]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/toypics.py
[pornhub] Extract categories and tags (closes #10499)
[youtube-dl] / youtube_dl / extractor / toypics.py
1 # -*- coding:utf-8 -*-
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 import re
6
7
8 class ToypicsIE(InfoExtractor):
9     IE_DESC = 'Toypics user profile'
10     _VALID_URL = r'https?://videos\.toypics\.net/view/(?P<id>[0-9]+)/.*'
11     _TEST = {
12         'url': 'http://videos.toypics.net/view/514/chancebulged,-2-1/',
13         'md5': '16e806ad6d6f58079d210fe30985e08b',
14         'info_dict': {
15             'id': '514',
16             'ext': 'mp4',
17             'title': 'Chance-Bulge\'d, 2',
18             'age_limit': 18,
19             'uploader': 'kidsune',
20         }
21     }
22
23     def _real_extract(self, url):
24         mobj = re.match(self._VALID_URL, url)
25         video_id = mobj.group('id')
26         page = self._download_webpage(url, video_id)
27         video_url = self._html_search_regex(
28             r'src:\s+"(http://static[0-9]+\.toypics\.net/flvideo/[^"]+)"', page, 'video URL')
29         title = self._html_search_regex(
30             r'<title>Toypics - ([^<]+)</title>', page, 'title')
31         username = self._html_search_regex(
32             r'toypics.net/([^/"]+)" class="user-name">', page, 'username')
33         return {
34             'id': video_id,
35             'url': video_url,
36             'title': title,
37             'uploader': username,
38             'age_limit': 18,
39         }
40
41
42 class ToypicsUserIE(InfoExtractor):
43     IE_DESC = 'Toypics user profile'
44     _VALID_URL = r'https?://videos\.toypics\.net/(?P<username>[^/?]+)(?:$|[?#])'
45     _TEST = {
46         'url': 'http://videos.toypics.net/Mikey',
47         'info_dict': {
48             'id': 'Mikey',
49         },
50         'playlist_mincount': 19,
51     }
52
53     def _real_extract(self, url):
54         mobj = re.match(self._VALID_URL, url)
55         username = mobj.group('username')
56
57         profile_page = self._download_webpage(
58             url, username, note='Retrieving profile page')
59
60         video_count = int(self._search_regex(
61             r'public/">Public Videos \(([0-9]+)\)</a></li>', profile_page,
62             'video count'))
63
64         PAGE_SIZE = 8
65         urls = []
66         page_count = (video_count + PAGE_SIZE + 1) // PAGE_SIZE
67         for n in range(1, page_count + 1):
68             lpage_url = url + '/public/%d' % n
69             lpage = self._download_webpage(
70                 lpage_url, username,
71                 note='Downloading page %d/%d' % (n, page_count))
72             urls.extend(
73                 re.findall(
74                     r'<p class="video-entry-title">\s+<a href="(https?://videos.toypics.net/view/[^"]+)">',
75                     lpage))
76
77         return {
78             '_type': 'playlist',
79             'id': username,
80             'entries': [{
81                 '_type': 'url',
82                 'url': eurl,
83                 'ie_key': 'Toypics',
84             } for eurl in urls]
85         }