X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fsina.py;h=b2258a0f64c9f985edb5354ae5c11a381ebcc8af;hb=5c2266df4b9aeb7881ed8c026a038e2a25e43734;hp=7548696a779ef5b6f12223accfbc6bafa84cc395;hpb=76f270a46a47c7df2d75ca8da437c12c729fc380;p=youtube-dl diff --git a/youtube_dl/extractor/sina.py b/youtube_dl/extractor/sina.py index 7548696a7..b2258a0f6 100644 --- a/youtube_dl/extractor/sina.py +++ b/youtube_dl/extractor/sina.py @@ -4,39 +4,44 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - compat_urllib_request, - compat_urllib_parse, -) +from ..compat import compat_urllib_parse +from ..utils import sanitized_Request class SinaIE(InfoExtractor): - _VALID_URL = r'''https?://(.*?\.)?video\.sina\.com\.cn/ + _VALID_URL = r'''(?x)https?://(.*?\.)?video\.sina\.com\.cn/ ( - (.+?/(((?P\d+).html)|(.*?(\#|(vid=))(?P\d+?)($|&)))) + (.+?/(((?P\d+).html)|(.*?(\#|(vid=)|b/)(?P\d+?)($|&|\-)))) | # This is used by external sites like Weibo (api/sinawebApi/outplay.php/(?P.+?)\.swf) ) ''' - _TEST = { - 'url': 'http://video.sina.com.cn/news/vlist/zt/chczlj2013/?opsubject_id=top12#110028898', - 'file': '110028898.flv', - 'md5': 'd65dd22ddcf44e38ce2bf58a10c3e71f', - 'info_dict': { - 'title': '《中国新闻》 朝鲜要求巴拿马立即释放被扣船员', - } - } - - @classmethod - def suitable(cls, url): - return re.match(cls._VALID_URL, url, flags=re.VERBOSE) is not None + _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') + 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') @@ -49,12 +54,12 @@ class SinaIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE) + 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 = compat_urllib_request.Request(url) + request = sanitized_Request(url) request.get_method = lambda: 'HEAD' (_, urlh) = self._download_webpage_handle(request, 'NA', False) return self._real_extract(urlh.geturl())