]>
Commit | Line | Data |
---|---|---|
f24e9833 PH |
1 | from __future__ import unicode_literals |
2 | ||
0143dc02 | 3 | import re |
0143dc02 PH |
4 | |
5 | from .common import InfoExtractor | |
1cc79574 | 6 | from ..utils import ( |
589c33da | 7 | int_or_none, |
5c2266df | 8 | sanitized_Request, |
589c33da | 9 | str_to_int, |
0143dc02 PH |
10 | unescapeHTML, |
11 | unified_strdate, | |
12 | ) | |
589c33da | 13 | from ..aes import aes_decrypt_text |
0143dc02 | 14 | |
bfe9de85 | 15 | |
0143dc02 | 16 | class YouPornIE(InfoExtractor): |
589c33da | 17 | _VALID_URL = r'https?://(?:www\.)?youporn\.com/watch/(?P<id>\d+)/(?P<display_id>[^/?#&]+)' |
4f13f8f7 | 18 | _TESTS = [{ |
f24e9833 | 19 | 'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/', |
2c3322e3 | 20 | 'md5': '3744d24c50438cf5b6f6d59feb5055c2', |
f24e9833 PH |
21 | 'info_dict': { |
22 | 'id': '505835', | |
589c33da | 23 | 'display_id': 'sex-ed-is-it-safe-to-masturbate-daily', |
f24e9833 | 24 | 'ext': 'mp4', |
f24e9833 | 25 | 'title': 'Sex Ed: Is It Safe To Masturbate Daily?', |
589c33da S |
26 | 'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?', |
27 | 'thumbnail': 're:^https?://.*\.jpg$', | |
e572a101 | 28 | 'uploader': 'Ask Dan And Jennifer', |
589c33da S |
29 | 'upload_date': '20101221', |
30 | 'average_rating': int, | |
31 | 'view_count': int, | |
755ff8d2 | 32 | 'comment_count': int, |
589c33da S |
33 | 'categories': list, |
34 | 'tags': list, | |
f24e9833 | 35 | 'age_limit': 18, |
4f13f8f7 S |
36 | }, |
37 | }, { | |
38 | # Anonymous User uploader | |
39 | 'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4', | |
40 | 'info_dict': { | |
41 | 'id': '561726', | |
42 | 'display_id': 'big-tits-awesome-brunette-on-amazing-webcam-show', | |
43 | 'ext': 'mp4', | |
44 | 'title': 'Big Tits Awesome Brunette On amazing webcam show', | |
45 | 'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4', | |
46 | 'thumbnail': 're:^https?://.*\.jpg$', | |
47 | 'uploader': 'Anonymous User', | |
48 | 'upload_date': '20111125', | |
49 | 'average_rating': int, | |
50 | 'view_count': int, | |
755ff8d2 | 51 | 'comment_count': int, |
4f13f8f7 S |
52 | 'categories': list, |
53 | 'tags': list, | |
54 | 'age_limit': 18, | |
55 | }, | |
56 | 'params': { | |
57 | 'skip_download': True, | |
58 | }, | |
59 | }] | |
0143dc02 | 60 | |
0143dc02 PH |
61 | def _real_extract(self, url): |
62 | mobj = re.match(self._VALID_URL, url) | |
589c33da S |
63 | video_id = mobj.group('id') |
64 | display_id = mobj.group('display_id') | |
0143dc02 | 65 | |
5c2266df | 66 | request = sanitized_Request(url) |
589c33da S |
67 | request.add_header('Cookie', 'age_verified=1') |
68 | webpage = self._download_webpage(request, display_id) | |
69 | ||
70 | title = self._search_regex( | |
71 | [r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P<title>.+?)\1', | |
72 | r'<h1[^>]+class=["\']heading\d?["\'][^>]*>([^<])<'], | |
73 | webpage, 'title', group='title') | |
0143dc02 | 74 | |
589c33da S |
75 | links = [] |
76 | ||
77 | sources = self._search_regex( | |
002c7552 | 78 | r'(?s)sources\s*:\s*({.+?})', webpage, 'sources', default=None) |
589c33da S |
79 | if sources: |
80 | for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources): | |
e572a101 | 81 | links.append(link) |
5f6a1245 | 82 | |
589c33da S |
83 | # Fallback #1 |
84 | for _, link in re.findall( | |
85 | r'(?:videoUrl|videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage): | |
86 | links.append(link) | |
87 | ||
88 | # Fallback #2, this also contains extra low quality 180p format | |
89 | for _, link in re.findall(r'<a[^>]+href=(["\'])(http.+?)\1[^>]+title=["\']Download [Vv]ideo', webpage): | |
