youtube-dl/youtube_dl/extractor/xvideos.py

54 lines
1.5 KiB
Python
Raw Normal View History

2014-01-23 03:02:48 +09:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
)
class XVideosIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
2013-06-28 03:46:46 +09:00
_TEST = {
2014-01-23 03:02:48 +09:00
'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,
2013-06-28 03:46:46 +09:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1)
webpage = self._download_webpage(url, video_id)
self.report_extraction(video_id)
# Extract video URL
2014-01-23 03:02:48 +09:00
video_url = compat_urllib_parse.unquote(
self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL'))
# Extract title
2014-01-23 03:02:48 +09:00
video_title = self._html_search_regex(
r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
# Extract video thumbnail
2014-01-23 03:02:48 +09:00
video_thumbnail = self._search_regex(
r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
2014-01-23 03:02:48 +09:00
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,
}