You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
59 lines
1.7 KiB
59 lines
1.7 KiB
from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..utils import (
|
|
compat_urllib_parse,
|
|
ExtractorError,
|
|
clean_html,
|
|
)
|
|
|
|
|
|
class XVideosIE(InfoExtractor):
|
|
_VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
|
|
_TEST = {
|
|
'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,
|
|
}
|
|
}
|
|
|
|
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)
|
|
|
|
mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage)
|
|
if mobj:
|
|
raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
|
|
|
|
# Extract video URL
|
|
video_url = compat_urllib_parse.unquote(
|
|
self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL'))
|
|
|
|
# Extract title
|
|
video_title = self._html_search_regex(
|
|
r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
|
|
|
|
# Extract video thumbnail
|
|
video_thumbnail = self._search_regex(
|
|
r'url_bigthumb=(.+?)&', webpage, 'thumbnail', fatal=False)
|
|
|
|
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,
|
|
}
|