import collections
import re
-import sys
from .common import InfoExtractor
-from ..compat import (
- compat_str,
- compat_urlparse,
-)
+from ..compat import compat_urlparse
from ..utils import (
clean_html,
ExtractorError,
'pass': password.encode('cp1251'),
})
- # https://new.vk.com/ serves two same remixlhk cookies in Set-Cookie header
- # and expects the first one to be set rather than second (see
- # https://github.com/rg3/youtube-dl/issues/9841#issuecomment-227871201).
- # As of RFC6265 the newer one cookie should be set into cookie store
- # what actually happens.
- # We will workaround this VK issue by resetting the remixlhk cookie to
- # the first one manually.
- for header, cookies in url_handle.headers.items():
- if header.lower() != 'set-cookie':
- continue
- if sys.version_info[0] >= 3:
- cookies = cookies.encode('iso-8859-1')
- cookies = cookies.decode('utf-8')
- remixlhk = re.search(r'remixlhk=(.+?);.*?\bdomain=(.+?)(?:[,;]|$)', cookies)
- if remixlhk:
- value, domain = remixlhk.groups()
- self._set_cookie(domain, 'remixlhk', value)
- break
+ # 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')
login_page = self._download_webpage(
'https://login.vk.com/?act=login', None,
'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
'md5': '7babad3b85ea2e91948005b1b8b0cb84',
'info_dict': {
- 'id': '162222515',
+ 'id': '-77521_162222515',
'ext': 'mp4',
'title': 'ProtivoGunz - Хуёвая песня',
'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
'url': 'http://vk.com/video205387401_165548505',
'md5': '6c0aeb2e90396ba97035b9cbde548700',
'info_dict': {
- 'id': '165548505',
+ 'id': '205387401_165548505',
'ext': 'mp4',
'title': 'No name',
'uploader': 'Tom Cruise',
'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
'info_dict': {
- 'id': '162925554',
+ 'id': '32194266_162925554',
'ext': 'mp4',
'uploader': 'Vladimir Gavrin',
'title': 'Lin Dan',
'md5': 'a590bcaf3d543576c9bd162812387666',
'note': 'Only available for registered users',
'info_dict': {
- 'id': '164049491',
+ 'id': '-8871596_164049491',
'ext': 'mp4',
'uploader': 'Триллеры',
'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
'md5': '4d7a5ef8cf114dfa09577e57b2993202',
'info_dict': {
- 'id': '168067957',
+ 'id': '-43215063_168067957',
'ext': 'mp4',
'uploader': 'Киномания - лучшее из мира кино',
'title': ' ',
'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
'note': 'ivi.ru embed',
'info_dict': {
- 'id': '60690',
+ 'id': '-43215063_169084319',
'ext': 'mp4',
'title': 'Книга Илая',
'duration': 6771,
'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
'md5': '091287af5402239a1051c37ec7b92913',
'info_dict': {
- 'id': '171201961',
+ 'id': '30481095_171201961',
'ext': 'mp4',
'title': 'ТюменцевВВ_09.07.2015',
'uploader': 'Anton Ivanov',
'url': 'https://vk.com/video276849682_170681728',
'info_dict': {
'id': 'V3K4mi0SYkc',
- 'ext': 'webm',
+ 'ext': 'mp4',
'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
- 'duration': 179,
+ 'duration': 178,
'upload_date': '20130116',
'uploader': "Children's Joy Foundation Inc.",
'uploader_id': 'thecjf',
'url': 'http://vk.com/video-110305615_171782105',
'md5': 'e13fcda136f99764872e739d13fac1d1',
'info_dict': {
- 'id': '171782105',
+ 'id': '-110305615_171782105',
'ext': 'mp4',
'title': 'S-Dance, репетиции к The way show',
'uploader': 'THE WAY SHOW | 17 апреля',
{
# finished live stream, postlive_mp4
'url': 'https://vk.com/videos-387766?z=video-387766_456242764%2Fpl_-387766_-2',
- 'md5': '90d22d051fccbbe9becfccc615be6791',
'info_dict': {
- 'id': '456242764',
+ 'id': '-387766_456242764',
'ext': 'mp4',
- 'title': 'ИгроМир 2016 — день 1',
+ 'title': 'ИгроМир 2016 День 1 — Игромания Утром',
'uploader': 'Игромания',
'duration': 5239,
- 'view_count': int,
+ # TODO: use act=show to extract view_count
+ # 'view_count': int,
+ 'upload_date': '20160929',
+ 'uploader_id': '-387766',
+ 'timestamp': 1475137527,
},
},
{
# This video is no longer available, because its author has been blocked.
'url': 'https://vk.com/video-10639516_456240611',
'only_matching': True,
- }
- ]
+ },
+ {
+ # The video is not available in your region.
+ 'url': 'https://vk.com/video-51812607_171445436',
+ 'only_matching': True,
+ }]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
r'<!>This video is no longer available, because it has been deleted.':
'Video %s is no longer available, because it has been deleted.',
+
+ 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():
data = self._parse_json(
self._search_regex(
r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n', info_page,
- 'player params'),
- video_id)['params'][0]
+ 'player params', default='{}'),
+ video_id)
+ if data:
+ data = data['params'][0]
+
+ # <!--{...}
+ if not data:
+ data = self._parse_json(
+ self._search_regex(
+ r'<!--\s*({.+})', info_page, 'payload'),
+ video_id)['payload'][-1][-1]['player']['params'][0]
title = unescapeHTML(data['md_title'])
format_url = url_or_none(format_url)
if not format_url or not format_url.startswith(('http', '//', 'rtmp')):
continue
- if (format_id.startswith(('url', 'cache')) or
- format_id in ('extra_data', 'live_mp4', 'postlive_mp4')):
+ if (format_id.startswith(('url', 'cache'))
+ or format_id in ('extra_data', 'live_mp4', 'postlive_mp4')):
height = int_or_none(self._search_regex(
r'^(?:url|cache)(\d+)', format_id, 'height', default=None))
formats.append({
self._sort_formats(formats)
return {
- 'id': compat_str(data.get('vid') or video_id),
+ 'id': video_id,
'formats': formats,
'title': title,
'thumbnail': data.get('jpg'),
Rapsys Git / youtubedl / blobdiff