1 from __future__ import unicode_literals
5 from .common import InfoExtractor
13 from ..aes import aes_decrypt_text
16 class YouPornIE(InfoExtractor):
17 _VALID_URL = r'https?://(?:www\.)?youporn\.com/watch/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
19 'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
20 'md5': '3744d24c50438cf5b6f6d59feb5055c2',
23 'display_id': 'sex-ed-is-it-safe-to-masturbate-daily',
25 'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
26 'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
27 'thumbnail': r're:^https?://.*\.jpg$',
28 'uploader': 'Ask Dan And Jennifer',
29 'upload_date': '20101221',
30 'average_rating': int,
39 'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
42 'display_id': 'big-tits-awesome-brunette-on-amazing-webcam-show',
44 'title': 'Big Tits Awesome Brunette On amazing webcam show',
45 'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
46 'thumbnail': r're:^https?://.*\.jpg$',
47 'uploader': 'Unknown',
48 'upload_date': '20111125',
49 'average_rating': int,
57 'skip_download': True,
61 def _real_extract(self, url):
62 mobj = re.match(self._VALID_URL, url)
63 video_id = mobj.group('id')
64 display_id = mobj.group('display_id')
66 request = sanitized_Request(url)
67 request.add_header('Cookie', 'age_verified=1')
68 webpage = self._download_webpage(request, display_id)
70 title = self._search_regex(
71 [r'(?:video_titles|videoTitle|title)\s*[:=]\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
72 r'<h1[^>]+class=["\']heading\d?["\'][^>]*>(?P<title>[^<]+)<'],
73 webpage, 'title', group='title',
74 default=None) or self._og_search_title(
75 webpage, default=None) or self._html_search_meta(
76 'title', webpage, fatal=True)
80 sources = self._search_regex(
81 r'(?s)sources\s*:\s*({.+?})', webpage, 'sources', default=None)
83 for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources):
87 for _, link in re.findall(
88 r'(?:videoUrl|videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage):
91 # Fallback #2, this also contains extra low quality 180p format
92 for _, link in re.findall(r'<a[^>]+href=(["\'])(http.+?)\1[^>]+title=["\']Download [Vv]ideo', webpage):
95 # Fallback #3, encrypted links
96 for _, encrypted_link in re.findall(
97 r'encryptedQuality\d{3,4}URL\s*=\s*(["\'])([\da-zA-Z+/=]+)\1', webpage):
98 links.append(aes_decrypt_text(encrypted_link, title, 32).decode('utf-8'))
101 for video_url in set(unescapeHTML(link) for link in links):
105 # Video URL's path looks like this:
106 # /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
107 # /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
108 # We will benefit from it by extracting some metadata
109 mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+/', video_url)
111 height = int(mobj.group('height'))
112 bitrate = int(mobj.group('bitrate'))
114 'format_id': '%dp-%dk' % (height, bitrate),
119 self._sort_formats(formats)
121 description = self._og_search_description(webpage, default=None)
122 thumbnail = self._search_regex(
123 r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
124 webpage, 'thumbnail', fatal=False, group='thumbnail')
126 uploader = self._html_search_regex(
127 r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
128 webpage, 'uploader', fatal=False)
129 upload_date = unified_strdate(self._html_search_regex(
130 r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>',
131 webpage, 'upload date', fatal=False))
133 age_limit = self._rta_search(webpage)
135 average_rating = int_or_none(self._search_regex(
136 r'<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',
137 webpage, 'average rating', fatal=False))
139 view_count = str_to_int(self._search_regex(
140 r'(?s)<div[^>]+class=(["\']).*?\bvideoInfoViews\b.*?\1[^>]*>.*?(?P<count>[\d,.]+)<',
141 webpage, 'view count', fatal=False, group='count'))
142 comment_count = str_to_int(self._search_regex(
143 r'>All [Cc]omments? \(([\d,.]+)\)',
144 webpage, 'comment count', fatal=False))
146 def extract_tag_box(regex, title):
147 tag_box = self._search_regex(regex, webpage, title, default=None)
150 return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box)
152 categories = extract_tag_box(
153 r'(?s)Categories:.*?</[^>]+>(.+?)</div>', 'categories')
154 tags = extract_tag_box(
155 r'(?s)Tags:.*?</div>\s*<div[^>]+class=["\']tagBoxContent["\'][^>]*>(.+?)</div>',
160 'display_id': display_id,
162 'description': description,
163 'thumbnail': thumbnail,
164 'uploader': uploader,
165 'upload_date': upload_date,
166 'average_rating': average_rating,
167 'view_count': view_count,
168 'comment_count': comment_count,
169 'categories': categories,
171 'age_limit': age_limit,