2016-08-17 23:14:05 +00:00
|
|
|
|
import collections
|
2022-07-27 20:31:03 +00:00
|
|
|
|
import hashlib
|
2013-11-01 21:28:51 +00:00
|
|
|
|
import re
|
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
2022-07-27 20:31:03 +00:00
|
|
|
|
from .dailymotion import DailymotionIE
|
|
|
|
|
from .odnoklassniki import OdnoklassnikiIE
|
|
|
|
|
from .pladform import PladformIE
|
|
|
|
|
from .vimeo import VimeoIE
|
|
|
|
|
from .youtube import YoutubeIE
|
2019-04-06 19:17:54 +00:00
|
|
|
|
from ..compat import compat_urlparse
|
2013-11-01 21:28:51 +00:00
|
|
|
|
from ..utils import (
|
2014-02-16 19:05:15 +00:00
|
|
|
|
ExtractorError,
|
2022-07-27 20:31:03 +00:00
|
|
|
|
clean_html,
|
2016-07-13 14:51:44 +00:00
|
|
|
|
get_element_by_class,
|
2016-02-23 12:47:13 +00:00
|
|
|
|
int_or_none,
|
2014-12-13 11:24:42 +00:00
|
|
|
|
orderedSet,
|
2018-07-26 06:24:46 +00:00
|
|
|
|
str_or_none,
|
2015-06-15 14:55:25 +00:00
|
|
|
|
str_to_int,
|
2013-11-01 21:28:51 +00:00
|
|
|
|
unescapeHTML,
|
2016-09-29 16:48:21 +00:00
|
|
|
|
unified_timestamp,
|
2022-07-27 20:31:03 +00:00
|
|
|
|
update_url_query,
|
2018-07-21 12:08:28 +00:00
|
|
|
|
url_or_none,
|
2016-03-25 20:19:24 +00:00
|
|
|
|
urlencode_postdata,
|
2014-12-13 11:24:42 +00:00
|
|
|
|
)
|
2013-11-01 21:28:51 +00:00
|
|
|
|
|
|
|
|
|
|
2016-07-13 14:51:44 +00:00
|
|
|
|
class VKBaseIE(InfoExtractor):
|
|
|
|
|
_NETRC_MACHINE = 'vk'
|
|
|
|
|
|
2022-07-27 20:31:03 +00:00
|
|
|
|
def _download_webpage_handle(self, url_or_request, video_id, *args, fatal=True, **kwargs):
|
|
|
|
|
response = super()._download_webpage_handle(url_or_request, video_id, *args, fatal=fatal, **kwargs)
|
|
|
|
|
challenge_url, cookie = response[1].geturl() if response else '', None
|
|
|
|
|
if challenge_url.startswith('https://vk.com/429.html?'):
|
|
|
|
|
cookie = self._get_cookies(challenge_url).get('hash429')
|
|
|
|
|
if not cookie:
|
|
|
|
|
return response
|
|
|
|
|
|
|
|
|
|
hash429 = hashlib.md5(cookie.value.encode('ascii')).hexdigest()
|
|
|
|
|
self._request_webpage(
|
|
|
|
|
update_url_query(challenge_url, {'key': hash429}), video_id, fatal=fatal,
|
|
|
|
|
note='Resolving WAF challenge', errnote='Failed to bypass WAF challenge')
|
|
|
|
|
return super()._download_webpage_handle(url_or_request, video_id, *args, fatal=True, **kwargs)
|
|
|
|
|
|
2022-03-18 20:53:33 +00:00
|
|
|
|
def _perform_login(self, username, password):
|
2016-07-13 14:51:44 +00:00
|
|
|
|
login_page, url_handle = self._download_webpage_handle(
|
|
|
|
|
'https://vk.com', None, 'Downloading login page')
|
|
|
|
|
|
|
|
|
|
login_form = self._hidden_inputs(login_page)
|
|
|
|
|
|
|
|
|
|
login_form.update({
|
|
|
|
|
'email': username.encode('cp1251'),
|
|
|
|
|
'pass': password.encode('cp1251'),
|
|
|
|
|
})
|
|
|
|
|
|
2019-05-17 20:17:15 +00:00
|
|
|
|
# vk serves two same remixlhk cookies in Set-Cookie header and expects
|
|
|
|
|
# first one to be actually set
|
|
|
|
|
self._apply_first_set_cookie_header(url_handle, 'remixlhk')
|
2016-07-13 14:51:44 +00:00
|
|
|
|
|
|
|
|
|
login_page = self._download_webpage(
|
2021-10-31 14:16:12 +00:00
|
|
|
|
'https://vk.com/login', None,
|
2017-11-11 13:49:03 +00:00
|
|
|
|
note='Logging in',
|
2016-07-13 14:51:44 +00:00
|
|
|
|
data=urlencode_postdata(login_form))
|
|
|
|
|
|
|
|
|
|
if re.search(r'onLoginFailed', login_page):
|
|
|
|
|
raise ExtractorError(
|
|
|
|
|
'Unable to login, incorrect username and/or password', expected=True)
|
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
def _download_payload(self, path, video_id, data, fatal=True):
|
2022-07-27 20:31:03 +00:00
|
|
|
|
endpoint = f'https://vk.com/{path}.php'
|
2019-10-25 18:35:07 +00:00
|
|
|
|
data['al'] = 1
|
|
|
|
|
code, payload = self._download_json(
|
2022-07-27 20:31:03 +00:00
|
|
|
|
endpoint, video_id, data=urlencode_postdata(data), fatal=fatal,
|
|
|
|
|
headers={
|
|
|
|
|
'Referer': endpoint,
|
|
|
|
|
'X-Requested-With': 'XMLHttpRequest',
|
|
|
|
|
})['payload']
|
2019-10-25 18:35:07 +00:00
|
|
|
|
if code == '3':
|
|
|
|
|
self.raise_login_required()
|
|
|
|
|
elif code == '8':
|
|
|
|
|
raise ExtractorError(clean_html(payload[0][1:-1]), expected=True)
|
|
|
|
|
return payload
|
|
|
|
|
|
2016-07-13 14:51:44 +00:00
|
|
|
|
|
|
|
|
|
class VKIE(VKBaseIE):
|
2015-07-18 11:23:33 +00:00
|
|
|
|
IE_NAME = 'vk'
|
|
|
|
|
IE_DESC = 'VK'
|
2022-08-01 01:23:25 +00:00
|
|
|
|
_EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1']
|
2015-07-08 14:27:06 +00:00
|
|
|
|
_VALID_URL = r'''(?x)
|
|
|
|
|
https?://
|
|
|
|
|
(?:
|
2016-05-06 14:02:40 +00:00
|
|
|
|
(?:
|
2016-07-02 09:43:19 +00:00
|
|
|
|
(?:(?:m|new)\.)?vk\.com/video_|
|
2016-05-06 14:02:40 +00:00
|
|
|
|
(?:www\.)?daxab.com/
|
|
|
|
|
)
|
|
|
|
|
ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
|
2015-07-08 14:27:06 +00:00
|
|
|
|
(?:
|
2022-01-03 19:15:30 +00:00
|
|
|
|
(?:(?:m|new)\.)?vk\.com/(?:.+?\?.*?z=)?(?:video|clip)|
|
2016-05-06 14:02:40 +00:00
|
|
|
|
(?:www\.)?daxab.com/embed/
|
2015-07-08 14:27:06 +00:00
|
|
|
|
)
|
2022-01-02 17:14:20 +00:00
|
|
|
|
(?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>([\da-f]+)|(ln-[\da-zA-Z]+)))?
