X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9815bb0a551468e4939cacfffbc2d5cb8dd12431..77f319061b1661d04f5f4674aac40c72b824d665:/youtube_dl/extractor/xnxx.py diff --git a/youtube_dl/extractor/xnxx.py b/youtube_dl/extractor/xnxx.py index 68acb84..bcb1403 100644 --- a/youtube_dl/extractor/xnxx.py +++ b/youtube_dl/extractor/xnxx.py @@ -1,45 +1,48 @@ -import re +# encoding: utf-8 +from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import ( - compat_urllib_parse, - - ExtractorError, -) +from ..compat import compat_urllib_parse_unquote class XNXXIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)' - VIDEO_URL_RE = r'flv_url=(.*?)&' - VIDEO_TITLE_RE = r'(.*?)\s+-\s+XNXX.COM' - VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&' + _VALID_URL = r'https?://(?:video|www)\.xnxx\.com/video-?(?P<id>[0-9a-z]+)/' + _TESTS = [{ + 'url': 'http://www.xnxx.com/video-55awb78/skyrim_test_video', + 'md5': 'ef7ecee5af78f8b03dca2cf31341d3a0', + 'info_dict': { + 'id': '55awb78', + 'ext': 'flv', + 'title': 'Skyrim Test Video', + 'age_limit': 18, + }, + }, { + 'url': 'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_', + 'only_matching': True, + }, { + 'url': 'http://www.xnxx.com/video-55awb78/', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - video_id = mobj.group(1) - - # Get webpage content + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - video_url = self._search_regex(self.VIDEO_URL_RE, - webpage, u'video URL') - video_url = compat_urllib_parse.unquote(video_url) + video_url = self._search_regex(r'flv_url=(.*?)&', + webpage, 'video URL') + video_url = compat_urllib_parse_unquote(video_url) - video_title = self._html_search_regex(self.VIDEO_TITLE_RE, - webpage, u'title') + video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XNXX.COM', + webpage, 'title') - video_thumbnail = self._search_regex(self.VIDEO_THUMB_RE, - webpage, u'thumbnail', fatal=False) + video_thumbnail = self._search_regex(r'url_bigthumb=(.*?)&', + webpage, 'thumbnail', fatal=False) - return [{ + return { 'id': video_id, 'url': video_url, - 'uploader': None, - 'upload_date': None, 'title': video_title, 'ext': 'flv', 'thumbnail': video_thumbnail, - 'description': None, - }] + 'age_limit': 18, + }