1 from __future__
import unicode_literals
8 from .common
import InfoExtractor
10 compat_urllib_parse_urlparse
,
11 compat_urllib_request
,
23 class YouPornIE(InfoExtractor
):
24 _VALID_URL
= r
'^(?P<proto>https?://)(?:www\.)?(?P<url>youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+))'
26 'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
30 'upload_date': '20101221',
31 'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
32 'uploader': 'Ask Dan And Jennifer',
33 'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
38 def _real_extract(self
, url
):
39 mobj
= re
.match(self
._VALID
_URL
, url
)
40 video_id
= mobj
.group('videoid')
41 url
= mobj
.group('proto') + 'www.' + mobj
.group('url')
43 req
= compat_urllib_request
.Request(url
)
44 req
.add_header('Cookie', 'age_verified=1')
45 webpage
= self
._download
_webpage
(req
, video_id
)
46 age_limit
= self
._rta
_search
(webpage
)
49 json_params
= self
._search
_regex
(
50 r
'var currentVideo = new Video\((.*)\)[,;]',
51 webpage
, 'JSON parameters')
53 params
= json
.loads(json_params
)
55 raise ExtractorError('Invalid JSON')
57 self
.report_extraction(video_id
)
59 video_title
= params
['title']
60 upload_date
= unified_strdate(params
['release_date_f'])
61 video_description
= params
['description']
62 video_uploader
= params
['submitted_by']
63 thumbnail
= params
['thumbnails'][0]['image']
65 raise ExtractorError('Missing JSON parameter: ' + sys
.exc_info()[1])
67 # Get all of the links from the page
68 DOWNLOAD_LIST_RE
= r
'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
69 download_list_html
= self
._search
_regex
(DOWNLOAD_LIST_RE
,
70 webpage
, 'download list').strip()
71 LINK_RE
= r
'<a href="([^"]+)">'
72 links
= re
.findall(LINK_RE
, download_list_html
)
74 # Get all encrypted links
75 encrypted_links
= re
.findall(r
'var encryptedQuality[0-9]{3}URL = \'([a
-zA
-Z0
-9+/]+={0,2}
)\';', webpage)
76 for encrypted_link in encrypted_links:
77 link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf
-8')
82 # A link looks like this:
83 # http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0
84 # A path looks like this:
85 # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
86 video_url = unescapeHTML(link)
87 path = compat_urllib_parse_urlparse(video_url).path
88 format_parts = path.split('/')[4].split('_
')[:2]
90 dn = compat_urllib_parse_urlparse(video_url).netloc.partition('.')[0]
92 resolution = format_parts[0]
93 height = int(resolution[:-len('p
')])
94 bitrate = int(format_parts[1][:-len('k
')])
95 format = '-'.join(format_parts) + '-' + dn
103 'resolution
': resolution,
106 self._sort_formats(formats)
109 raise ExtractorError('ERROR
: no known formats available
for video
')
113 'uploader
': video_uploader,
114 'upload_date
': upload_date,
115 'title
': video_title,
116 'thumbnail
': thumbnail,
117 'description
': video_description,
118 'age_limit
': age_limit,