yt-dlp/youtube_dl/extractor/sina.py
Sergey M? 5c2266df4b Switch codebase to use sanitized_Request instead of
compat_urllib_request.Request

[downloader/dash] Use sanitized_Request

[downloader/http] Use sanitized_Request

[atresplayer] Use sanitized_Request

[bambuser] Use sanitized_Request

[bliptv] Use sanitized_Request

[brightcove] Use sanitized_Request

[cbs] Use sanitized_Request

[ceskatelevize] Use sanitized_Request

[collegerama] Use sanitized_Request

[extractor/common] Use sanitized_Request

[crunchyroll] Use sanitized_Request

[dailymotion] Use sanitized_Request

[dcn] Use sanitized_Request

[dramafever] Use sanitized_Request

[dumpert] Use sanitized_Request

[eitb] Use sanitized_Request

[escapist] Use sanitized_Request

[everyonesmixtape] Use sanitized_Request

[extremetube] Use sanitized_Request

[facebook] Use sanitized_Request

[fc2] Use sanitized_Request

[flickr] Use sanitized_Request

[4tube] Use sanitized_Request

[gdcvault] Use sanitized_Request

[extractor/generic] Use sanitized_Request

[hearthisat] Use sanitized_Request

[hotnewhiphop] Use sanitized_Request

[hypem] Use sanitized_Request

[iprima] Use sanitized_Request

[ivi] Use sanitized_Request

[keezmovies] Use sanitized_Request

[letv] Use sanitized_Request

[lynda] Use sanitized_Request

[metacafe] Use sanitized_Request

[minhateca] Use sanitized_Request

[miomio] Use sanitized_Request

[meovideo] Use sanitized_Request

[mofosex] Use sanitized_Request

[moniker] Use sanitized_Request

[mooshare] Use sanitized_Request

[movieclips] Use sanitized_Request

[mtv] Use sanitized_Request

[myvideo] Use sanitized_Request

[neteasemusic] Use sanitized_Request

[nfb] Use sanitized_Request

[niconico] Use sanitized_Request

[noco] Use sanitized_Request

[nosvideo] Use sanitized_Request

[novamov] Use sanitized_Request

[nowness] Use sanitized_Request

[nuvid] Use sanitized_Request

[played] Use sanitized_Request

[pluralsight] Use sanitized_Request

[pornhub] Use sanitized_Request

[pornotube] Use sanitized_Request

[primesharetv] Use sanitized_Request

[promptfile] Use sanitized_Request

[qqmusic] Use sanitized_Request

[rtve] Use sanitized_Request

[safari] Use sanitized_Request

[sandia] Use sanitized_Request

[shared] Use sanitized_Request

[sharesix] Use sanitized_Request

[sina] Use sanitized_Request

[smotri] Use sanitized_Request

[sohu] Use sanitized_Request

[spankwire] Use sanitized_Request

[sportdeutschland] Use sanitized_Request

[streamcloud] Use sanitized_Request

[streamcz] Use sanitized_Request

[tapely] Use sanitized_Request

[tube8] Use sanitized_Request

[tubitv] Use sanitized_Request

[twitch] Use sanitized_Request

[twitter] Use sanitized_Request

[udemy] Use sanitized_Request

[vbox7] Use sanitized_Request

[veoh] Use sanitized_Request

[vessel] Use sanitized_Request

[vevo] Use sanitized_Request

[viddler] Use sanitized_Request

[videomega] Use sanitized_Request

[viewvster] Use sanitized_Request

[viki] Use sanitized_Request

[vk] Use sanitized_Request

[vodlocker] Use sanitized_Request

[voicerepublic] Use sanitized_Request

[wistia] Use sanitized_Request

[xfileshare] Use sanitized_Request

[xtube] Use sanitized_Request

[xvideos] Use sanitized_Request

[yandexmusic] Use sanitized_Request

[youku] Use sanitized_Request

[youporn] Use sanitized_Request

[youtube] Use sanitized_Request

[patreon] Use sanitized_Request

[extractor/common] Remove unused import

[nfb] PEP 8
2015-11-23 21:56:23 +06:00

72 lines
2.7 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urllib_parse
from ..utils import sanitized_Request
class SinaIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://(.*?\.)?video\.sina\.com\.cn/
(
(.+?/(((?P<pseudo_id>\d+).html)|(.*?(\#|(vid=)|b/)(?P<id>\d+?)($|&|\-))))
|
# This is used by external sites like Weibo
(api/sinawebApi/outplay.php/(?P<token>.+?)\.swf)
)
'''
_TESTS = [
{
'url': 'http://video.sina.com.cn/news/vlist/zt/chczlj2013/?opsubject_id=top12#110028898',
'md5': 'd65dd22ddcf44e38ce2bf58a10c3e71f',
'info_dict': {
'id': '110028898',
'ext': 'flv',
'title': '《中国新闻》 朝鲜要求巴拿马立即释放被扣船员',
}
},
{
'url': 'http://video.sina.com.cn/v/b/101314253-1290078633.html',
'info_dict': {
'id': '101314253',
'ext': 'flv',
'title': '军方提高对朝情报监视级别',
},
},
]
def _extract_video(self, video_id):
data = compat_urllib_parse.urlencode({'vid': video_id})
url_doc = self._download_xml('http://v.iask.com/v_play.php?%s' % data,
video_id, 'Downloading video url')
image_page = self._download_webpage(
'http://interface.video.sina.com.cn/interface/common/getVideoImage.php?%s' % data,
video_id, 'Downloading thumbnail info')
return {'id': video_id,
'url': url_doc.find('./durl/url').text,
'ext': 'flv',
'title': url_doc.find('./vname').text,
'thumbnail': image_page.split('=')[1],
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
if mobj.group('token') is not None:
# The video id is in the redirected url
self.to_screen('Getting video id')
request = sanitized_Request(url)
request.get_method = lambda: 'HEAD'
(_, urlh) = self._download_webpage_handle(request, 'NA', False)
return self._real_extract(urlh.geturl())
elif video_id is None:
pseudo_id = mobj.group('pseudo_id')
webpage = self._download_webpage(url, pseudo_id)
video_id = self._search_regex(r'vid:\'(\d+?)\'', webpage, 'video id')
return self._extract_video(video_id)