|
2015-07-08 14:27:06 +00:00
|
|
|
|
)
|
|
|
|
|
'''
|
2022-08-01 01:23:25 +00:00
|
|
|
|
# https://help.sibnet.ru/?sibnet_video_embed
|
|
|
|
|
_EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//video\.sibnet\.ru/shell\.php\?.*?\bvideoid=\d+.*?)\1']
|
2014-02-16 19:05:15 +00:00
|
|
|
|
_TESTS = [
|
|
|
|
|
{
|
|
|
|
|
'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
|
|
|
|
|
'info_dict': {
|
2019-04-03 10:08:42 +00:00
|
|
|
|
'id': '-77521_162222515',
|
2018-02-20 15:21:10 +00:00
|
|
|
|
'ext': 'mp4',
|
2014-02-16 19:05:15 +00:00
|
|
|
|
'title': 'ProtivoGunz - Хуёвая песня',
|
2015-03-01 21:30:18 +00:00
|
|
|
|
'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
|
2022-07-27 20:31:03 +00:00
|
|
|
|
'uploader_id': '39545378',
|
2014-02-16 19:05:15 +00:00
|
|
|
|
'duration': 195,
|
2018-07-26 06:24:46 +00:00
|
|
|
|
'timestamp': 1329049880,
|
2014-11-21 22:23:39 +00:00
|
|
|
|
'upload_date': '20120212',
|
2022-07-27 20:31:03 +00:00
|
|
|
|
'comment_count': int,
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'thumbnail': r're:https?://.+\.jpg$',
|
2014-02-16 19:05:15 +00:00
|
|
|
|
},
|
2022-07-27 20:31:03 +00:00
|
|
|
|
'params': {'skip_download': 'm3u8'},
|
2013-11-01 21:28:51 +00:00
|
|
|
|
},
|
2014-02-16 19:05:15 +00:00
|
|
|
|
{
|
2014-11-21 22:52:01 +00:00
|
|
|
|
'url': 'http://vk.com/video205387401_165548505',
|
2014-02-16 19:05:15 +00:00
|
|
|
|
'info_dict': {
|
2019-04-03 10:08:42 +00:00
|
|
|
|
'id': '205387401_165548505',
|
2014-02-16 19:05:15 +00:00
|
|
|
|
'ext': 'mp4',
|
2014-11-21 22:52:01 +00:00
|
|
|
|
'title': 'No name',
|
2018-07-26 06:24:46 +00:00
|
|
|
|
'uploader': 'Tom Cruise',
|
|
|
|
|
'uploader_id': '205387401',
|
2014-11-21 22:52:01 +00:00
|
|
|
|
'duration': 9,
|
2018-07-26 06:24:46 +00:00
|
|
|
|
'timestamp': 1374364108,
|
|
|
|
|
'upload_date': '20130720',
|
2022-07-27 20:31:03 +00:00
|
|
|
|
'comment_count': int,
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'thumbnail': r're:https?://.+\.jpg$',
|
2014-02-16 19:05:15 +00:00
|
|
|
|
}
|
|
|
|
|
},
|
2014-02-28 16:51:54 +00:00
|
|
|
|
{
|
|
|
|
|
'note': 'Embedded video',
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'url': 'https://vk.com/video_ext.php?oid=-77521&id=162222515&hash=87b046504ccd8bfa',
|
2014-02-28 16:51:54 +00:00
|
|
|
|
'info_dict': {
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'id': '-77521_162222515',
|
2014-02-28 16:51:54 +00:00
|
|
|
|
'ext': 'mp4',
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
|
|
|
|
|
'title': 'ProtivoGunz - Хуёвая песня',
|
|
|
|
|
'duration': 195,
|
|
|
|
|
'upload_date': '20120212',
|
|
|
|
|
'timestamp': 1329049880,
|
2022-07-27 20:31:03 +00:00
|
|
|
|
'uploader_id': '39545378',
|
|
|
|
|
'thumbnail': r're:https?://.+\.jpg$',
|
2016-05-06 14:02:40 +00:00
|
|
|
|
},
|
2022-07-27 20:31:03 +00:00
|
|
|
|
'params': {'skip_download': 'm3u8'},
|
2014-02-28 16:51:54 +00:00
|
|
|
|
},
|
2014-02-16 19:05:15 +00:00
|
|
|
|
{
|
2014-11-21 22:52:01 +00:00
|
|
|
|
# VIDEO NOW REMOVED
|
|
|
|
|
# please update if you find a video whose URL follows the same pattern
|
2014-02-16 19:05:15 +00:00
|
|
|
|
'url': 'http://vk.com/video-8871596_164049491',
|
|
|
|
|
'md5': 'a590bcaf3d543576c9bd162812387666',
|
|
|
|
|
'note': 'Only available for registered users',
|
|
|
|
|
'info_dict': {
|
2019-04-03 10:08:42 +00:00
|
|
|
|
'id': '-8871596_164049491',
|
2014-02-16 19:05:15 +00:00
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'uploader': 'Триллеры',
|
2014-06-29 12:33:39 +00:00
|
|
|
|
'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
|
2014-02-16 19:05:15 +00:00
|
|
|
|
'duration': 8352,
|
2015-06-15 14:55:25 +00:00
|
|
|
|
'upload_date': '20121218',
|
|
|
|
|
'view_count': int,
|
2014-02-16 19:05:15 +00:00
|
|
|
|
},
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'skip': 'Removed',
|
2014-02-28 16:51:54 +00:00
|
|
|
|
},
|
2014-06-29 12:33:39 +00:00
|
|
|
|
{
|
|
|
|
|
'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
|
|
|
|
|
'info_dict': {
|
2019-04-03 10:08:42 +00:00
|
|
|
|
'id': '-43215063_168067957',
|
2014-06-29 12:33:39 +00:00
|
|
|
|
'ext': 'mp4',
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'uploader': 'Bro Mazter',
|
2014-06-29 12:33:39 +00:00
|
|
|
|
'title': ' ',
|
|
|
|
|
'duration': 7291,
|
2014-11-21 22:23:39 +00:00
|
|
|
|
'upload_date': '20140328',
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'uploader_id': '223413403',
|
|
|
|
|
'timestamp': 1396018030,
|
2014-06-29 12:33:39 +00:00
|
|
|
|
},
|
|
|
|
|
'skip': 'Requires vk account credentials',
|
|
|
|
|
},
|
2014-06-29 13:07:59 +00:00
|
|
|
|
{
|
|
|
|
|
