]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/youporn.py
Update changelog.
[youtubedl] / youtube_dl / extractor / youporn.py
1 import json
2 import re
3 import sys
4
5 from .common import InfoExtractor
6 from ..utils import (
7 compat_urllib_parse_urlparse,
8 compat_urllib_request,
9
10 ExtractorError,
11 unescapeHTML,
12 unified_strdate,
13 )
14 from ..aes import (
15 aes_decrypt_text
16 )
17
18
19 class YouPornIE(InfoExtractor):
20 _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+))'
21 _TEST = {
22 u'url': u'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
23 u'file': u'505835.mp4',
24 u'md5': u'71ec5fcfddacf80f495efa8b6a8d9a89',
25 u'info_dict': {
26 u"upload_date": u"20101221",
27 u"description": u"Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?",
28 u"uploader": u"Ask Dan And Jennifer",
29 u"title": u"Sex Ed: Is It Safe To Masturbate Daily?",
30 u"age_limit": 18,
31 }
32 }
33
34 def _real_extract(self, url):
35 mobj = re.match(self._VALID_URL, url)
36 video_id = mobj.group('videoid')
37 url = 'http://www.' + mobj.group('url')
38
39 req = compat_urllib_request.Request(url)
40 req.add_header('Cookie', 'age_verified=1')
41 webpage = self._download_webpage(req, video_id)
42 age_limit = self._rta_search(webpage)
43
44 # Get JSON parameters
45 json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, u'JSON parameters')
46 try:
47 params = json.loads(json_params)
48 except:
49 raise ExtractorError(u'Invalid JSON')
50
51 self.report_extraction(video_id)
52 try:
53 video_title = params['title']
54 upload_date = unified_strdate(params['release_date_f'])
55 video_description = params['description']
56 video_uploader = params['submitted_by']
57 thumbnail = params['thumbnails'][0]['image']
58 except KeyError:
59 raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
60
61 # Get all of the links from the page
62 DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
63 download_list_html = self._search_regex(DOWNLOAD_LIST_RE,
64 webpage, u'download list').strip()
65 LINK_RE = r'<a href="([^"]+)">'
66 links = re.findall(LINK_RE, download_list_html)
67
68 # Get all encrypted links
69 encrypted_links = re.findall(r'var encryptedQuality[0-9]{3}URL = \'([a-zA-Z0-9+/]+={0,2})\';', webpage)
70 for encrypted_link in encrypted_links:
71 link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
72 links.append(link)
73
74 formats = []
75 for link in links:
76 # A link looks like this:
77 # 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
78 # A path looks like this:
79 # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
80 video_url = unescapeHTML(link)
81 path = compat_urllib_parse_urlparse(video_url).path
82 format_parts = path.split('/')[4].split('_')[:2]
83
84 dn = compat_urllib_parse_urlparse(video_url).netloc.partition('.')[0]
85
86 resolution = format_parts[0]
87 height = int(resolution[:-len('p')])
88 bitrate = int(format_parts[1][:-len('k')])
89 format = u'-'.join(format_parts) + u'-' + dn
90
91 formats.append({
92 'url': video_url,
93 'format': format,
94 'format_id': format,
95 'height': height,
96 'tbr': bitrate,
97 'resolution': resolution,
98 })
99
100 self._sort_formats(formats)
101
102 if not formats:
103 raise ExtractorError(u'ERROR: no known formats available for video')
104
105 return {
106 'id': video_id,
107 'uploader': video_uploader,
108 'upload_date': upload_date,
109 'title': video_title,
110 'thumbnail': thumbnail,
111 'description': video_description,
112 'age_limit': age_limit,
113 'formats': formats,
114 }