6 from .common
import InfoExtractor
8 compat_urllib_parse_urlparse
,
19 class YouPornIE(InfoExtractor
):
20 _VALID_URL
= r
'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)'
22 u
'url': u
'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
23 u
'file': u
'505835.mp4',
24 u
'md5': u
'71ec5fcfddacf80f495efa8b6a8d9a89',
26 u
"upload_date": u
"20101221",
27 u
"description": u
"Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?",
28 u
"uploader": u
"Ask Dan And Jennifer",
29 u
"title": u
"Sex Ed: Is It Safe To Masturbate Daily?"
33 def _print_formats(self
, formats
):
34 """Print all available formats"""
35 print(u
'Available formats:')
36 print(u
'ext\t\tformat')
37 print(u
'---------------------------------')
38 for format
in formats
:
39 print(u
'%s\t\t%s' % (format
['ext'], format
['format']))
41 def _specific(self
, req_format
, formats
):
43 if x
["format"] == req_format
:
47 def _real_extract(self
, url
):
48 mobj
= re
.match(self
._VALID
_URL
, url
)
49 video_id
= mobj
.group('videoid')
51 req
= compat_urllib_request
.Request(url
)
52 req
.add_header('Cookie', 'age_verified=1')
53 webpage
= self
._download
_webpage
(req
, video_id
)
54 age_limit
= self
._rta
_search
(webpage
)
57 json_params
= self
._search
_regex
(r
'var currentVideo = new Video\((.*)\);', webpage
, u
'JSON parameters')
59 params
= json
.loads(json_params
)
61 raise ExtractorError(u
'Invalid JSON')
63 self
.report_extraction(video_id
)
65 video_title
= params
['title']
66 upload_date
= unified_strdate(params
['release_date_f'])
67 video_description
= params
['description']
68 video_uploader
= params
['submitted_by']
69 thumbnail
= params
['thumbnails'][0]['image']
71 raise ExtractorError('Missing JSON parameter: ' + sys
.exc_info()[1])
73 # Get all of the formats available
74 DOWNLOAD_LIST_RE
= r
'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
75 download_list_html
= self
._search
_regex
(DOWNLOAD_LIST_RE
,
76 webpage
, u
'download list').strip()
78 # Get all of the links from the page
79 LINK_RE
= r
'(?s)<a href="(?P<url>[^"]+)">'
80 links
= re
.findall(LINK_RE
, download_list_html
)
82 # Get link of hd video if available
83 mobj
= re
.search(r
'var encryptedQuality720URL = \'(?P
<encrypted_video_url
>[a
-zA
-Z0
-9+/]+={0,2}
)\';', webpage)
85 encrypted_video_url = mobj.group(u'encrypted_video_url
')
86 video_url = aes_decrypt_text(encrypted_video_url, video_title, 32).decode('utf
-8')
87 links = [video_url] + links
90 raise ExtractorError(u'ERROR
: no known formats available
for video
')
92 self.to_screen(u'Links found
: %d' % len(links))
97 # A link looks like this:
98 # 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
99 # A path looks like this:
100 # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
101 video_url = unescapeHTML( link )
102 path = compat_urllib_parse_urlparse( video_url ).path
103 extension = os.path.splitext( path )[1][1:]
104 format = path.split('/')[4].split('_
')[:2]
106 # bitrate = format[1]
107 format = "-".join( format )
108 # title = u'%s-%s-%s' % (video_title, size, bitrate)
113 'uploader
': video_uploader,
114 'upload_date
': upload_date,
115 'title
': video_title,
118 'thumbnail
': thumbnail,
119 'description
': video_description,
120 'age_limit
': age_limit,
123 if self._downloader.params.get('listformats
', None):
124 self._print_formats(formats)
127 req_format = self._downloader.params.get('format
', 'best
')
128 self.to_screen(u'Format
: %s' % req_format)
130 if req_format is None or req_format == 'best
':
132 elif req_format == 'worst
':
134 elif req_format in ('-1', 'all
'):
137 format = self._specific( req_format, formats )
139 raise ExtractorError(u'Requested format
not available
')