vk.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/vk.py')
-rw-r--r--youtube_dl/extractor/vk.py57
1 files changed, 48 insertions, 9 deletions
diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py
index 36cd7e52e..daf615af9 100644
--- a/youtube_dl/extractor/vk.py
+++ b/youtube_dl/extractor/vk.py
@@ -11,12 +11,13 @@ from ..utils import (
compat_urllib_parse,
compat_str,
unescapeHTML,
-)
+ unified_strdate,
+ orderedSet)
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 = [
@@ -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',
@@ -64,10 +70,13 @@ class VKIE(InfoExtractor):
'uploader': 'Триллеры',
'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
'duration': 8352,
+ 'upload_date': '20121218'
},
'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': {
@@ -76,6 +85,7 @@ class VKIE(InfoExtractor):
'uploader': 'Киномания - лучшее из мира кино',
'title': 'Запах женщины (1992)',
'duration': 9392,
+ 'upload_date': '20130914'
},
'skip': 'Requires vk account credentials',
},
@@ -88,6 +98,7 @@ class VKIE(InfoExtractor):
'uploader': 'Киномания - лучшее из мира кино',
'title': ' ',
'duration': 7291,
+ 'upload_date': '20140328',
},
'skip': 'Requires vk account credentials',
},
@@ -100,6 +111,7 @@ class VKIE(InfoExtractor):
'ext': 'mp4',
'title': 'Книга Илая',
'duration': 6771,
+ 'upload_date': '20140626',
},
'skip': 'Only works from Russia',
},
@@ -169,6 +181,13 @@ 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:
+ x = mobj.group(1) + ' ' + mobj.group(2)
+ upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
+
formats = [{
'format_id': k,
'url': v,
@@ -183,5 +202,25 @@ 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 = '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 _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)