2013-11-01 22:28:51 +01:00
|
|
|
|
# encoding: utf-8
|
2014-01-21 17:32:03 +01:00
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
2013-11-01 22:28:51 +01:00
|
|
|
|
import re
|
|
|
|
|
import json
|
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
2014-12-13 12:24:42 +01:00
|
|
|
|
from ..compat import (
|
|
|
|
|
compat_str,
|
|
|
|
|
compat_urllib_parse,
|
|
|
|
|
compat_urllib_request,
|
|
|
|
|
)
|
2013-11-01 22:28:51 +01:00
|
|
|
|
from ..utils import (
|
2014-02-16 20:05:15 +01:00
|
|
|
|
ExtractorError,
|
2014-12-13 12:24:42 +01:00
|
|
|
|
orderedSet,
|
2013-11-01 22:28:51 +01:00
|
|
|
|
unescapeHTML,
|
2014-11-22 00:16:12 +01:00
|
|
|
|
unified_strdate,
|
2014-12-13 12:24:42 +01:00
|
|
|
|
)
|
2013-11-01 22:28:51 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class VKIE(InfoExtractor):
|
2014-01-21 17:32:03 +01:00
|
|
|
|
IE_NAME = 'vk.com'
|
2014-11-17 23:52:00 +01:00
|
|
|
|
_VALID_URL = r'https?://(?:m\.)?vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:.+?\?.*?z=)?video(?P<videoid>[^s].*?)(?:\?|%2F|$))'
|
2014-02-16 20:17:10 +01:00
|
|
|
|
_NETRC_MACHINE = 'vk'
|
2013-11-01 22:28:51 +01:00
|
|
|
|
|
2014-02-16 20:05:15 +01:00
|
|
|
|
_TESTS = [
|
|
|
|
|
{
|
|
|
|
|
'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
|
|
|
|
|
'md5': '0deae91935c54e00003c2a00646315f0',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '162222515',
|
|
|
|
|
'ext': 'flv',
|
|
|
|
|
'title': 'ProtivoGunz - Хуёвая песня',
|
2015-03-01 22:30:18 +01:00
|
|
|
|
'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
|
2014-02-16 20:05:15 +01:00
|
|
|
|
'duration': 195,
|
2014-11-21 23:23:39 +01:00
|
|
|
|
'upload_date': '20120212',
|
2014-02-16 20:05:15 +01:00
|
|
|
|
},
|
2013-11-01 22:28:51 +01:00
|
|
|
|
},
|
2014-02-16 20:05:15 +01:00
|
|
|
|
{
|
2014-11-21 23:52:01 +01:00
|
|
|
|
'url': 'http://vk.com/video205387401_165548505',
|
|
|
|
|
'md5': '6c0aeb2e90396ba97035b9cbde548700',
|
2014-02-16 20:05:15 +01:00
|
|
|
|
'info_dict': {
|
2014-11-21 23:52:01 +01:00
|
|
|
|
'id': '165548505',
|
2014-02-16 20:05:15 +01:00
|
|
|
|
'ext': 'mp4',
|
2014-11-21 23:52:01 +01:00
|
|
|
|
'uploader': 'Tom Cruise',
|
|
|
|
|
'title': 'No name',
|
|
|
|
|
'duration': 9,
|
|
|
|
|
'upload_date': '20130721'
|
2014-02-16 20:05:15 +01:00
|
|
|
|
}
|
|
|
|
|
},
|
2014-02-28 17:51:54 +01:00
|
|
|
|
{
|
|
|
|
|
'note': 'Embedded video',
|
|
|
|
|
'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
|
|
|
|
|
'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '162925554',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'uploader': 'Vladimir Gavrin',
|
|
|
|
|
'title': 'Lin Dan',
|
|
|
|
|
'duration': 101,
|
2014-11-21 23:23:39 +01:00
|
|
|
|
'upload_date': '20120730',
|
2014-02-28 17:51:54 +01:00
|
|
|
|
}
|
|
|
|
|
},
|
2014-02-16 20:05:15 +01:00
|
|
|
|
{
|
2014-11-21 23:52:01 +01:00
|
|
|
|
# VIDEO NOW REMOVED
|
|
|
|
|
# please update if you find a video whose URL follows the same pattern
|
2014-02-16 20:05:15 +01:00
|
|
|
|
'url': 'http://vk.com/video-8871596_164049491',
|
|
|
|
|
'md5': 'a590bcaf3d543576c9bd162812387666',
|
|
|
|
|
'note': 'Only available for registered users',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '164049491',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'uploader': 'Триллеры',
|
2014-06-29 14:33:39 +02:00
|
|
|
|
'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
|
2014-02-16 20:05:15 +01:00
|
|
|
|
'duration': 8352,
|
2014-11-21 23:52:01 +01:00
|
|
|
|
'upload_date': '20121218'
|
2014-02-16 20:05:15 +01:00
|
|
|
|
},
|
|
|
|
|
'skip': 'Requires vk account credentials',
