1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
youtube-dl/youtube_dl/extractor/odnoklassniki.py

150 lines
4.8 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote
from ..utils import (
2015-09-17 16:59:15 +00:00
ExtractorError,
unified_strdate,
int_or_none,
qualities,
unescapeHTML,
)
class OdnoklassnikiIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:odnoklassniki|ok)\.ru/(?:video|web-api/video/moviePlayer)/(?P<id>[\d-]+)'
_TESTS = [{
# metadata in JSON
'url': 'http://ok.ru/video/20079905452',
2015-08-08 16:08:54 +00:00
'md5': '6ba728d85d60aa2e6dd37c9e70fdc6bc',
'info_dict': {
'id': '20079905452',
'ext': 'mp4',
'title': 'Культура меняет нас (прекрасный ролик!))',
'duration': 100,
2015-08-08 16:08:54 +00:00
'upload_date': '20141207',
'uploader_id': '330537914540',
'uploader': 'Виталий Добровольский',
'like_count': int,
2015-08-08 16:04:48 +00:00
'age_limit': 0,
},
2015-09-17 16:59:32 +00:00
'skip': 'Video has been blocked',
}, {
# metadataUrl
'url': 'http://ok.ru/video/63567059965189-0',
'md5': '9676cf86eff5391d35dea675d224e131',
'info_dict': {
'id': '63567059965189-0',
'ext': 'mp4',
'title': 'Девушка без комплексов ...',
'duration': 191,
2015-08-08 16:08:54 +00:00
'upload_date': '20150518',
'uploader_id': '534380003155',
2015-08-08 16:08:54 +00:00
'uploader': '☭ Андрей Мещанинов ☭',
'like_count': int,
2015-08-08 16:04:48 +00:00
'age_limit': 0,
},
2015-09-02 16:08:50 +00:00
}, {
# YouTube embed (metadataUrl, provider == USER_YOUTUBE)
'url': 'http://ok.ru/video/64211978996595-1',
'md5': '5d7475d428845cd2e13bae6f1a992278',
'info_dict': {
'id': '64211978996595-1',
'ext': 'mp4',
'title': 'Космическая среда от 26 августа 2015',
'description': 'md5:848eb8b85e5e3471a3a803dae1343ed0',
'duration': 440,
'upload_date': '20150826',
'uploader_id': '750099571',
'uploader': 'Алина П',
'age_limit': 0,
},
}, {
'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452',
'only_matching': True,
}, {
'url': 'http://www.ok.ru/video/20648036891',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
2015-05-25 15:27:43 +00:00
webpage = self._download_webpage(
'http://ok.ru/video/%s' % video_id, video_id)
2015-09-17 16:59:15 +00:00
error = self._search_regex(
r'[^>]+class="vp_video_stub_txt"[^>]*>([^<]+)<',
webpage, 'error', default=None)
if error:
raise ExtractorError(error, expected=True)
player = self._parse_json(
unescapeHTML(self._search_regex(
2015-09-02 15:38:56 +00:00
r'data-options=(?P<quote>["\'])(?P<player>{.+?%s.+?})(?P=quote)' % video_id,
webpage, 'player', group='player')),
video_id)
flashvars = player['flashvars']
metadata = flashvars.get('metadata')
if metadata:
metadata = self._parse_json(metadata, video_id)
else:
metadata = self._download_json(
compat_urllib_parse_unquote(flashvars['metadataUrl']),
video_id, 'Downloading metadata JSON')
movie = metadata['movie']
title = movie['title']
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(
'ya:ovs:upload_date', webpage, 'upload date', default=None))
age_limit = None
adult = self._html_search_meta(
'ya:ovs:adult', webpage, 'age limit', default=None)
if adult:
age_limit = 18 if adult == 'true' else 0
like_count = int_or_none(metadata.get('likeCount'))
2015-09-02 16:08:50 +00:00
info = {
'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,
}
2015-09-02 16:08:50 +00:00
if metadata.get('provider') == 'USER_YOUTUBE':
info.update({
'_type': 'url_transparent',
'url': movie['contentId'],
})
return info
quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd'))
formats = [{
'url': f['url'],
'ext': 'mp4',
'format_id': f['name'],
'quality': quality(f['name']),
} for f in metadata['videos']]
2015-09-02 16:09:33 +00:00
self._sort_formats(formats)
2015-09-02 16:08:50 +00:00
info['formats'] = formats
return info