X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fsohu.py;h=29bd9ce6f76247b5ac997050075c7e720d8a3b2b;hb=15b74b94beb8720a4f6d7ee076c123dd8ae05309;hp=7db5b2f13367749aebef75e0785bc842bdba19fd;hpb=cd65491c306f644d7bb3c7ad98795a3f8660be49;p=youtube-dl.git diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index 7db5b2f13..29bd9ce6f 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -8,7 +8,7 @@ from ..compat import ( compat_str, compat_urllib_request ) -from ..utils import url_sanitize_consecutive_slashes +from ..utils import ExtractorError class SohuIE(InfoExtractor): @@ -23,12 +23,10 @@ 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', + 'md5': 'ac9a5d322b4bf9ae184d53e4711e4f1a', 'info_dict': { 'id': '409385080', 'ext': 'mp4', @@ -36,7 +34,7 @@ class SohuIE(InfoExtractor): } }, { 'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml', - 'md5': '9bf34be48f2f4dadcb226c74127e203c', + 'md5': '49308ff6dafde5ece51137d04aec311e', 'info_dict': { 'id': '78693464', 'ext': 'mp4', @@ -47,9 +45,10 @@ class SohuIE(InfoExtractor): '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', + 'md5': '492923eac023ba2f13ff69617c32754a', 'info_dict': { 'id': '78910339_part1', 'ext': 'mp4', @@ -57,7 +56,7 @@ class SohuIE(InfoExtractor): 'title': 'ãç¥æ¢èå®æç§ç±ã第13æ æäºä¹å½± 赫å¡éå§', } }, { - 'md5': '3e1f46aaeb95354fd10e7fca9fc1804e', + 'md5': 'de604848c0e8e9c4a4dde7e1347c0637', 'info_dict': { 'id': '78910339_part2', 'ext': 'mp4', @@ -65,7 +64,7 @@ class SohuIE(InfoExtractor): 'title': 'ãç¥æ¢èå®æç§ç±ã第13æ æäºä¹å½± 赫å¡éå§', } }, { - 'md5': '8407e634175fdac706766481b9443450', + 'md5': '93584716ee0657c0b205b8aa3d27aa13', 'info_dict': { 'id': '78910339_part3', 'ext': 'mp4', @@ -73,6 +72,17 @@ class SohuIE(InfoExtractor): '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): @@ -89,23 +99,31 @@ class SohuIE(InfoExtractor): 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)