1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
15 class YouPornIE(InfoExtractor
):
16 _VALID_URL
= r
'https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?'
18 'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
19 'md5': '3744d24c50438cf5b6f6d59feb5055c2',
22 'display_id': 'sex-ed-is-it-safe-to-masturbate-daily',
24 'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
25 'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
26 'thumbnail': r
're:^https?://.*\.jpg$',
28 'uploader': 'Ask Dan And Jennifer',
29 'upload_date': '20101217',
30 'average_rating': int,
36 'skip': 'This video has been disabled',
39 'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
42 'display_id': 'big-tits-awesome-brunette-on-amazing-webcam-show',
44 'title': 'Big Tits Awesome Brunette On amazing webcam show',
45 'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
46 'thumbnail': r
're:^https?://.*\.jpg$',
47 'uploader': 'Unknown',
48 'upload_date': '20110418',
49 'average_rating': int,
56 'skip_download': True,
60 'url': 'https://www.youporn.com/embed/505835/sex-ed-is-it-safe-to-masturbate-daily/',
61 'only_matching': True,
63 'url': 'http://www.youporn.com/watch/505835',
64 'only_matching': True,
66 'url': 'https://www.youporn.com/watch/13922959/femdom-principal/',
67 'only_matching': True,
71 def _extract_urls(webpage
):
73 r
'<iframe[^>]+\bsrc=["\']((?
:https?
:)?
//(?
:www\
.)?youporn\
.com
/embed
/\d
+)',
76 def _real_extract(self, url):
77 mobj = self._match_valid_url(url)
78 video_id = mobj.group('id')
79 display_id = mobj.group('display_id
') or video_id
81 definitions = self._download_json(
82 'https
://www
.youporn
.com
/api
/video
/media_definitions
/%s/' % video_id,
86 for definition in definitions:
87 if not isinstance(definition, dict):
89 video_url = url_or_none(definition.get('videoUrl
'))
94 'filesize
': int_or_none(definition.get('videoSize
')),
96 height = int_or_none(definition.get('quality
'))
97 # Video URL's path looks like this
:
98 # /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
99 # /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
100 # /videos/201703/11/109285532/1080P_4000K_109285532.mp4
101 # We will benefit from it by extracting some metadata
102 mobj
= re
.search(r
'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url
)
105 height
= int(mobj
.group('height'))
106 bitrate
= int(mobj
.group('bitrate'))
108 'format_id': '%dp-%dk' % (height
, bitrate
),
113 self
._sort
_formats
(formats
)
115 webpage
= self
._download
_webpage
(
116 'http://www.youporn.com/watch/%s' % video_id
, display_id
,
117 headers
={'Cookie': 'age_verified=1'}
)
119 title
= self
._html
_search
_regex
(
120 r
'(?s)<div[^>]+class=["\']watchVideoTitle
[^
>]+>(.+?
)</div
>',
121 webpage, 'title
', default=None) or self._og_search_title(
122 webpage, default=None) or self._html_search_meta(
123 'title
', webpage, fatal=True)
125 description = self._html_search_regex(
126 r'(?s
)<div
[^
>]+\bid
=["\']description["\'][^
>]*>(.+?
)</div
>',
127 webpage, 'description
',
128 default=None) or self._og_search_description(
129 webpage, default=None)
130 thumbnail = self._search_regex(
131 r'(?
:imageurl\s
*=|poster\s
*:)\s
*(["\'])(?P<thumbnail>.+?)\1',
132 webpage, 'thumbnail', fatal=False, group='thumbnail')
133 duration = int_or_none(self._html_search_meta(
134 'video:duration', webpage, 'duration', fatal=False))
136 uploader = self._html_search_regex(
137 r'(?s)<div[^>]+class=["\']submitByLink
["\'][^>]*>(.+?)</div>',
138 webpage, 'uploader', fatal=False)
139 upload_date = unified_strdate(self._html_search_regex(
140 [r'UPLOADED:\s*<span>([^<]+)',
141 r'Date\s+[Aa]dded:\s*<span>([^<]+)',
142 r'(?s)<div[^>]+class=["\']videoInfo(?
:Date|Time
)["\'][^>]*>(.+?)</div>'],
143 webpage, 'upload date', fatal=False))
145 age_limit = self._rta_search(webpage)
148 views = self._search_regex(
149 r'(<div[^>]+\bclass=["\']js_videoInfoViews
["\']>)', webpage,
150 'views', default=None)
152 view_count = str_to_int(extract_attributes(views).get('data-value'))
153 comment_count = str_to_int(self._search_regex(
154 r'>All [Cc]omments? \(([\d,.]+)\)',
155 webpage, 'comment count', default=None))
157 def extract_tag_box(regex, title):
158 tag_box = self._search_regex(regex, webpage, title, default=None)
161 return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box)
163 categories = extract_tag_box(
164 r'(?s)Categories:.*?</[^>]+>(.+?)</div>', 'categories')
165 tags = extract_tag_box(
166 r'(?s)Tags:.*?</div>\s*<div[^>]+class=["\']tagBoxContent
["\'][^>]*>(.+?)</div>',
171 'display_id': display_id,
173 'description': description,
174 'thumbnail': thumbnail,
175 'duration': duration,
176 'uploader': uploader,
177 'upload_date': upload_date,
178 'view_count': view_count,
179 'comment_count': comment_count,
180 'categories': categories,
182 'age_limit': age_limit,