1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-11-27 09:52:53 +08:00
youtube-dl/youtube_dl/extractor/xnxx.py
Philipp Hagemeister 1cc79574fc Fix imports and general cleanup
· Import from compat what comes from compat. Yes, some names are available in utils too, but that's an implementation detail.
· Use _match_id consistently whenever possible
· Fix some outdated tests
· Use consistent valid URL (always match the whole protocol, no ^ at start required)
· Use modern test definitions
2014-12-13 12:35:45 +01:00

45 lines
1.4 KiB
Python

# encoding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
)
class XNXXIE(InfoExtractor):
_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):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
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(r'<title>(.*?)\s+-\s+XNXX.COM',
webpage, 'title')
video_thumbnail = self._search_regex(r'url_bigthumb=(.*?)&amp;',
webpage, 'thumbnail', fatal=False)
return {
'id': video_id,
'url': video_url,
'title': video_title,
'ext': 'flv',
'thumbnail': video_thumbnail,
'age_limit': 18,
}