X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fxvideos.py;h=7e00448246beb9ab9b7c25f33b05e6f4f1bb8283;hb=199ece7eb83ffe7ba069b50080fe971df1db2d6c;hp=90138d7e523a405c20bae8352c6233b5868860f5;hpb=8ed6b34477367ff2900a0e8b3628056188598fe8;p=youtube-dl diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py index 90138d7e5..7e0044824 100644 --- a/youtube_dl/extractor/xvideos.py +++ b/youtube_dl/extractor/xvideos.py @@ -1,20 +1,25 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor from ..utils import ( compat_urllib_parse, + ExtractorError, + clean_html, ) class XVideosIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' _TEST = { - u'url': u'http://www.xvideos.com/video939581/funny_porns_by_s_-1', - u'file': u'939581.flv', - u'md5': u'1d0c835822f0a71a7bf011855db929d0', - u'info_dict': { - u"title": u"Funny Porns By >>>>S<<<<<< -1", - u"age_limit": 18, + 'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl', + 'md5': '4b46ae6ea5e6e9086e714d883313c0c9', + 'info_dict': { + 'id': '4588838', + 'ext': 'flv', + 'title': 'Biker Takes his Girl', + 'age_limit': 18, } } @@ -26,19 +31,23 @@ class XVideosIE(InfoExtractor): self.report_extraction(video_id) + mobj = re.search(r'

(.+?)

', webpage) + if mobj: + raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True) + # Extract video URL - video_url = compat_urllib_parse.unquote(self._search_regex(r'flv_url=(.+?)&', - webpage, u'video URL')) + video_url = compat_urllib_parse.unquote( + self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL')) # Extract title - video_title = self._html_search_regex(r'(.*?)\s+-\s+XVID', - webpage, u'title') + video_title = self._html_search_regex( + r'<title>(.*?)\s+-\s+XVID', webpage, 'title') # Extract video thumbnail - video_thumbnail = self._search_regex(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)', - webpage, u'thumbnail', fatal=False) + video_thumbnail = self._search_regex( + r'url_bigthumb=(.+?)&', webpage, 'thumbnail', fatal=False) - info = { + return { 'id': video_id, 'url': video_url, 'uploader': None, @@ -49,5 +58,3 @@ class XVideosIE(InfoExtractor): 'description': None, 'age_limit': 18, } - - return [info]