X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fsohu.py;h=f8a4840f7b210d0092154a0910188a22efd9bf8b;hb=0954cd8aa4421b1844a30e99702c364f1fffc15f;hp=335e84fab7b990019aaf1063fd2fd6ea721bb465;hpb=5c7495a19429e3b27c003a4bd5bb96ed1e3a4932;p=youtube-dl diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index 335e84fab..f8a4840f7 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -8,6 +8,7 @@ from ..compat import ( compat_str, compat_urllib_request ) +from ..utils import sanitize_url_path_consecutive_slashes class SohuIE(InfoExtractor): @@ -41,6 +42,49 @@ class SohuIE(InfoExtractor): 'ext': 'mp4', 'title': '【爱范品】第31期:MWC见不到的奇葩手机', } + }, { + 'note': 'Multipart video', + 'url': 'http://my.tv.sohu.com/pl/8384802/78910339.shtml', + 'info_dict': { + 'id': '78910339', + 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', + }, + 'playlist': [{ + 'md5': 'bdbfb8f39924725e6589c146bc1883ad', + 'info_dict': { + 'id': '78910339_part1', + 'ext': 'mp4', + 'duration': 294, + 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', + } + }, { + 'md5': '3e1f46aaeb95354fd10e7fca9fc1804e', + 'info_dict': { + 'id': '78910339_part2', + 'ext': 'mp4', + 'duration': 300, + 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', + } + }, { + 'md5': '8407e634175fdac706766481b9443450', + 'info_dict': { + 'id': '78910339_part3', + 'ext': 'mp4', + 'duration': 150, + 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', + } + }] + }, { + '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): @@ -57,18 +101,17 @@ 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)(.+?)', - webpage, 'video title') - title = raw_title.partition('-')[0].strip() + + title = re.sub(r' - 搜狐视频$', '', self._og_search_title(webpage)) vid = self._html_search_regex( r'var vid ?= ?["\'](\d+)["\']', @@ -105,11 +148,8 @@ class SohuIE(InfoExtractor): part_info = part_str.split('|') - # Sanitize URL to prevent download failure - if part_info[0][-1] == '/' and su[i][0] == '/': - su[i] = su[i][1:] - - video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3]) + video_url = sanitize_url_path_consecutive_slashes( + '%s%s?key=%s' % (part_info[0], su[i], part_info[3])) formats.append({ 'url': video_url, @@ -133,9 +173,10 @@ class SohuIE(InfoExtractor): info['id'] = video_id else: info = { - '_type': 'playlist', + '_type': 'multi_video', 'entries': playlist, 'id': video_id, + 'title': title, } return info