'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
|
|
|
|
|
'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
|
|
|
|
|
'note': 'ivi.ru embed',
|
|
|
|
|
'info_dict': {
|
2019-04-03 10:08:42 +00:00
|
|
|
|
'id': '-43215063_169084319',
|
2014-06-29 13:07:59 +00:00
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Книга Илая',
|
|
|
|
|
'duration': 6771,
|
2014-11-21 22:23:39 +00:00
|
|
|
|
'upload_date': '20140626',
|
2015-06-15 14:55:25 +00:00
|
|
|
|
'view_count': int,
|
2014-06-29 13:07:59 +00:00
|
|
|
|
},
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'skip': 'Removed',
|
2014-06-29 13:07:59 +00:00
|
|
|
|
},
|
2022-01-02 17:14:20 +00:00
|
|
|
|
{
|
|
|
|
|
'url': 'https://vk.com/video-93049196_456239755?list=ln-cBjJ7S4jYYx3ADnmDT',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '-93049196_456239755',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': '8 серия (озвучка)',
|
|
|
|
|
'duration': 8383,
|
2022-07-27 20:31:03 +00:00
|
|
|
|
'comment_count': int,
|
|
|
|
|
'uploader': 'Dizi2021',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'timestamp': 1640162189,
|
2022-01-02 17:14:20 +00:00
|
|
|
|
'upload_date': '20211222',
|
2022-07-27 20:31:03 +00:00
|
|
|
|
'uploader_id': '-93049196',
|
|
|
|
|
'thumbnail': r're:https?://.+\.jpg$',
|
2022-01-02 17:14:20 +00:00
|
|
|
|
},
|
|
|
|
|
},
|
2015-07-11 15:23:49 +00:00
|
|
|
|
{
|
|
|
|
|
# video (removed?) only available with list id
|
|
|
|
|
'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
|
|
|
|
|
'md5': '091287af5402239a1051c37ec7b92913',
|
|
|
|
|
'info_dict': {
|
2019-04-03 10:08:42 +00:00
|
|
|
|
'id': '30481095_171201961',
|
2015-07-11 15:23:49 +00:00
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'ТюменцевВВ_09.07.2015',
|
|
|
|
|
'uploader': 'Anton Ivanov',
|
|
|
|
|
'duration': 109,
|
|
|
|
|
'upload_date': '20150709',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
},
|
2016-09-29 16:48:21 +00:00
|
|
|
|
'skip': 'Removed',
|
2015-07-11 15:23:49 +00:00
|
|
|
|
},
|
2015-07-08 14:41:08 +00:00
|
|
|
|
{
|
|
|
|
|
# youtube embed
|
|
|
|
|
'url': 'https://vk.com/video276849682_170681728',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'V3K4mi0SYkc',
|
2019-04-03 10:08:42 +00:00
|
|
|
|
'ext': 'mp4',
|
2015-07-08 14:41:08 +00:00
|
|
|
|
'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
|
2018-07-26 06:24:46 +00:00
|
|
|
|
'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
|
2019-04-03 10:08:42 +00:00
|
|
|
|
'duration': 178,
|
2022-07-27 20:31:03 +00:00
|
|
|
|
'upload_date': '20130117',
|
2018-07-26 06:24:46 +00:00
|
|
|
|
'uploader': "Children's Joy Foundation Inc.",
|
2015-07-08 14:41:08 +00:00
|
|
|
|
'uploader_id': 'thecjf',
|
|
|
|
|
'view_count': int,
|
2022-07-27 20:31:03 +00:00
|
|
|
|
'channel_id': 'UCgzCNQ11TmR9V97ECnhi3gw',
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'channel': 'Children\'s Joy Foundation Inc.',
|
|
|
|
|
'uploader_url': 'http://www.youtube.com/user/thecjf',
|
|
|
|
|
'thumbnail': r're:https?://.+\.jpg$',
|
|
|
|
|
'tags': 'count:27',
|
|
|
|
|
'start_time': 0.0,
|
|
|
|
|
'categories': ['Nonprofits & Activism'],
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCgzCNQ11TmR9V97ECnhi3gw',
|
|
|
|
|
'age_limit': 0,
|
2015-07-08 14:41:08 +00:00
|
|
|
|
},
|
|
|
|
|
},
|
2016-09-25 03:39:29 +00:00
|
|
|
|
{
|
|
|
|
|
# dailymotion embed
|
|
|
|
|
'url': 'https://vk.com/video-37468416_456239855',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'k3lz2cmXyRuJQSjGHUv',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'md5:d52606645c20b0ddbb21655adaa4f56f',
|
2019-11-26 21:01:34 +00:00
|
|
|
|
'description': 'md5:424b8e88cc873217f520e582ba28bb36',
|
2016-09-25 03:39:29 +00:00
|
|
|
|
'uploader': 'AniLibria.Tv',
|
|
|
|
|
'upload_date': '20160914',
|
|
|
|
|
'uploader_id': 'x1p5vl5',
|
|
|
|
|
'timestamp': 1473877246,
|
|
|
|
|
},
|
2022-07-27 20:31:03 +00:00
|
|
|
|
'skip': 'Removed'
|
2016-09-25 03:39:29 +00:00
|
|
|
|
},
|
2016-02-23 12:47:13 +00:00
|
|
|
|
{
|
|
|
|
|
# video key is extra_data not url\d+
|
|
|
|
|
'url': 'http://vk.com/video-110305615_171782105',
|
|
|
|
|
'md5': 'e13fcda136f99764872e739d13fac1d1',
|
|
|
|
|
'info_dict': {
|
2019-04-03 10:08:42 +00:00
|
|
|
|
'id': '-110305615_171782105',
|
2016-02-23 12:47:13 +00:00
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'S-Dance, репетиции к The way show',
|
|
|
|
|
'uploader': 'THE WAY SHOW | 17 апреля',
|
2018-07-26 06:24:46 +00:00
|
|
|
|
'uploader_id': '-110305615',
|
|
|
|
|
'timestamp': 1454859345,
|
2016-02-23 12:47:13 +00:00
|
|
|
|
'upload_date': '20160207',
|
2018-07-26 06:24:46 +00:00
|
|
|
|
