From 0932300e3a7d609f203bdfad4bcadaf1fafee67c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Thu, 18 Jul 2013 15:31:50 +0200 Subject: [PATCH] Add SinaIE (related #1039): extractor for video.sina.com.cn --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/sina.py | 67 ++++++++++++++++++++++++++++++++ 2 files changed, 68 insertions(+) create mode 100644 youtube_dl/extractor/sina.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 79868aa06..4c1c9a01e 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -51,6 +51,7 @@ from .rbmaradio import RBMARadioIE from .redtube import RedTubeIE from .ringtv import RingTVIE +from .sina import SinaIE from .soundcloud import SoundcloudIE, SoundcloudSetIE from .spiegel import SpiegelIE from .stanfordoc import StanfordOpenClassroomIE diff --git a/youtube_dl/extractor/sina.py b/youtube_dl/extractor/sina.py new file mode 100644 index 000000000..14b1c656c --- /dev/null +++ b/youtube_dl/extractor/sina.py @@ -0,0 +1,67 @@ +# coding: utf-8 + +import re +import xml.etree.ElementTree + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_request, + compat_urllib_parse, +) + + +class SinaIE(InfoExtractor): + _VALID_URL = r'''https?://(.*?\.)?video\.sina\.com\.cn/ + ( + (.+?/(((?P\d+).html)|(.*?(\#|(vid=))(?P\d+?)($|&)))) + | + # This is used by external sites like Weibo + (api/sinawebApi/outplay.php/(?P.+?)\.swf) + ) + ''' + + _TEST = { + u'url': u'http://video.sina.com.cn/news/vlist/zt/chczlj2013/?opsubject_id=top12#110028898', + u'file': u'110028898.flv', + u'md5': u'd65dd22ddcf44e38ce2bf58a10c3e71f', + u'info_dict': { + u'title': u'《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 + + def _extract_video(self, video_id): + data = compat_urllib_parse.urlencode({'vid': video_id}) + url_page = self._download_webpage('http://v.iask.com/v_play.php?%s' % data, + video_id, u'Downloading video url') + image_page = self._download_webpage( + 'http://interface.video.sina.com.cn/interface/common/getVideoImage.php?%s' % data, + video_id, u'Downloading thumbnail info') + url_doc = xml.etree.ElementTree.fromstring(url_page.encode('utf-8')) + + 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, flags=re.VERBOSE) + video_id = mobj.group('id') + if mobj.group('token') is not None: + # The video id is in the redirected url + self.to_screen(u'Getting video id') + request = compat_urllib_request.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, u'video id') + + return self._extract_video(video_id)