2015-02-28 02:15:03 +08:00
|
|
|
|
# coding: utf-8
|
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
2016-04-26 00:15:15 +08:00
|
|
|
|
from ..compat import (
|
2017-04-17 04:24:34 +08:00
|
|
|
|
compat_etree_fromstring,
|
2016-04-26 00:15:15 +08:00
|
|
|
|
compat_parse_qs,
|
|
|
|
|
compat_urllib_parse_unquote,
|
|
|
|
|
compat_urllib_parse_urlparse,
|
|
|
|
|
)
|
2015-02-28 02:15:03 +08:00
|
|
|
|
from ..utils import (
|
2015-09-18 00:59:15 +08:00
|
|
|
|
ExtractorError,
|
2015-02-28 02:15:03 +08:00
|
|
|
|
unified_strdate,
|
|
|
|
|
int_or_none,
|
|
|
|
|
qualities,
|
2015-05-14 00:26:30 +08:00
|
|
|
|
unescapeHTML,
|
2017-11-28 16:04:51 +08:00
|
|
|
|
urlencode_postdata,
|
2015-02-28 02:15:03 +08:00
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class OdnoklassnikiIE(InfoExtractor):
|
2018-04-08 23:21:21 +08:00
|
|
|
|
_VALID_URL = r'''(?x)
|
|
|
|
|
https?://
|
|
|
|
|
(?:(?:www|m|mobile)\.)?
|
|
|
|
|
(?:odnoklassniki|ok)\.ru/
|
|
|
|
|
(?:
|
|
|
|
|
video(?:embed)?/|
|
|
|
|
|
web-api/video/moviePlayer/|
|
|
|
|
|
live/|
|
|
|
|
|
dk\?.*?st\.mvId=
|
|
|
|
|
)
|
|
|
|
|
(?P<id>[\d-]+)
|
|
|
|
|
'''
|
2015-02-28 02:15:03 +08:00
|
|
|
|
_TESTS = [{
|
2015-05-25 23:22:13 +08:00
|
|
|
|
# metadata in JSON
|
2015-02-28 02:15:03 +08:00
|
|
|
|
'url': 'http://ok.ru/video/20079905452',
|
2018-01-08 22:53:03 +08:00
|
|
|
|
'md5': '0b62089b479e06681abaaca9d204f152',
|
2015-02-28 02:15:03 +08:00
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '20079905452',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Культура меняет нас (прекрасный ролик!))',
|
|
|
|
|
'duration': 100,
|
2015-08-09 00:08:54 +08:00
|
|
|
|
'upload_date': '20141207',
|
2015-02-28 02:15:03 +08:00
|
|
|
|
'uploader_id': '330537914540',
|
|
|
|
|
'uploader': 'Виталий Добровольский',
|
|
|
|
|
'like_count': int,
|
2015-08-09 00:04:48 +08:00
|
|
|
|
'age_limit': 0,
|
2015-05-25 23:22:13 +08:00
|
|
|
|
},
|
|
|
|
|
}, {
|
|
|
|
|
# metadataUrl
|
2016-04-26 00:15:15 +08:00
|
|
|
|
'url': 'http://ok.ru/video/63567059965189-0?fromTime=5',
|
2017-04-19 07:16:31 +08:00
|
|
|
|
'md5': '6ff470ea2dd51d5d18c295a355b0b6bc',
|
2015-05-25 23:22:13 +08:00
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '63567059965189-0',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Девушка без комплексов ...',
|
|
|
|
|
'duration': 191,
|
2015-08-09 00:08:54 +08:00
|
|
|
|
'upload_date': '20150518',
|
2015-05-25 23:22:13 +08:00
|
|
|
|
'uploader_id': '534380003155',
|
2015-08-09 00:08:54 +08:00
|
|
|
|
'uploader': '☭ Андрей Мещанинов ☭',
|
2015-05-25 23:22:13 +08:00
|
|
|
|
'like_count': int,
|
2015-08-09 00:04:48 +08:00
|
|
|
|
'age_limit': 0,
|
2016-04-26 00:15:15 +08:00
|
|
|
|
'start_time': 5,
|
2015-02-28 02:15:03 +08:00
|
|
|
|
},
|
2015-09-03 00:08:50 +08:00
|
|
|
|
}, {
|
|
|
|
|
# YouTube embed (metadataUrl, provider == USER_YOUTUBE)
|
|
|
|
|
'url': 'http://ok.ru/video/64211978996595-1',
