[vk] improve extraction(fixes #7976)

This commit is contained in:
remitamine 2016-05-06 15:02:40 +01:00
parent 6f59aa934b
commit 04e88ca2ca
3 changed files with 64 additions and 22 deletions

View file

@ -0,0 +1,39 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class BIQLEIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?biqle\.(?:com|org|ru)/watch/(?P<id>-?\d+_\d+)'
_TESTS = [{
'url': 'http://www.biqle.ru/watch/847655_160197695',
'md5': 'ad5f746a874ccded7b8f211aeea96637',
'info_dict': {
'id': '160197695',
'ext': 'mp4',
'title': 'Foo Fighters - The Pretender (Live at Wembley Stadium)',
'uploader': 'Andrey Rogozin',
'upload_date': '20110605',
}
}, {
'url': 'https://biqle.org/watch/-44781847_168547604',
'md5': '7f24e72af1db0edf7c1aaba513174f97',
'info_dict': {
'id': '168547604',
'ext': 'mp4',
'title': 'Ребенок в шоке от автоматической мойки',
'uploader': 'Dmitry Kotov',
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
embed_url = self._proto_relative_url(self._search_regex(
r'<iframe.+?src="((?:http:)?//daxab\.com/[^"]+)".*?></iframe>', webpage, 'embed url'))
return {
'_type': 'url_transparent',
'url': embed_url,
}

View file

@ -75,6 +75,7 @@ from .bigflix import BigflixIE
from .bild import BildIE
from .bilibili import BiliBiliIE
from .biobiochiletv import BioBioChileTVIE
from .biqle import BIQLEIE
from .bleacherreport import (
BleacherReportIE,
BleacherReportCMSIE,

View file

@ -26,12 +26,16 @@ class VKIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
(?:m\.)?vk\.com/video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|
(?:
(?:m\.)?vk\.com/video_|
(?:www\.)?daxab.com/
)
ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
(?:
(?:m\.)?vk\.com/(?:.+?\?.*?z=)?video|
(?:www\.)?biqle\.ru/watch/
(?:www\.)?daxab.com/embed/
)
(?P<videoid>[^s].*?)(?:\?(?:.*\blist=(?P<list_id>[\da-f]+))?|%2F|$)
(?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>[\da-f]+))?
)
'''
_NETRC_MACHINE = 'vk'
@ -75,7 +79,8 @@ class VKIE(InfoExtractor):
'duration': 101,
'upload_date': '20120730',
'view_count': int,
}
},
'skip': 'This video has been removed from public access.',
},
{
# VIDEO NOW REMOVED
@ -142,7 +147,7 @@ class VKIE(InfoExtractor):
'id': 'V3K4mi0SYkc',
'ext': 'webm',
'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
'description': 'md5:d9903938abdc74c738af77f527ca0596',
'duration': 178,
'upload_date': '20130116',
'uploader': "Children's Joy Foundation",
@ -173,11 +178,6 @@ class VKIE(InfoExtractor):
'url': 'https://vk.com/video205387401_164765225',
'only_matching': True,
},
{
# vk wrapper
'url': 'http://www.biqle.ru/watch/847655_160197695',
'only_matching': True,
},
{
# pladform embed
'url': 'https://vk.com/video-76116461_171554880',
@ -217,20 +217,22 @@ class VKIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
if not video_id:
video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
info_url = url
if video_id:
info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
# Some videos (removed?) can only be downloaded with list id specified
list_id = mobj.group('list_id')
if list_id:
info_url += '&list=%s' % list_id
else:
info_url = 'http://vk.com/video_ext.php?' + mobj.group('embed_query')
video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
info_page = self._download_webpage(info_url, video_id)
error_message = self._html_search_regex(
r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
[r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'],
info_page, 'error message', default=None)
if error_message:
raise ExtractorError(error_message, expected=True)
@ -305,17 +307,17 @@ class VKIE(InfoExtractor):
view_count = None
views = self._html_search_regex(
r'"mv_views_count_number"[^>]*>(.+?\bviews?)<',
info_page, 'view count', fatal=False)
info_page, 'view count', default=None)
if views:
view_count = str_to_int(self._search_regex(
r'([\d,.]+)', views, 'view count', fatal=False))
formats = []
for k, v in data.items():
if not k.startswith('url') and k != 'extra_data' or not v:
if not k.startswith('url') and not k.startswith('cache') and k != 'extra_data' or not v:
continue
height = int_or_none(self._search_regex(
r'^url(\d+)', k, 'height', default=None))
r'^(?:url|cache)(\d+)', k, 'height', default=None))
formats.append({
'format_id': k,
'url': v,