-import re
+# encoding: utf-8
+from __future__ import unicode_literals
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
-
- ExtractorError,
)
class XNXXIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)'
- VIDEO_URL_RE = r'flv_url=(.*?)&'
- VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
- VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&'
+ _VALID_URL = r'^https?://(?:video|www)\.xnxx\.com/video(?P<id>[0-9]+)/(.*)'
+ _TEST = {
+ 'url': 'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
+ 'md5': '0831677e2b4761795f68d417e0b7b445',
+ 'info_dict': {
+ 'id': '1135332',
+ 'ext': 'flv',
+ 'title': 'lida » Naked Funny Actress (5)',
+ 'age_limit': 18,
+ }
+ }
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 = 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,
+ }