]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/youporn.py
Update changelog.
[youtubedl] / youtube_dl / extractor / youporn.py
1 from __future__ import unicode_literals
2
3
4 import json
5 import re
6 import sys
7
8 from .common import InfoExtractor
9 from ..compat import (
10 compat_urllib_parse_urlparse,
11 compat_urllib_request,
12 )
13 from ..utils import (
14 ExtractorError,
15 unescapeHTML,
16 unified_strdate,
17 )
18 from ..aes import (
19 aes_decrypt_text
20 )
21
22
23 class YouPornIE(InfoExtractor):
24 _VALID_URL = r'^(?P<proto>https?://)(?:www\.)?(?P<url>youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+))'
25 _TEST = {
26 'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
27 'info_dict': {
28 'id': '505835',
29 'ext': 'mp4',
30 'upload_date': '20101221',
31 'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
32 'uploader': 'Ask Dan And Jennifer',
33 'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
34 'age_limit': 18,
35 }
36 }
37
38 def _real_extract(self, url):
39 mobj = re.match(self._VALID_URL, url)
40 video_id = mobj.group('videoid')
41 url = mobj.group('proto') + 'www.' + mobj.group('url')
42
43 req = compat_urllib_request.Request(url)
44 req.add_header('Cookie', 'age_verified=1')
45 webpage = self._download_webpage(req, video_id)
46 age_limit = self._rta_search(webpage)
47
48 # Get JSON parameters
49 json_params = self._search_regex(
50 [r'videoJa?son\s*=\s*({.+})',
51 r'var\s+currentVideo\s*=\s*new\s+Video\((.+?)\)[,;]'],
52 webpage, 'JSON parameters')
53 try:
54 params = json.loads(json_params)
55 except ValueError:
56 raise ExtractorError('Invalid JSON')
57
58 self.report_extraction(video_id)
59 try:
60 video_title = params['title']
61 upload_date = unified_strdate(params['release_date_f'])
62 video_description = params['description']
63 video_uploader = params['submitted_by']
64 thumbnail = params['thumbnails'][0]['image']
65 except KeyError:
66 raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
67
68 # Get all of the links from the page
69 DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
70 download_list_html = self._search_regex(DOWNLOAD_LIST_RE,
71 webpage, 'download list').strip()
72 LINK_RE = r'<a href="([^"]+)">'
73 links = re.findall(LINK_RE, download_list_html)
74
75 # Get all encrypted links
76 encrypted_links = re.findall(r'var encryptedQuality[0-9]{3}URL = \'([a-zA-Z0-9+/]+={0,2})\';', webpage)
77 for encrypted_link in encrypted_links:
78 link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
79 links.append(link)
80
81 formats = []
82 for link in links:
83 # A link looks like this:
84 # 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
85 # A path looks like this:
86 # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
87 video_url = unescapeHTML(link)
88 path = compat_urllib_parse_urlparse(video_url).path
89 format_parts = path.split('/')[4].split('_')[:2]
90
91 dn = compat_urllib_parse_urlparse(video_url).netloc.partition('.')[0]
92
93 resolution = format_parts[0]
94 height = int(resolution[:-len('p')])
95 bitrate = int(format_parts[1][:-len('k')])
96 format = '-'.join(format_parts) + '-' + dn
97
98 formats.append({
99 'url': video_url,
100 'format': format,
101 'format_id': format,
102 'height': height,
103 'tbr': bitrate,
104 'resolution': resolution,
105 })
106
107 self._sort_formats(formats)
108
109 if not formats:
110 raise ExtractorError('ERROR: no known formats available for video')
111
112 return {
113 'id': video_id,
114 'uploader': video_uploader,
115 'upload_date': upload_date,
116 'title': video_title,
117 'thumbnail': thumbnail,
118 'description': video_description,
119 'age_limit': age_limit,
120 'formats': formats,
121 }