},
|
2022-07-27 20:31:03 +00:00
|
|
|
|
'skip': 'Removed',
|
2016-02-23 12:47:13 +00:00
|
|
|
|
},
|
2016-09-29 16:04:10 +00:00
|
|
|
|
{
|
2016-12-29 21:31:19 +00:00
|
|
|
|
# finished live stream, postlive_mp4
|
2016-09-29 16:04:10 +00:00
|
|
|
|
'url': 'https://vk.com/videos-387766?z=video-387766_456242764%2Fpl_-387766_-2',
|
|
|
|
|
'info_dict': {
|
2019-04-03 10:08:42 +00:00
|
|
|
|
'id': '-387766_456242764',
|
2016-09-29 16:04:10 +00:00
|
|
|
|
'ext': 'mp4',
|
2019-04-03 10:08:42 +00:00
|
|
|
|
'title': 'ИгроМир 2016 День 1 — Игромания Утром',
|
2016-09-29 16:04:10 +00:00
|
|
|
|
'uploader': 'Игромания',
|
|
|
|
|
'duration': 5239,
|
2019-04-03 10:08:42 +00:00
|
|
|
|
'upload_date': '20160929',
|
|
|
|
|
'uploader_id': '-387766',
|
|
|
|
|
'timestamp': 1475137527,
|
2022-07-27 20:31:03 +00:00
|
|
|
|
'thumbnail': r're:https?://.+\.jpg$',
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
'like_count': int,
|
2016-09-29 16:04:10 +00:00
|
|
|
|
},
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2016-09-29 16:04:10 +00:00
|
|
|
|
},
|
2016-09-29 16:21:39 +00:00
|
|
|
|
{
|
2016-12-29 21:31:19 +00:00
|
|
|
|
# live stream, hls and rtmp links, most likely already finished live
|
2016-09-29 16:21:39 +00:00
|
|
|
|
# stream by the time you are reading this comment
|
|
|
|
|
'url': 'https://vk.com/video-140332_456239111',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2014-11-23 09:11:04 +00:00
|
|
|
|
{
|
|
|
|
|
# removed video, just testing that we match the pattern
|
|
|
|
|
'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2015-07-18 13:25:06 +00:00
|
|
|
|
{
|
|
|
|
|
# age restricted video, requires vk account credentials
|
|
|
|
|
'url': 'https://vk.com/video205387401_164765225',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2015-12-07 16:05:54 +00:00
|
|
|
|
{
|
|
|
|
|
# pladform embed
|
|
|
|
|
'url': 'https://vk.com/video-76116461_171554880',
|
|
|
|
|
'only_matching': True,
|
2016-07-02 09:43:19 +00:00
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
'url': 'http://new.vk.com/video205387401_165548505',
|
|
|
|
|
'only_matching': True,
|
2017-02-04 08:23:35 +00:00
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
# This video is no longer available, because its author has been blocked.
|
|
|
|
|
'url': 'https://vk.com/video-10639516_456240611',
|
|
|
|
|
'only_matching': True,
|
2018-11-17 13:59:13 +00:00
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
# The video is not available in your region.
|
|
|
|
|
'url': 'https://vk.com/video-51812607_171445436',
|
|
|
|
|
'only_matching': True,
|
2022-01-03 19:15:30 +00:00
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
'url': 'https://vk.com/clip30014565_456240946',
|
|
|
|
|
'only_matching': True,
|
2018-11-17 13:59:13 +00:00
|
|
|
|
}]
|
2014-02-16 19:05:15 +00:00
|
|
|
|
|
2013-11-01 21:28:51 +00:00
|
|
|
|
def _real_extract(self, url):
|
2021-08-19 01:41:24 +00:00
|
|
|
|
mobj = self._match_valid_url(url)
|
2014-02-28 16:51:54 +00:00
|
|
|
|
video_id = mobj.group('videoid')
|
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
mv_data = {}
|
2016-05-06 14:02:40 +00:00
|
|
|
|
if video_id:
|
2019-10-25 18:35:07 +00:00
|
|
|
|
data = {
|
2022-07-27 20:31:03 +00:00
|
|
|
|
'act': 'show',
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'video': video_id,
|
|
|
|
|
}
|
2016-05-06 14:02:40 +00:00
|
|
|
|
# Some videos (removed?) can only be downloaded with list id specified
|
|
|
|
|
list_id = mobj.group('list_id')
|
|
|
|
|
if list_id:
|
2019-10-25 18:35:07 +00:00
|
|
|
|
data['list'] = list_id
|
|
|
|
|
|
|
|
|
|
payload = self._download_payload('al_video', video_id, data)
|
|
|
|
|
info_page = payload[1]
|
|
|
|
|
opts = payload[-1]
|
|
|
|
|
mv_data = opts.get('mvData') or {}
|
|
|
|
|
player = opts.get('player') or {}
|
2016-05-06 14:02:40 +00:00
|
|
|
|
else:
|
2014-02-28 16:51:54 +00:00
|
|
|
|
video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
|
2014-02-16 19:05:15 +00:00
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
info_page = self._download_webpage(
|
|
|
|
|
'http://vk.com/video_ext.php?' + mobj.group('embed_query'), video_id)
|
2014-02-16 19:05:15 +00:00
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
error_message = self._html_search_regex(
|
|
|
|
|
[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)
|
2015-07-18 13:15:20 +00:00
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
|
|
|
|
|
raise ExtractorError(
|
|
|
|
|
'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
|
|
|
|
|
expected=True)
|
2015-07-06 18:04:19 +00:00
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.'
