X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9815bb0a551468e4939cacfffbc2d5cb8dd12431..848723ea972c09f28787db91d8c06e98a274ab89:/youtube_dl/extractor/xvideos.py diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py index 8b3cb39..85e99e1 100644 --- a/youtube_dl/extractor/xvideos.py +++ b/youtube_dl/extractor/xvideos.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -8,6 +10,15 @@ from ..utils import ( class XVideosIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' + _TEST = { + 'url': 'http://www.xvideos.com/video939581/funny_porns_by_s_-1', + 'file': '939581.flv', + 'md5': '1d0c835822f0a71a7bf011855db929d0', + 'info_dict': { + "title": "Funny Porns By >>>>S<<<<<< -1", + "age_limit": 18, + } + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -18,18 +29,18 @@ class XVideosIE(InfoExtractor): self.report_extraction(video_id) # 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, @@ -38,6 +49,5 @@ class XVideosIE(InfoExtractor): 'ext': 'flv', 'thumbnail': video_thumbnail, 'description': None, + 'age_limit': 18, } - - return [info]