w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[xnxx] Modernize

Browse source
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-03-09 17:22:53 +01:00
parent 9e55e37a2e
commit bdebf51c8f
1 changed files with 20 additions and 26 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

46
youtube_dl/extractor/xnxx.py
View file

@ -1,55 +1,49 @@
# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
ExtractorError,
)
class XNXXIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:video|www)\.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=(.*?)&amp;'
_VALID_URL = r'^https?://(?:video|www)\.xnxx\.com/video(?P<id>[0-9]+)/(.*)'
_TEST = {
u'url': u'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
u'file': u'1135332.flv',
u'md5': u'0831677e2b4761795f68d417e0b7b445',
u'info_dict': {
u"title": u"lida \u00bb Naked Funny Actress (5)",
u"age_limit": 18,
'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)
video_id = mobj.group('id')
# Get webpage content
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=(.*?)&amp;',
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=(.*?)&amp;',
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,
}]
}