|
2018-01-15 15:56:45 +00:00
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
ERRORS = {
|
|
|
|
|
r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
|
|
|
|
|
ERROR_COPYRIGHT,
|
2018-01-15 15:56:45 +00:00
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
r'>The video .*? was removed from public access by request of the copyright holder.<':
|
|
|
|
|
ERROR_COPYRIGHT,
|
2014-11-23 21:14:27 +00:00
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
r'<!>Please log in or <':
|
|
|
|
|
'Video %s is only available for registered users, '
|
|
|
|
|
'use --username and --password options to provide account credentials.',
|
2014-11-23 21:14:27 +00:00
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
r'<!>Unknown error':
|
|
|
|
|
'Video %s does not exist.',
|
2015-03-01 15:55:43 +00:00
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
r'<!>Видео временно недоступно':
|
|
|
|
|
'Video %s is temporarily unavailable.',
|
2015-07-11 15:26:03 +00:00
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
r'<!>Access denied':
|
|
|
|
|
'Access denied to video %s.',
|
2017-02-04 08:23:35 +00:00
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
r'<!>Видеозапись недоступна, так как её автор был заблокирован.':
|
|
|
|
|
'Video %s is no longer available, because its author has been blocked.',
|
2017-02-04 08:23:35 +00:00
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
r'<!>This video is no longer available, because its author has been blocked.':
|
|
|
|
|
'Video %s is no longer available, because its author has been blocked.',
|
2018-07-26 06:24:46 +00:00
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
r'<!>This video is no longer available, because it has been deleted.':
|
|
|
|
|
'Video %s is no longer available, because it has been deleted.',
|
2018-11-17 13:59:13 +00:00
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
r'<!>The video .+? is not available in your region.':
|
|
|
|
|
'Video %s is not available in your region.',
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
for error_re, error_msg in ERRORS.items():
|
|
|
|
|
if re.search(error_re, info_page):
|
|
|
|
|
raise ExtractorError(error_msg % video_id, expected=True)
|
2014-02-16 19:05:15 +00:00
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
player = self._parse_json(self._search_regex(
|
|
|
|
|
r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n',
|
|
|
|
|
info_page, 'player params'), video_id)
|
2014-10-28 14:06:07 +00:00
|
|
|
|
|
2017-09-05 17:50:25 +00:00
|
|
|
|
youtube_url = YoutubeIE._extract_url(info_page)
|
2015-07-08 14:34:50 +00:00
|
|
|
|
if youtube_url:
|
2019-10-25 18:35:07 +00:00
|
|
|
|
return self.url_result(youtube_url, YoutubeIE.ie_key())
|
2014-06-29 13:07:59 +00:00
|
|
|
|
|
2016-10-06 16:22:52 +00:00
|
|
|
|
vimeo_url = VimeoIE._extract_url(url, info_page)
|
2015-09-30 16:12:52 +00:00
|
|
|
|
if vimeo_url is not None:
|
2019-10-25 18:35:07 +00:00
|
|
|
|
return self.url_result(vimeo_url, VimeoIE.ie_key())
|
2015-09-30 16:12:52 +00:00
|
|
|
|
|
2015-12-07 16:03:52 +00:00
|
|
|
|
pladform_url = PladformIE._extract_url(info_page)
|
|
|
|
|
if pladform_url:
|
2019-10-25 18:35:07 +00:00
|
|
|
|
return self.url_result(pladform_url, PladformIE.ie_key())
|
2015-12-07 16:03:52 +00:00
|
|
|
|
|
2015-01-04 02:15:27 +00:00
|
|
|
|
m_rutube = re.search(
|
2016-02-08 15:30:23 +00:00
|
|
|
|
r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page)
|
2015-01-04 02:15:27 +00:00
|
|
|
|
if m_rutube is not None:
|
|
|
|
|
rutube_url = self._proto_relative_url(
|
|
|
|
|
m_rutube.group(1).replace('\\', ''))
|
|
|
|
|
return self.url_result(rutube_url)
|
|
|
|
|
|
2022-08-06 21:59:19 +00:00
|
|
|
|
dailymotion_url = next(DailymotionIE._extract_embed_urls(url, info_page), None)
|
|
|
|
|
if dailymotion_url:
|
|
|
|
|
return self.url_result(dailymotion_url, DailymotionIE.ie_key())
|
2016-09-25 03:39:29 +00:00
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
odnoklassniki_url = OdnoklassnikiIE._extract_url(info_page)
|
|
|
|
|
if odnoklassniki_url:
|
|
|
|
|
return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
|
|
|
|
|
|
2022-08-06 21:59:19 +00:00
|
|
|
|
sibnet_url = next(self._extract_embed_urls(url, info_page), None)
|
|
|
|
|
if sibnet_url:
|
|
|
|
|
return self.url_result(sibnet_url)
|
2021-05-20 15:38:49 +00:00
|
|
|
|
|
2015-06-15 14:46:10 +00:00
|
|
|
|
m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
|
2014-06-29 13:07:59 +00:00
|
|
|
|
if m_opts:
|
2015-06-15 14:46:10 +00:00
|
|
|
|
m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