90 | links.append(link) | |
91 | ||
92 | # Fallback #3, encrypted links | |
93 | for _, encrypted_link in re.findall( | |
94 | r'encryptedQuality\d{3,4}URL\s*=\s*(["\'])([\da-zA-Z+/=]+)\1', webpage): | |
95 | links.append(aes_decrypt_text(encrypted_link, title, 32).decode('utf-8')) | |
96 | ||
0143dc02 | 97 | formats = [] |
589c33da S |
98 | for video_url in set(unescapeHTML(link) for link in links): |
99 | f = { | |
0143dc02 | 100 | 'url': video_url, |
589c33da S |
101 | } |
102 | # Video URL's path looks like this: | |
103 | # /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4 | |
d627cec6 | 104 | # /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4 |
589c33da | 105 | # We will benefit from it by extracting some metadata |
d627cec6 | 106 | mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+/', video_url) |
589c33da S |
107 | if mobj: |
108 | height = int(mobj.group('height')) | |
109 | bitrate = int(mobj.group('bitrate')) | |
110 | f.update({ | |
111 | 'format_id': '%dp-%dk' % (height, bitrate), | |
112 | 'height': height, | |
113 | 'tbr': bitrate, | |
114 | }) | |
115 | formats.append(f) | |
bfe9de85 PH |
116 | self._sort_formats(formats) |
117 | ||
b99d88c6 | 118 | description = self._og_search_description(webpage, default=None) |
589c33da S |
119 | thumbnail = self._search_regex( |
120 | r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1', | |
121 | webpage, 'thumbnail', fatal=False, group='thumbnail') | |
122 | ||
4f13f8f7 | 123 | uploader = self._html_search_regex( |
2c3322e3 | 124 | r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>', |
589c33da S |
125 | webpage, 'uploader', fatal=False) |
126 | upload_date = unified_strdate(self._html_search_regex( | |
2c3322e3 | 127 | r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>', |
589c33da S |
128 | webpage, 'upload date', fatal=False)) |
129 | ||
130 | age_limit = self._rta_search(webpage) | |
131 | ||
132 | average_rating = int_or_none(self._search_regex( | |
2c3322e3 | 133 | r'<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>', |
589c33da S |
134 | webpage, 'average rating', fatal=False)) |
135 | ||
136 | view_count = str_to_int(self._search_regex( | |
2c3322e3 S |
137 | r'(?s)<div[^>]+class=(["\']).*?\bvideoInfoViews\b.*?\1[^>]*>.*?(?P<count>[\d,.]+)<', |
138 | webpage, 'view count', fatal=False, group='count')) | |
755ff8d2 S |
139 | comment_count = str_to_int(self._search_regex( |
140 | r'>All [Cc]omments? \(([\d,.]+)\)', | |
141 | webpage, 'comment count', fatal=False)) | |
589c33da S |
142 | |
143 | def extract_tag_box(title): | |
144 | tag_box = self._search_regex( | |
145 | (r'<div[^>]+class=["\']tagBoxTitle["\'][^>]*>\s*%s\b.*?</div>\s*' | |
146 | '<div[^>]+class=["\']tagBoxContent["\']>(.+?)</div>') % re.escape(title), | |
147 | webpage, '%s tag box' % title, default=None) | |
148 | if not tag_box: | |
149 | return [] | |
150 | return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box) | |
151 | ||
152 | categories = extract_tag_box('Category') | |
153 | tags = extract_tag_box('Tags') | |
5f6a1245 | 154 | |
7df28654 | 155 | return { |
156 | 'id': video_id, | |
589c33da S |
157 | 'display_id': display_id, |
158 | 'title': title, | |
159 | 'description': description, | |
160 | 'thumbnail': thumbnail, | |
161 | 'uploader': uploader, | |
162 | 'upload_date': upload_date, | |
163 | 'average_rating': average_rating, | |
164 | 'view_count': view_count, | |
755ff8d2 | 165 | 'comment_count': comment_count, |
589c33da S |
166 | 'categories': categories, |
167 | 'tags': tags, | |
7df28654 | 168 | 'age_limit': age_limit, |
169 | 'formats': formats, | |
170 | } |