]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/fourtube.py
1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
16 class FourTubeIE(InfoExtractor
):
18 _VALID_URL
= r
'https?://(?:www\.)?4tube\.com/videos/(?P<id>\d+)'
21 'url': 'http://www.4tube.com/videos/209733/hot-babe-holly-michaels-gets-her-ass-stuffed-by-black',
22 'md5': '6516c8ac63b03de06bc8eac14362db4f',
26 'title': 'Hot Babe Holly Michaels gets her ass stuffed by black',
27 'uploader': 'WCP Club',
28 'uploader_id': 'wcp-club',
29 'upload_date': '20131031',
30 'timestamp': 1383263892,
39 def _real_extract(self
, url
):
40 video_id
= self
._match
_id
(url
)
41 webpage
= self
._download
_webpage
(url
, video_id
)
43 title
= self
._html
_search
_meta
('name', webpage
)
44 timestamp
= parse_iso8601(self
._html
_search
_meta
(
45 'uploadDate', webpage
))
46 thumbnail
= self
._html
_search
_meta
('thumbnailUrl', webpage
)
47 uploader_id
= self
._html
_search
_regex
(
48 r
'<a class="img-avatar" href="[^"]+/channels/([^/"]+)" title="Go to [^"]+ page">',
49 webpage
, 'uploader id')
50 uploader
= self
._html
_search
_regex
(
51 r
'<a class="img-avatar" href="[^"]+/channels/[^/"]+" title="Go to ([^"]+) page">',
54 categories_html
= self
._search
_regex
(
55 r
'(?s)><i class="icon icon-tag"></i>\s*Categories / Tags\s*.*?<ul class="list">(.*?)</ul>',
56 webpage
, 'categories', fatal
=False)
60 c
.strip() for c
in re
.findall(
61 r
'(?s)<li><a.*?>(.*?)</a>', categories_html
)]
63 view_count
= str_to_int(self
._search
_regex
(
64 r
'<meta itemprop="interactionCount" content="UserPlays:([0-9,]+)">',
65 webpage
, 'view count', fatal
=False))
66 like_count
= str_to_int(self
._search
_regex
(
67 r
'<meta itemprop="interactionCount" content="UserLikes:([0-9,]+)">',
68 webpage
, 'like count', fatal
=False))
69 duration
= parse_duration(self
._html
_search
_meta
('duration', webpage
))
71 params_js
= self
._search
_regex
(
72 r
'\$\.ajax\(url,\ opts\);\s*\}\s*\}\)\(([0-9,\[\] ]+)\)',
73 webpage
, 'initialization parameters'
75 params
= self
._parse
_json
('[%s]' % params_js
, video_id
)
77 sources
= ['%s' % p
for p
in params
[2]]
79 token_url
= 'http://tkn.4tube.com/{0}/desktop/{1}'.format(
80 media_id
, '+'.join(sources
))
82 b
'Content-Type': b
'application/x-www-form-urlencoded',
83 b
'Origin': b
'http://www.4tube.com',
85 token_req
= compat_urllib_request
.Request(token_url
, b
'{}', headers
)
86 tokens
= self
._download
_json
(token_req
, video_id
)
88 'url': tokens
[format
]['token'],
89 'format_id': format
+ 'p',
90 'resolution': format
+ 'p',
91 'quality': int(format
),
92 } for format
in sources
]
93 self
._sort
_formats
(formats
)
99 'categories': categories
,
100 'thumbnail': thumbnail
,
101 'uploader': uploader
,
102 'uploader_id': uploader_id
,
103 'timestamp': timestamp
,
104 'like_count': like_count
,
105 'view_count': view_count
,
106 'duration': duration
,