X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fsohu.py;h=daf6ad555be2a84dc89ec8dfcabcdfde78cf0194;hb=3047121c639428235191ff5f7afbda7ecda38779;hp=ef7ec51df4c857ca5cb4628c850b9f6f227d4587;hpb=5ee6fc974e617ce2f8d9d62c416091a1daa6d802;p=youtube-dl diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index ef7ec51df..daf6ad555 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -4,8 +4,14 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import compat_str -from ..compat import compat_urllib_request +from ..compat import ( + compat_str, + compat_urllib_parse, +) +from ..utils import ( + ExtractorError, + sanitized_Request, +) class SohuIE(InfoExtractor): @@ -20,9 +26,7 @@ class SohuIE(InfoExtractor): 'ext': 'mp4', 'title': 'MVï¼Far East MovementãThe Illestã', }, - 'params': { - 'cn_verification_proxy': 'proxy.uku.im:8888' - } + 'skip': 'On available in China', }, { 'url': 'http://tv.sohu.com/20150305/n409385080.shtml', 'md5': '699060e75cf58858dd47fb9c03c42cfb', @@ -39,6 +43,49 @@ class SohuIE(InfoExtractor): 'ext': 'mp4', 'title': 'ãç±èåã第31æï¼MWCè§ä¸å°çå¥è©ææº', } + }, { + 'note': 'Multipart video', + 'url': 'http://my.tv.sohu.com/pl/8384802/78910339.shtml', + 'info_dict': { + 'id': '78910339', + 'title': 'ãç¥æ¢èå®æç§ç±ã第13æ æäºä¹å½± 赫å¡éå§', + }, + 'playlist': [{ + 'md5': 'bdbfb8f39924725e6589c146bc1883ad', + 'info_dict': { + 'id': '78910339_part1', + 'ext': 'mp4', + 'duration': 294, + 'title': 'ãç¥æ¢èå®æç§ç±ã第13æ æäºä¹å½± 赫å¡éå§', + } + }, { + 'md5': '3e1f46aaeb95354fd10e7fca9fc1804e', + 'info_dict': { + 'id': '78910339_part2', + 'ext': 'mp4', + 'duration': 300, + 'title': 'ãç¥æ¢èå®æç§ç±ã第13æ æäºä¹å½± 赫å¡éå§', + } + }, { + 'md5': '8407e634175fdac706766481b9443450', + 'info_dict': { + 'id': '78910339_part3', + 'ext': 'mp4', + 'duration': 150, + 'title': 'ãç¥æ¢èå®æç§ç±ã第13æ æäºä¹å½± 赫å¡éå§', + } + }] + }, { + 'note': 'Video with title containing dash', + 'url': 'http://my.tv.sohu.com/us/249884221/78932792.shtml', + 'info_dict': { + 'id': '78932792', + 'ext': 'mp4', + 'title': 'youtube-dl testing video', + }, + 'params': { + 'skip_download': True + } }] def _real_extract(self, url): @@ -49,29 +96,37 @@ class SohuIE(InfoExtractor): else: base_data_url = 'http://hot.vrs.sohu.com/vrs_flash.action?vid=' - req = compat_urllib_request.Request(base_data_url + vid_id) + req = sanitized_Request(base_data_url + vid_id) cn_verification_proxy = self._downloader.params.get('cn_verification_proxy') if cn_verification_proxy: req.add_header('Ytdl-request-proxy', cn_verification_proxy) - return self._download_json(req, video_id, - 'Downloading JSON data for %s' % vid_id) + return self._download_json( + req, video_id, + 'Downloading JSON data for %s' % vid_id) mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') mytv = mobj.group('mytv') is not None webpage = self._download_webpage(url, video_id) - raw_title = self._html_search_regex( - r'(?s)