|
2014-02-28 17:51:54 +01:00
|
|
|
|
},
|
2014-06-29 14:33:39 +02:00
|
|
|
|
{
|
|
|
|
|
'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
|
|
|
|
|
'md5': '4d7a5ef8cf114dfa09577e57b2993202',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '168067957',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'uploader': 'Киномания - лучшее из мира кино',
|
|
|
|
|
'title': ' ',
|
|
|
|
|
'duration': 7291,
|
2014-11-21 23:23:39 +01:00
|
|
|
|
'upload_date': '20140328',
|
2014-06-29 14:33:39 +02:00
|
|
|
|
},
|
|
|
|
|
'skip': 'Requires vk account credentials',
|
|
|
|
|
},
|
2014-06-29 15:07:59 +02:00
|
|
|
|
{
|
|
|
|
|
'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
|
|
|
|
|
'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
|
|
|
|
|
'note': 'ivi.ru embed',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '60690',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Книга Илая',
|
|
|
|
|
'duration': 6771,
|
2014-11-21 23:23:39 +01:00
|
|
|
|
'upload_date': '20140626',
|
2014-06-29 15:07:59 +02:00
|
|
|
|
},
|
2014-06-29 22:16:31 +02:00
|
|
|
|
'skip': 'Only works from Russia',
|
2014-06-29 15:07:59 +02:00
|
|
|
|
},
|
2014-11-23 10:11:04 +01:00
|
|
|
|
{
|
|
|
|
|
# removed video, just testing that we match the pattern
|
|
|
|
|
'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2014-02-16 20:05:15 +01:00
|
|
|
|
]
|
|
|
|
|
|
|
|
|
|
def _login(self):
|
|
|
|
|
(username, password) = self._get_login_info()
|
|
|
|
|
if username is None:
|
|
|
|
|
return
|
|
|
|
|
|
|
|
|
|
login_form = {
|
|
|
|
|
'act': 'login',
|
|
|
|
|
'role': 'al_frame',
|
|
|
|
|
'expire': '1',
|
2015-06-12 23:09:35 +02:00
|
|
|
|
'email': username.encode('cp1251'),
|
|
|
|
|
'pass': password.encode('cp1251'),
|
2014-02-16 20:05:15 +01:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
request = compat_urllib_request.Request('https://login.vk.com/?act=login',
|
2014-11-23 21:39:15 +01:00
|
|
|
|
compat_urllib_parse.urlencode(login_form).encode('utf-8'))
|
2014-02-16 20:05:15 +01:00
|
|
|
|
login_page = self._download_webpage(request, None, note='Logging in as %s' % username)
|
|
|
|
|
|
|
|
|
|
if re.search(r'onLoginFailed', login_page):
|
|
|
|
|
raise ExtractorError('Unable to login, incorrect username and/or password', expected=True)
|
|
|
|
|
|
|
|
|
|
def _real_initialize(self):
|
|
|
|
|
self._login()
|
2013-11-01 22:28:51 +01:00
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
mobj = re.match(self._VALID_URL, url)
|
2014-02-28 17:51:54 +01:00
|
|
|
|
video_id = mobj.group('videoid')
|
|
|
|
|
|
|
|
|
|
if not video_id:
|
|
|
|
|
video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
|
2014-02-16 20:05:15 +01:00
|
|
|
|
|
2015-03-01 16:56:30 +01:00
|
|
|
|
info_url = 'http://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
|
2013-11-01 22:28:51 +01:00
|
|
|
|
info_page = self._download_webpage(info_url, video_id)
|
2014-02-16 20:05:15 +01:00
|
|
|
|
|
2014-10-28 15:35:25 +01:00
|
|
|
|
ERRORS = {
|
|
|
|
|
r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
|
2014-11-23 22:14:27 +01:00
|
|
|
|
'Video %s has been removed from public access due to rightholder complaint.',
|
|
|
|
|
|
2014-10-28 15:35:25 +01:00
|
|
|
|
r'<!>Please log in or <':
|
2014-11-23 22:14:27 +01:00
|
|
|
|
'Video %s is only available for registered users, '
|
|
|
|
|
'use --username and --password options to provide account credentials.',
|
|
|
|
|
|
|
|
|
|
r'<!>Unknown error':
|
2015-03-01 16:55:43 +01:00
|
|
|
|
'Video %s does not exist.',
|
|
|
|
|
|
|
|
|
|
r'<!>Видео временно недоступно':
|
|
|
|
|