|
2014-06-29 13:07:59 +00:00
|
|
|
|
if m_opts_url:
|
|
|
|
|
opts_url = m_opts_url.group(1)
|
|
|
|
|
if opts_url.startswith('//'):
|
|
|
|
|
opts_url = 'http:' + opts_url
|
|
|
|
|
return self.url_result(opts_url)
|
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
data = player['params'][0]
|
2016-09-29 16:21:39 +00:00
|
|
|
|
title = unescapeHTML(data['md_title'])
|
|
|
|
|
|
2016-12-29 21:31:19 +00:00
|
|
|
|
# 2 = live
|
|
|
|
|
# 3 = post live (finished live)
|
2016-12-29 21:21:49 +00:00
|
|
|
|
is_live = data.get('live') == 2
|
2016-09-29 16:21:39 +00:00
|
|
|
|
|
2016-09-29 16:48:21 +00:00
|
|
|
|
timestamp = unified_timestamp(self._html_search_regex(
|
2016-09-29 16:51:52 +00:00
|
|
|
|
r'class=["\']mv_info_date[^>]+>([^<]+)(?:<|from)', info_page,
|
2018-07-26 06:24:46 +00:00
|
|
|
|
'upload date', default=None)) or int_or_none(data.get('date'))
|
2016-09-25 18:26:58 +00:00
|
|
|
|
|
2016-09-29 16:51:52 +00:00
|
|
|
|
view_count = str_to_int(self._search_regex(
|
|
|
|
|
r'class=["\']mv_views_count[^>]+>\s*([\d,.]+)',
|
2017-12-15 15:53:56 +00:00
|
|
|
|
info_page, 'view count', default=None))
|
2015-06-15 14:55:25 +00:00
|
|
|
|
|
2016-02-23 12:47:13 +00:00
|
|
|
|
formats = []
|
2016-09-29 16:21:39 +00:00
|
|
|
|
for format_id, format_url in data.items():
|
2018-07-21 12:08:28 +00:00
|
|
|
|
format_url = url_or_none(format_url)
|
|
|
|
|
if not format_url or not format_url.startswith(('http', '//', 'rtmp')):
|
2016-02-23 12:47:13 +00:00
|
|
|
|
continue
|
2019-05-10 20:56:22 +00:00
|
|
|
|
if (format_id.startswith(('url', 'cache'))
|
|
|
|
|
or format_id in ('extra_data', 'live_mp4', 'postlive_mp4')):
|
2016-09-29 16:21:39 +00:00
|
|
|
|
height = int_or_none(self._search_regex(
|
|
|
|
|
r'^(?:url|cache)(\d+)', format_id, 'height', default=None))
|
|
|
|
|
formats.append({
|
|
|
|
|
'format_id': format_id,
|
|
|
|
|
'url': format_url,
|
|
|
|
|
'height': height,
|
|
|
|
|
})
|
|
|
|
|
elif format_id == 'hls':
|
|
|
|
|
formats.extend(self._extract_m3u8_formats(
|
2017-03-25 18:37:54 +00:00
|
|
|
|
format_url, video_id, 'mp4', 'm3u8_native',
|
2016-12-29 21:21:49 +00:00
|
|
|
|
m3u8_id=format_id, fatal=False, live=is_live))
|
2016-09-29 16:21:39 +00:00
|
|
|
|
elif format_id == 'rtmp':
|
|
|
|
|
formats.append({
|
|
|
|
|
'format_id': format_id,
|
|
|
|
|
'url': format_url,
|
|
|
|
|
'ext': 'flv',
|
|
|
|
|
})
|
2014-01-21 17:21:44 +00:00
|
|
|
|
|
2021-10-31 05:13:49 +00:00
|
|
|
|
subtitles = {}
|
|
|
|
|
for sub in data.get('subs') or {}:
|
|
|
|
|
subtitles.setdefault(sub.get('lang', 'en'), []).append({
|
|
|
|
|
'ext': sub.get('title', '.srt').split('.')[-1],
|
|
|
|
|
'url': url_or_none(sub.get('url')),
|
|
|
|
|
})
|
|
|
|
|
|
2013-11-01 21:28:51 +00:00
|
|
|
|
return {
|
2019-04-03 10:08:42 +00:00
|
|
|
|
'id': video_id,
|
2014-01-21 17:21:44 +00:00
|
|
|
|
'formats': formats,
|
2016-09-29 16:21:39 +00:00
|
|
|
|
'title': title,
|
2014-01-21 17:21:44 +00:00
|
|
|
|
'thumbnail': data.get('jpg'),
|
|
|
|
|
'uploader': data.get('md_author'),
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'uploader_id': str_or_none(data.get('author_id') or mv_data.get('authorId')),
|
|
|
|
|
'duration': int_or_none(data.get('duration') or mv_data.get('duration')),
|
2016-09-29 16:48:21 +00:00
|
|
|
|
'timestamp': timestamp,
|
2015-06-15 14:55:25 +00:00
|
|
|
|
'view_count': view_count,
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'like_count': int_or_none(mv_data.get('likes')),
|
|
|
|
|
'comment_count': int_or_none(mv_data.get('commcount')),
|
2016-12-29 21:21:49 +00:00
|
|
|
|
'is_live': is_live,
|
2021-10-31 05:13:49 +00:00
|
|
|
|
'subtitles': subtitles,
|
2013-11-01 21:28:51 +00:00
|
|
|
|
}
|
2014-11-17 22:52:00 +00:00
|
|
|
|
|
|
|
|
|
|
2016-07-13 14:51:44 +00:00
|
|
|
|
class VKUserVideosIE(VKBaseIE):
|
2015-07-18 11:23:33 +00:00
|
|
|
|
IE_NAME = 'vk:uservideos'
|
|
|
|
|
IE_DESC = "VK - User's Videos"
|
2022-10-09 01:50:44 +00:00
|
|
|
|
_VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/video/(?:playlist/)?(?P<id>[^?$#/&]+)(?!\?.*\bz=video)(?:[/?#&](?:.*?\bsection=(?P<section>\w+))?|$)'
|
2014-11-17 22:52:00 +00:00
|
|
|
|
_TEMPLATE_URL = 'https://vk.com/videos'
|
2015-07-18 11:22:25 +00:00
|
|
|
|
_TESTS = [{
|
2022-01-09 15:31:34 +00:00
|
|
|
|
'url': 'https://vk.com/video/@mobidevices',
|
2019-12-09 08:13:02 +00:00
|
|
|
|
'info_dict': {
|
2022-01-09 15:31:34 +00:00
|
|
|
|
'id': '-17892518_all',
|
2019-12-09 08:13:02 +00:00
|
|
|
|
},
|
2022-01-09 15:31:34 +00:00
|
|
|
|
'playlist_mincount': 1355,
|
2019-12-09 08:13:02 +00:00