|
2017-04-19 07:16:31 +08:00
|
|
|
|
'md5': '2f206894ffb5dbfcce2c5a14b909eea5',
|
2015-09-03 00:08:50 +08:00
|
|
|
|
'info_dict': {
|
2017-11-28 16:04:51 +08:00
|
|
|
|
'id': 'V_VztHT5BzY',
|
2015-09-03 00:08:50 +08:00
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Космическая среда от 26 августа 2015',
|
|
|
|
|
'description': 'md5:848eb8b85e5e3471a3a803dae1343ed0',
|
|
|
|
|
'duration': 440,
|
|
|
|
|
'upload_date': '20150826',
|
2017-04-19 07:16:31 +08:00
|
|
|
|
'uploader_id': 'tvroscosmos',
|
|
|
|
|
'uploader': 'Телестудия Роскосмоса',
|
2015-09-03 00:08:50 +08:00
|
|
|
|
'age_limit': 0,
|
|
|
|
|
},
|
2016-04-26 00:05:47 +08:00
|
|
|
|
}, {
|
|
|
|
|
# YouTube embed (metadata, provider == USER_YOUTUBE, no metadata.movie.title field)
|
|
|
|
|
'url': 'http://ok.ru/video/62036049272859-0',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '62036049272859-0',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'МУЗЫКА ДОЖДЯ .',
|
|
|
|
|
'description': 'md5:6f1867132bd96e33bf53eda1091e8ed0',
|
|
|
|
|
'upload_date': '20120106',
|
|
|
|
|
'uploader_id': '473534735899',
|
|
|
|
|
'uploader': 'МARINA D',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2017-04-19 07:16:31 +08:00
|
|
|
|
'skip': 'Video has not been found',
|
2015-02-28 02:15:03 +08:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452',
|
|
|
|
|
'only_matching': True,
|
2015-09-01 16:34:05 +08:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://www.ok.ru/video/20648036891',
|
|
|
|
|
'only_matching': True,
|
2015-10-19 02:11:16 +08:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://www.ok.ru/videoembed/20648036891',
|
|
|
|
|
'only_matching': True,
|
2016-01-29 00:56:49 +08:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://m.ok.ru/video/20079905452',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://mobile.ok.ru/video/20079905452',
|
|
|
|
|
'only_matching': True,
|
2018-01-08 22:53:03 +08:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.ok.ru/live/484531969818',
|
|
|
|
|
'only_matching': True,
|
2018-04-08 23:13:00 +08:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://m.ok.ru/dk?st.cmd=movieLayer&st.discId=863789452017&st.retLoc=friend&st.rtu=%2Fdk%3Fst.cmd%3DfriendMovies%26st.mode%3Down%26st.mrkId%3D%257B%2522uploadedMovieMarker%2522%253A%257B%2522marker%2522%253A%25221519410114503%2522%252C%2522hasMore%2522%253Atrue%257D%252C%2522sharedMovieMarker%2522%253A%257B%2522marker%2522%253Anull%252C%2522hasMore%2522%253Afalse%257D%257D%26st.friendId%3D561722190321%26st.frwd%3Don%26_prevCmd%3DfriendMovies%26tkn%3D7257&st.discType=MOVIE&st.mvId=863789452017&_prevCmd=friendMovies&tkn=3648#lst#',
|
|
|
|
|
'only_matching': True,
|
2019-01-20 16:15:01 +08:00
|
|
|
|
}, {
|
|
|
|
|
# Paid video
|
|
|
|
|
'url': 'https://ok.ru/video/954886983203',
|
|
|
|
|
'only_matching': True,
|
2015-02-28 02:15:03 +08:00
