3 from .common
import InfoExtractor
13 class YouPornIE(InfoExtractor
):
14 _VALID_URL
= r
'https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?'
16 'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
17 'md5': '3744d24c50438cf5b6f6d59feb5055c2',
20 'display_id': 'sex-ed-is-it-safe-to-masturbate-daily',
22 'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
23 'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
24 'thumbnail': r
're:^https?://.*\.jpg$',
26 'uploader': 'Ask Dan And Jennifer',
27 'upload_date': '20101217',
28 'average_rating': int,
34 'skip': 'This video has been disabled',
37 'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
40 'display_id': 'big-tits-awesome-brunette-on-amazing-webcam-show',
42 'title': 'Big Tits Awesome Brunette On amazing webcam show',
43 'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
44 'thumbnail': r
're:^https?://.*\.jpg$',
45 'uploader': 'Unknown',
46 'upload_date': '20110418',
47 'average_rating': int,
54 'skip_download': True,
58 'url': 'https://www.youporn.com/embed/505835/sex-ed-is-it-safe-to-masturbate-daily/',
59 'only_matching': True,
61 'url': 'http://www.youporn.com/watch/505835',
62 'only_matching': True,
64 'url': 'https://www.youporn.com/watch/13922959/femdom-principal/',
65 'only_matching': True,
69 def _extract_urls(webpage
):
71 r
'<iframe[^>]+\bsrc=["\']((?
:https?
:)?
//(?
:www\
.)?youporn\
.com
/embed
/\d
+)',
74 def _real_extract(self, url):
75 mobj = self._match_valid_url(url)
76 video_id = mobj.group('id')
77 display_id = mobj.group('display_id
') or video_id
79 definitions = self._download_json(
80 'https
://www
.youporn
.com
/api
/video
/media_definitions
/%s/' % video_id,
84 for definition in definitions:
85 if not isinstance(definition, dict):
87 video_url = url_or_none(definition.get('videoUrl
'))
92 'filesize
': int_or_none(definition.get('videoSize
')),
94 height = int_or_none(definition.get('quality
'))
95 # Video URL's path looks like this
:
96 # /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
97 # /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
98 # /videos/201703/11/109285532/1080P_4000K_109285532.mp4
99 # We will benefit from it by extracting some metadata
100 mobj
= re
.search(r
'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url
)
103 height
= int(mobj
.group('height'))
104 bitrate
= int(mobj
.group('bitrate'))
106 'format_id': '%dp-%dk' % (height
, bitrate
),
111 self
._sort
_formats
(formats
)
113 webpage
= self
._download
_webpage
(
114 'http://www.youporn.com/watch/%s' % video_id
, display_id
,
115 headers
={'Cookie': 'age_verified=1'}
)
117 title
= self
._html
_search
_regex
(
118 r
'(?s)<div[^>]+class=["\']watchVideoTitle
[^
>]+>(.+?
)</div
>',
119 webpage, 'title
', default=None) or self._og_search_title(
120 webpage, default=None) or self._html_search_meta(
121 'title
', webpage, fatal=True)
123 description = self._html_search_regex(
124 r'(?s
)<div
[^
>]+\bid
=["\']description["\'][^
>]*>(.+?
)</div
>',
125 webpage, 'description
',
126 default=None) or self._og_search_description(
127 webpage, default=None)
128 thumbnail = self._search_regex(
129 r'(?
:imageurl\s
*=|poster\s
*:)\s
*(["\'])(?P<thumbnail>.+?)\1',
130 webpage, 'thumbnail', fatal=False, group='thumbnail')
131 duration = int_or_none(self._html_search_meta(
132 'video:duration', webpage, 'duration', fatal=False))
134 uploader = self._html_search_regex(
135 r'(?s)<div[^>]+class=["\']submitByLink
["\'][^>]*>(.+?)</div>',
136 webpage, 'uploader', fatal=False)
137 upload_date = unified_strdate(self._html_search_regex(
138 (r'UPLOADED:\s*<span>([^<]+)',
139 r'Date\s+[Aa]dded:\s*<span>([^<]+)',
140 r'''(?s)<div[^>]+class=["']videoInfo(?:Date|Time)\b[^>]*>(.+?)</div>''',
141 r'(?s
)<label
\b[^
>]*>Uploaded
[^
<]*</label
>\s
*<span
\b[^
>]*>(.+?
)</span
>'),
142 webpage, 'upload date
', fatal=False))
144 age_limit = self._rta_search(webpage)
147 views = self._search_regex(
148 r'(<div
[^
>]+\bclass
=["\']js_videoInfoViews["\']>)', webpage,
149 'views
', default=None)
151 view_count = str_to_int(extract_attributes(views).get('data
-value
'))
152 comment_count = str_to_int(self._search_regex(
153 r'>All
[Cc
]omments? \
(([\d
,.]+)\
)',
154 webpage, 'comment count
', default=None))
156 def extract_tag_box(regex, title):
157 tag_box = self._search_regex(regex, webpage, title, default=None)
160 return re.findall(r'<a
[^
>]+href
=[^
>]+>([^
<]+)', tag_box)
162 categories = extract_tag_box(
163 r'(?s
)Categories
:.*?
</[^
>]+>(.+?
)</div
>', 'categories
')
164 tags = extract_tag_box(
165 r'(?s
)Tags
:.*?
</div
>\s
*<div
[^
>]+class=["\']tagBoxContent["\'][^
>]*>(.+?
)</div
>',
170 'display_id
': display_id,
172 'description
': description,
173 'thumbnail
': thumbnail,
174 'duration
': duration,
175 'uploader
': uploader,
176 'upload_date
': upload_date,
177 'view_count
': view_count,
178 'comment_count
': comment_count,
179 'categories
': categories,
181 'age_limit
': age_limit,