|
|
|
|
}, {
|
2022-01-09 15:31:34 +00:00
|
|
|
|
'url': 'https://vk.com/video/@mobidevices?section=uploaded',
|
2015-02-17 23:33:41 +00:00
|
|
|
|
'info_dict': {
|
2022-01-09 15:31:34 +00:00
|
|
|
|
'id': '-17892518_uploaded',
|
2015-02-17 23:33:41 +00:00
|
|
|
|
},
|
2022-01-09 15:31:34 +00:00
|
|
|
|
'playlist_mincount': 182,
|
2022-10-09 01:50:44 +00:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://vk.com/video/playlist/-174476437_2',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '-174476437_2',
|
|
|
|
|
'title': 'Анонсы'
|
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 108,
|
2015-07-18 11:22:25 +00:00
|
|
|
|
}]
|
2019-12-09 08:13:02 +00:00
|
|
|
|
_VIDEO = collections.namedtuple('Video', ['owner_id', 'id'])
|
2015-07-18 11:22:25 +00:00
|
|
|
|
|
2022-01-09 15:31:34 +00:00
|
|
|
|
def _entries(self, page_id, section):
|
|
|
|
|
video_list_json = self._download_payload('al_video', page_id, {
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'act': 'load_videos_silent',
|
2022-01-09 15:31:34 +00:00
|
|
|
|
'offset': 0,
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'oid': page_id,
|
2019-12-09 08:13:02 +00:00
|
|
|
|
'section': section,
|
2022-01-09 15:31:34 +00:00
|
|
|
|
})[0][section]
|
|
|
|
|
count = video_list_json['count']
|
|
|
|
|
total = video_list_json['total']
|
|
|
|
|
video_list = video_list_json['list']
|
|
|
|
|
|
|
|
|
|
while True:
|
|
|
|
|
for video in video_list:
|
|
|
|
|
v = self._VIDEO._make(video[:2])
|
|
|
|
|
video_id = '%d_%d' % (v.owner_id, v.id)
|
|
|
|
|
yield self.url_result(
|
|
|
|
|
'http://vk.com/video' + video_id, VKIE.ie_key(), video_id)
|
|
|
|
|
if count >= total:
|
|
|
|
|
break
|
|
|
|
|
video_list_json = self._download_payload('al_video', page_id, {
|
|
|
|
|
'act': 'load_videos_silent',
|
|
|
|
|
'offset': count,
|
|
|
|
|
'oid': page_id,
|
|
|
|
|
'section': section,
|
|
|
|
|
})[0][section]
|
|
|
|
|
count += video_list_json['count']
|
|
|
|
|
video_list = video_list_json['list']
|
2019-12-09 08:13:02 +00:00
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2022-01-09 15:31:34 +00:00
|
|
|
|
u_id, section = self._match_valid_url(url).groups()
|
|
|
|
|
webpage = self._download_webpage(url, u_id)
|
2022-10-09 01:50:44 +00:00
|
|
|
|
|
|
|
|
|
if u_id.startswith('@'):
|
|
|
|
|
page_id = self._search_regex(r'data-owner-id\s?=\s?"([^"]+)"', webpage, 'page_id')
|
|
|
|
|
elif '_' in u_id:
|
|
|
|
|
page_id, section = u_id.split('_', 1)
|
|
|
|
|
else:
|
|
|
|
|
raise ExtractorError('Invalid URL', expected=True)
|
|
|
|
|
|
2019-12-09 08:13:02 +00:00
|
|
|
|
if not section:
|
|
|
|
|
section = 'all'
|
|
|
|
|
|
2022-10-09 01:50:44 +00:00
|
|
|
|
playlist_title = clean_html(get_element_by_class('VideoInfoPanel__title', webpage))
|
|
|
|
|
return self.playlist_result(self._entries(page_id, section), '%s_%s' % (page_id, section), playlist_title)
|
2016-07-13 14:51:44 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class VKWallPostIE(VKBaseIE):
|
|
|
|
|
IE_NAME = 'vk:wallpost'
|
|
|
|
|
_VALID_URL = r'https?://(?:(?:(?:(?:m|new)\.)?vk\.com/(?:[^?]+\?.*\bw=)?wall(?P<id>-?\d+_\d+)))'
|
|
|
|
|
_TESTS = [{
|
|
|
|
|
# public page URL, audio playlist
|
|
|
|
|
'url': 'https://vk.com/bs.official?w=wall-23538238_35',
|
|
|
|
|
'info_dict': {
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'id': '-23538238_35',
|
|
|
|
|
'title': 'Black Shadow - Wall post -23538238_35',
|
2016-07-13 14:51:44 +00:00
|
|
|
|
'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c',
|
|
|
|
|
},
|
|
|
|
|
'playlist': [{
|
|
|
|
|
'md5': '5ba93864ec5b85f7ce19a9af4af080f6',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '135220665_111806521',
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'ext': 'mp4',
|
2016-07-13 14:51:44 +00:00
|
|
|
|
'title': 'Black Shadow - Слепое Верование',
|
|
|
|
|
'duration': 370,
|
|
|
|
|
'uploader': 'Black Shadow',
|
|
|
|
|
'artist': 'Black Shadow',
|
|
|
|
|
'track': 'Слепое Верование',
|
|
|
|
|
},
|
|
|
|
|
}, {
|
|
|
|
|
'md5': '4cc7e804579122b17ea95af7834c9233',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '135220665_111802303',
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'ext': 'mp4',
|
2016-07-13 14:51:44 +00:00
|
|
|
|
'title': 'Black Shadow - Война - Негасимое Бездны Пламя!',
|
|
|
|
|
'duration': 423,
|
|
|
|
|
'uploader': 'Black Shadow',
|
|
|
|
|
'artist': 'Black Shadow',
|
|
|
|
|
'track': 'Война - Негасимое Бездны Пламя!',
|
|
|
|
|
},
|
|
|
|
|
}],
|
2016-08-17 23:14:05 +00:00
|
|
|
|
'params': {
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'skip_download': True,