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2016-04-26 00:15:15 +08:00
|
|
|
|
start_time = int_or_none(compat_parse_qs(
|
|
|
|
|
compat_urllib_parse_urlparse(url).query).get('fromTime', [None])[0])
|
|
|
|
|
|
2015-02-28 02:15:03 +08:00
|
|
|
|
video_id = self._match_id(url)
|
|
|
|
|
|
2015-05-25 23:27:43 +08:00
|
|
|
|
webpage = self._download_webpage(
|
|
|
|
|
'http://ok.ru/video/%s' % video_id, video_id)
|
2015-02-28 02:15:03 +08:00
|
|
|
|
|
2015-09-18 00:59:15 +08:00
|
|
|
|
error = self._search_regex(
|
|
|
|
|
r'[^>]+class="vp_video_stub_txt"[^>]*>([^<]+)<',
|
|
|
|
|
webpage, 'error', default=None)
|
|
|
|
|
if error:
|
|
|
|
|
raise ExtractorError(error, expected=True)
|
|
|
|
|
|
2015-02-28 02:15:03 +08:00
|
|
|
|
player = self._parse_json(
|
2015-05-14 00:26:30 +08:00
|
|
|
|
unescapeHTML(self._search_regex(
|
2015-09-02 23:38:56 +08:00
|
|
|
|
r'data-options=(?P<quote>["\'])(?P<player>{.+?%s.+?})(?P=quote)' % video_id,
|
|
|
|
|
webpage, 'player', group='player')),
|
2015-02-28 02:15:03 +08:00
|
|
|
|
video_id)
|
|
|
|
|
|
2015-05-25 23:22:13 +08:00
|
|
|
|
flashvars = player['flashvars']
|
|
|
|
|
|
|
|
|
|
metadata = flashvars.get('metadata')
|
|
|
|
|
if metadata:
|
|
|
|
|
metadata = self._parse_json(metadata, video_id)
|
|
|
|
|
else:
|
2017-11-28 16:04:51 +08:00
|
|
|
|
data = {}
|
|
|
|
|
st_location = flashvars.get('location')
|
|
|
|
|
if st_location:
|
|
|
|
|
data['st.location'] = st_location
|
2015-05-25 23:22:13 +08:00
|
|
|
|
metadata = self._download_json(
|
2015-07-18 01:45:00 +08:00
|
|
|
|
compat_urllib_parse_unquote(flashvars['metadataUrl']),
|
2017-11-28 16:04:51 +08:00
|
|
|
|
video_id, 'Downloading metadata JSON',
|
|
|
|
|
data=urlencode_postdata(data))
|
2015-02-28 02:15:03 +08:00
|
|
|
|
|
|
|
|
|
movie = metadata['movie']
|
2016-04-26 00:05:47 +08:00
|
|
|
|
|
|
|
|
|
# Some embedded videos may not contain title in movie dict (e.g.
|
|
|
|
|
# http://ok.ru/video/62036049272859-0) thus we allow missing title
|
|
|
|
|
# here and it's going to be extracted later by an extractor that
|
|
|
|
|
# will process the actual embed.
|
|
|
|
|
provider = metadata.get('provider')
|
|
|
|
|
title = movie['title'] if provider == 'UPLOADED_ODKL' else movie.get('title')
|
|
|
|
|
|
2015-02-28 02:15:03 +08:00
|
|
|
|
thumbnail = movie.get('poster')
|
|
|
|
|
duration = int_or_none(movie.get('duration'))
|
|
|
|
|
|
|
|
|
|
author = metadata.get('author', {})
|
|
|
|
|
uploader_id = author.get('id')
|
|
|
|
|
uploader = author.get('name')
|
|
|
|
|
|
|
|
|
|
upload_date = unified_strdate(self._html_search_meta(
|
2015-05-25 23:22:13 +08:00
|
|
|
|
'ya:ovs:upload_date', webpage, 'upload date', default=None))
|
2015-02-28 02:15:03 +08:00
|
|
|
|
|
|
|
|
|
age_limit = None
|
|
|
|
|
adult = self._html_search_meta(
|
2015-05-25 23:22:13 +08:00
|
|
|
|
'ya:ovs:adult', webpage, 'age limit', default=None)
|
2015-02-28 02:15:03 +08:00
|
|
|
|
if adult:
|
|
