1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
6 from ..compat
import compat_urllib_parse_unquote
16 class XVideosIE(InfoExtractor
):
20 (?:www\.)?xvideos\.com/video|
21 flashservice\.xvideos\.com/embedframe/|
22 static-hw\.xvideos\.com/swf/xv-player\.swf\?.*?\bid_video=
27 'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
28 'md5': '14cea69fcb84db54293b1e971466c2e1',
32 'title': 'Biker Takes his Girl',
37 'url': 'https://flashservice.xvideos.com/embedframe/4588838',
38 'only_matching': True,
40 'url': 'http://static-hw.xvideos.com/swf/xv-player.swf?id_video=4588838',
41 'only_matching': True,
44 def _real_extract(self
, url
):
45 video_id
= self
._match
_id
(url
)
47 webpage
= self
._download
_webpage
(
48 'https://www.xvideos.com/video%s/' % video_id
, video_id
)
50 mobj
= re
.search(r
'<h1 class="inlineError">(.+?)</h1>', webpage
)
52 raise ExtractorError('%s said: %s' % (self
.IE_NAME
, clean_html(mobj
.group(1))), expected
=True)
54 title
= self
._html
_search
_regex
(
55 (r
'<title>(?P<title>.+?)\s+-\s+XVID',
56 r
'setVideoTitle\s*\(\s*(["\'])(?P
<title
>(?
:(?
!\
1).)+)\
1'),
57 webpage, 'title
', default=None,
58 group='title
') or self._og_search_title(webpage)
61 for preference, thumbnail in enumerate(('', '169')):
62 thumbnail_url = self._search_regex(
63 r'setThumbUrl
%s\
(\s
*(["\'])(?P<thumbnail>(?:(?!\1).)+)\1' % thumbnail,
64 webpage, 'thumbnail', default=None, group='thumbnail')
68 'preference': preference,
71 duration = int_or_none(self._og_search_property(
72 'duration', webpage, default=None)) or parse_duration(
74 r'<span[^>]+class=["\']duration
["\'][^>]*>.*?(\d[^<]+)',
75 webpage, 'duration', fatal=False))
79 video_url = compat_urllib_parse_unquote(self._search_regex(
80 r'flv_url=(.+?)&', webpage, 'video URL', default=''))
87 for kind, _, format_url in re.findall(
88 r'setVideo([^(]+)\((["\'])(http
.+?
)\
2\
)', webpage):
89 format_id = kind.lower()
90 if format_id == 'hls
':
91 formats.extend(self._extract_m3u8_formats(
92 format_url, video_id, 'mp4
',
93 entry_protocol='m3u8_native
', m3u8_id='hls
', fatal=False))
94 elif format_id in ('urllow
', 'urlhigh
'):
97 'format_id
': '%s-%s' % (determine_ext(format_url, 'mp4
'), format_id[3:]),
98 'quality
': -2 if format_id.endswith('low
') else None,
101 self._sort_formats(formats)
107 'duration
': duration,
108 'thumbnails
': thumbnails,