aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/xvideos.py
blob: 4ee538b5038a08b778b3b03984a74770f299e1b6 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
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]+)(?:.*)'
    _TEST = {
        u'url': u'http://www.xvideos.com/video939581/funny_porns_by_s_-1',
        u'file': u'939581.flv',
        u'md5': u'1d0c835822f0a71a7bf011855db929d0',
        u'info_dict': {
            u"title": u"Funny Porns By >>>>S<<<<<< -1",
            u"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)

        # Extract video URL
        video_url = compat_urllib_parse.unquote(self._search_regex(r'flv_url=(.+?)&',
            webpage, u'video URL'))

        # Extract title
        video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XVID',
            webpage, u'title')

        # Extract video thumbnail
        video_thumbnail = self._search_regex(r'url_bigthumb=(.+?)&amp',
             webpage, u'thumbnail', fatal=False)

        info = {
            'id': video_id,
            'url': video_url,
            'uploader': None,
            'upload_date': None,
            'title': video_title,
            'ext': 'flv',
            'thumbnail': video_thumbnail,
            'description': None,
            'age_limit': 18,
        }

        return [info]