|
|
|
age_limit = 18 if adult == 'true' else 0
|
|
|
|
|
|
|
|
|
|
like_count = int_or_none(metadata.get('likeCount'))
|
|
|
|
|
|
2015-09-03 00:08:50 +08:00
|
|
|
|
info = {
|
2015-02-28 02:15:03 +08:00
|
|
|
|
'id': video_id,
|
|
|
|
|
'title': title,
|
|
|
|
|
'thumbnail': thumbnail,
|
|
|
|
|
'duration': duration,
|
|
|
|
|
'upload_date': upload_date,
|
|
|
|
|
'uploader': uploader,
|
|
|
|
|
'uploader_id': uploader_id,
|
|
|
|
|
'like_count': like_count,
|
|
|
|
|
'age_limit': age_limit,
|
2016-04-26 00:15:15 +08:00
|
|
|
|
'start_time': start_time,
|
2015-02-28 02:15:03 +08:00
|
|
|
|
}
|
2015-09-03 00:08:50 +08:00
|
|
|
|
|
2016-04-26 00:05:47 +08:00
|
|
|
|
if provider == 'USER_YOUTUBE':
|
2015-09-03 00:08:50 +08:00
|
|
|
|
info.update({
|
|
|
|
|
'_type': 'url_transparent',
|
|
|
|
|
'url': movie['contentId'],
|
|
|
|
|
})
|
|
|
|
|
return info
|
|
|
|
|
|
2018-01-08 22:53:03 +08:00
|
|
|
|
assert title
|
|
|
|
|
if provider == 'LIVE_TV_APP':
|
|
|
|
|
info['title'] = self._live_title(title)
|
|
|
|
|
|
2017-04-17 04:24:34 +08:00
|
|
|
|
quality = qualities(('4', '0', '1', '2', '3', '5'))
|
2015-09-03 00:08:50 +08:00
|
|
|
|
|
|
|
|
|
formats = [{
|
|
|
|
|
'url': f['url'],
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'format_id': f['name'],
|
|
|
|
|
} for f in metadata['videos']]
|
2017-04-17 04:24:34 +08:00
|
|
|
|
|
|
|
|
|
m3u8_url = metadata.get('hlsManifestUrl')
|
|
|
|
|
if m3u8_url:
|
|
|
|
|
formats.extend(self._extract_m3u8_formats(
|
|
|
|
|
m3u8_url, video_id, 'mp4', 'm3u8_native',
|
|
|
|
|
m3u8_id='hls', fatal=False))
|
|
|
|
|
|
|
|
|
|
dash_manifest = metadata.get('metadataEmbedded')
|
|
|
|
|
if dash_manifest:
|
|
|
|
|
formats.extend(self._parse_mpd_formats(
|
|
|
|
|
compat_etree_fromstring(dash_manifest), 'mpd'))
|
|
|
|
|
|
|
|
|
|
for fmt in formats:
|
|
|
|
|
fmt_type = self._search_regex(
|
|
|
|
|
r'\btype[/=](\d)', fmt['url'],
|
|
|
|
|
'format type', default=None)
|
|
|
|
|
if fmt_type:
|
|
|
|
|
fmt['quality'] = quality(fmt_type)
|
|
|
|
|
|
2018-01-08 22:53:03 +08:00
|
|
|
|
# Live formats
|
|
|
|
|
m3u8_url = metadata.get('hlsMasterPlaylistUrl')
|
|
|
|
|
if m3u8_url:
|
|
|
|
|
formats.extend(self._extract_m3u8_formats(
|
|
|
|
|
m3u8_url, video_id, 'mp4', entry_protocol='m3u8',
|
|
|
|
|
m3u8_id='hls', fatal=False))
|
|
|
|
|
rtmp_url = metadata.get('rtmpUrl')
|
|
|
|
|
if rtmp_url:
|
|
|
|
|
formats.append({
|
|
|
|
|
'url': rtmp_url,
|
|
|
|
|
'format_id': 'rtmp',
|
|
|
|
|
'ext': 'flv',
|
|
|
|
|
})
|
|
|
|
|
|
2019-01-20 16:15:01 +08:00
|
|
|
|
if not formats:
|
|
|
|
|
payment_info = metadata.get('paymentInfo')
|
|
|
|
|
if payment_info:
|
|
|
|
|
raise ExtractorError('This video is paid, subscribe to download it', expected=True)
|
|
|
|
|
|
2015-09-03 00:09:33 +08:00
|
|
|
|
self._sort_formats(formats)
|
2015-09-03 00:08:50 +08:00
|
|
|
|
|
|
|
|
|
info['formats'] = formats
|
|
|
|
|
return info
|