|
2016-08-17 23:14:05 +00:00
|
|
|
|
},
|
2016-07-13 14:51:44 +00:00
|
|
|
|
'skip': 'Requires vk account credentials',
|
|
|
|
|
}, {
|
|
|
|
|
# single YouTube embed, no leading -
|
|
|
|
|
'url': 'https://vk.com/wall85155021_6319',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '85155021_6319',
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'title': 'Сергей Горбунов - Wall post 85155021_6319',
|
2016-07-13 14:51:44 +00:00
|
|
|
|
},
|
|
|
|
|
'playlist_count': 1,
|
|
|
|
|
'skip': 'Requires vk account credentials',
|
|
|
|
|
}, {
|
|
|
|
|
# wall page URL
|
|
|
|
|
'url': 'https://vk.com/wall-23538238_35',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
# mobile wall page URL
|
|
|
|
|
'url': 'https://m.vk.com/wall-23538238_35',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
2019-10-25 18:35:07 +00:00
|
|
|
|
_BASE64_CHARS = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMN0PQRSTUVWXYZO123456789+/='
|
2019-12-09 08:13:02 +00:00
|
|
|
|
_AUDIO = collections.namedtuple('Audio', ['id', 'owner_id', 'url', 'title', 'performer', 'duration', 'album_id', 'unk', 'author_link', 'lyrics', 'flags', 'context', 'extra', 'hashes', 'cover_url', 'ads'])
|
2019-10-25 18:35:07 +00:00
|
|
|
|
|
|
|
|
|
def _decode(self, enc):
|
|
|
|
|
dec = ''
|
|
|
|
|
e = n = 0
|
|
|
|
|
for c in enc:
|
|
|
|
|
r = self._BASE64_CHARS.index(c)
|
|
|
|
|
cond = n % 4
|
|
|
|
|
e = 64 * e + r if cond else r
|
|
|
|
|
n += 1
|
|
|
|
|
if cond:
|
|
|
|
|
dec += chr(255 & e >> (-2 * n & 6))
|
|
|
|
|
return dec
|
|
|
|
|
|
|
|
|
|
def _unmask_url(self, mask_url, vk_id):
|
|
|
|
|
if 'audio_api_unavailable' in mask_url:
|
|
|
|
|
extra = mask_url.split('?extra=')[1].split('#')
|
|
|
|
|
func, base = self._decode(extra[1]).split(chr(11))
|
|
|
|
|
mask_url = list(self._decode(extra[0]))
|
|
|
|
|
url_len = len(mask_url)
|
|
|
|
|
indexes = [None] * url_len
|
|
|
|
|
index = int(base) ^ vk_id
|
|
|
|
|
for n in range(url_len - 1, -1, -1):
|
|
|
|
|
index = (url_len * (n + 1) ^ index + n) % url_len
|
|
|
|
|
indexes[n] = index
|
|
|
|
|
for n in range(1, url_len):
|
|
|
|
|
c = mask_url[n]
|
|
|
|
|
index = indexes[url_len - 1 - n]
|
|
|
|
|
mask_url[n] = mask_url[index]
|
|
|
|
|
mask_url[index] = c
|
|
|
|
|
mask_url = ''.join(mask_url)
|
|
|
|
|
return mask_url
|
2016-07-13 14:51:44 +00:00
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
post_id = self._match_id(url)
|
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
webpage = self._download_payload('wkview', post_id, {
|
|
|
|
|
'act': 'show',
|
|
|
|
|
'w': 'wall' + post_id,
|
|
|
|
|
})[1]
|
2016-07-13 14:51:44 +00:00
|
|
|
|
|
|
|
|
|
description = clean_html(get_element_by_class('wall_post_text', webpage))
|
2016-08-17 23:14:05 +00:00
|
|
|
|
uploader = clean_html(get_element_by_class('author', webpage))
|
2016-07-13 14:51:44 +00:00
|
|
|
|
|
|
|
|
|
entries = []
|
|
|
|
|
|
2019-10-25 18:35:07 +00:00
|
|
|
|
for audio in re.findall(r'data-audio="([^"]+)', webpage):
|
|
|
|
|
audio = self._parse_json(unescapeHTML(audio), post_id)
|
2019-12-09 08:13:02 +00:00
|
|
|
|
a = self._AUDIO._make(audio[:16])
|
2019-10-25 18:35:07 +00:00
|
|
|
|
if not a.url:
|
|
|
|
|
continue
|
|
|
|
|
title = unescapeHTML(a.title)
|
2019-11-18 11:51:25 +00:00
|
|
|
|
performer = unescapeHTML(a.performer)
|
2019-10-25 18:35:07 +00:00
|
|
|
|
entries.append({
|
|
|
|
|
'id': '%s_%s' % (a.owner_id, a.id),
|
|
|
|
|
'url': self._unmask_url(a.url, a.ads['vk_id']),
|
2019-11-18 11:51:25 +00:00
|
|
|
|
'title': '%s - %s' % (performer, title) if performer else title,
|
|
|
|
|
'thumbnails': [{'url': c_url} for c_url in a.cover_url.split(',')] if a.cover_url else None,
|
|
|
|
|
'duration': int_or_none(a.duration),
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'uploader': uploader,
|
2019-11-18 11:51:25 +00:00
|
|
|
|
'artist': performer,
|
2019-10-25 18:35:07 +00:00
|
|
|
|
'track': title,
|
|
|
|
|
'ext': 'mp4',
|
2022-02-11 06:39:03 +00:00
|
|
|
|
'protocol': 'm3u8_native',
|
2019-10-25 18:35:07 +00:00
|
|
|
|
})
|
2016-07-13 14:51:44 +00:00
|
|
|
|
|
|
|
|
|
for video in re.finditer(
|
|
|
|
|
r'<a[^>]+href=(["\'])(?P<url>/video(?:-?[\d_]+).*?)\1', webpage):
|
|
|
|
|
entries.append(self.url_result(
|
|
|
|
|
compat_urlparse.urljoin(url, video.group('url')), VKIE.ie_key()))
|
|
|
|
|
|
|
|
|
|
title = 'Wall post %s' % post_id
|
|
|
|
|
|
|
|
|
|
return self.playlist_result(
|
|
|
|
|
orderedSet(entries), post_id,
|
|
|
|
|
'%s - %s' % (uploader, title) if uploader else title,
|
|
|
|
|
description)
|