'Video %s is temporarily unavailable.',
|
2014-10-28 15:35:25 +01:00
|
|
|
|
}
|
2014-02-16 20:05:15 +01:00
|
|
|
|
|
2014-10-28 15:35:25 +01:00
|
|
|
|
for error_re, error_msg in ERRORS.items():
|
|
|
|
|
if re.search(error_re, info_page):
|
|
|
|
|
raise ExtractorError(error_msg % video_id, expected=True)
|
2014-10-28 15:06:07 +01:00
|
|
|
|
|
2013-11-01 22:28:51 +01:00
|
|
|
|
m_yt = re.search(r'src="(http://www.youtube.com/.*?)"', info_page)
|
|
|
|
|
if m_yt is not None:
|
2014-05-11 11:43:59 +02:00
|
|
|
|
self.to_screen('Youtube video detected')
|
2013-11-01 22:28:51 +01:00
|
|
|
|
return self.url_result(m_yt.group(1), 'Youtube')
|
2014-06-29 15:07:59 +02:00
|
|
|
|
|
2015-01-04 03:15:27 +01:00
|
|
|
|
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)
|
|
|
|
|
|
2015-06-15 16:46:10 +02:00
|
|
|
|
m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
|
2014-06-29 15:07:59 +02:00
|
|
|
|
if m_opts:
|
2015-06-15 16:46:10 +02:00
|
|
|
|
m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
|
2014-06-29 15:07:59 +02:00
|
|
|
|
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)
|
|
|
|
|
|
2015-06-15 16:46:10 +02:00
|
|
|
|
data_json = self._search_regex(r'var\s+vars\s*=\s*({.+?});', info_page, 'vars')
|
2014-01-21 17:29:04 +01:00
|
|
|
|
data = json.loads(data_json)
|
2013-11-01 22:28:51 +01:00
|
|
|
|
|
2014-11-18 21:19:56 +01:00
|
|
|
|
# Extract upload date
|
|
|
|
|
upload_date = None
|
2015-06-15 16:47:01 +02:00
|
|
|
|
mobj = re.search(r'id="mv_date(?:_views)?_wrap"[^>]*>([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
|
2014-11-18 21:19:56 +01:00
|
|
|
|
if mobj is not None:
|
2014-11-23 21:39:15 +01:00
|
|
|
|
mobj.group(1) + ' ' + mobj.group(2)
|
2014-11-18 21:19:56 +01:00
|
|
|
|
upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
|
|
|
|
|
|
2014-01-21 18:21:44 +01:00
|
|
|
|
formats = [{
|
|
|
|
|
'format_id': k,
|
|
|
|
|
'url': v,
|
|
|
|
|
'width': int(k[len('url'):]),
|
|
|
|
|
} for k, v in data.items()
|
|
|
|
|
if k.startswith('url')]
|
|
|
|
|
self._sort_formats(formats)
|
|
|
|
|
|
2013-11-01 22:28:51 +01:00
|
|
|
|
return {
|
2014-01-21 17:29:04 +01:00
|
|
|
|
'id': compat_str(data['vid']),
|
2014-01-21 18:21:44 +01:00
|
|
|
|
'formats': formats,
|
2014-01-21 17:29:04 +01:00
|
|
|
|
'title': unescapeHTML(data['md_title']),
|
2014-01-21 18:21:44 +01:00
|
|
|
|
'thumbnail': data.get('jpg'),
|
|
|
|
|
'uploader': data.get('md_author'),
|
2014-11-18 21:19:56 +01:00
|
|
|
|
'duration': data.get('duration'),
|
|
|
|
|
'upload_date': upload_date,
|
2013-11-01 22:28:51 +01:00
|
|
|
|
}
|
2014-11-17 23:52:00 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class VKUserVideosIE(InfoExtractor):
|
|
|
|
|
IE_NAME = 'vk.com:user-videos'
|
2014-11-21 23:54:11 +01:00
|
|
|
|
IE_DESC = 'vk.com:All of a user\'s videos'
|
2014-11-22 00:03:31 +01:00
|
|
|
|
_VALID_URL = r'https?://vk\.com/videos(?P<id>[0-9]+)(?:m\?.*)?'
|
2014-11-17 23:52:00 +01:00
|
|
|
|
_TEMPLATE_URL = 'https://vk.com/videos'
|
|
|
|
|
_TEST = {
|
|
|
|
|
'url': 'http://vk.com/videos205387401',
|
2015-02-18 00:33:41 +01:00
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '205387401',
|
|
|
|
|
},
|
2014-11-17 23:52:00 +01:00
|
|
|
|
'playlist_mincount': 4,
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2014-11-22 00:21:03 +01:00
|
|
|
|
page_id = self._match_id(url)
|
2014-11-17 23:52:00 +01:00
|
|
|
|
page = self._download_webpage(url, page_id)
|
2014-11-23 10:11:52 +01:00
|
|
|
|
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]
|
2014-11-22 00:25:05 +01:00
|
|
|
|
return self.playlist_result(url_entries, page_id)
|