]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/motherless.py
Merge tag 'upstream/2015.06.04.1'
[youtubedl] / youtube_dl / extractor / motherless.py
1 from __future__ import unicode_literals
2
3 import datetime
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import (
8 str_to_int,
9 unified_strdate,
10 )
11
12
13 class MotherlessIE(InfoExtractor):
14 _VALID_URL = r'http://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/)?(?P<id>[A-Z0-9]+)'
15 _TESTS = [
16 {
17 'url': 'http://motherless.com/AC3FFE1',
18 'md5': '310f62e325a9fafe64f68c0bccb6e75f',
19 'info_dict': {
20 'id': 'AC3FFE1',
21 'ext': 'mp4',
22 'title': 'Fucked in the ass while playing PS3',
23 'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'],
24 'upload_date': '20100913',
25 'uploader_id': 'famouslyfuckedup',
26 'thumbnail': 're:http://.*\.jpg',
27 'age_limit': 18,
28 }
29 },
30 {
31 'url': 'http://motherless.com/532291B',
32 'md5': 'bc59a6b47d1f958e61fbd38a4d31b131',
33 'info_dict': {
34 'id': '532291B',
35 'ext': 'mp4',
36 'title': 'Amazing girl playing the omegle game, PERFECT!',
37 'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen', 'game', 'hairy'],
38 'upload_date': '20140622',
39 'uploader_id': 'Sulivana7x',
40 'thumbnail': 're:http://.*\.jpg',
41 'age_limit': 18,
42 }
43 },
44 {
45 'url': 'http://motherless.com/g/cosplay/633979F',
46 'md5': '0b2a43f447a49c3e649c93ad1fafa4a0',
47 'info_dict': {
48 'id': '633979F',
49 'ext': 'mp4',
50 'title': 'Turtlette',
51 'categories': ['superheroine heroine superher'],
52 'upload_date': '20140827',
53 'uploader_id': 'shade0230',
54 'thumbnail': 're:http://.*\.jpg',
55 'age_limit': 18,
56 }
57 }
58 ]
59
60 def _real_extract(self, url):
61 video_id = self._match_id(url)
62 webpage = self._download_webpage(url, video_id)
63
64 title = self._html_search_regex(
65 r'id="view-upload-title">\s+([^<]+)<', webpage, 'title')
66 video_url = self._html_search_regex(
67 r'setup\(\{\s+"file".+: "([^"]+)",', webpage, 'video URL')
68 age_limit = self._rta_search(webpage)
69 view_count = str_to_int(self._html_search_regex(
70 r'<strong>Views</strong>\s+([^<]+)<',
71 webpage, 'view count', fatal=False))
72 like_count = str_to_int(self._html_search_regex(
73 r'<strong>Favorited</strong>\s+([^<]+)<',
74 webpage, 'like count', fatal=False))
75
76 upload_date = self._html_search_regex(
77 r'<strong>Uploaded</strong>\s+([^<]+)<', webpage, 'upload date')
78 if 'Ago' in upload_date:
79 days = int(re.search(r'([0-9]+)', upload_date).group(1))
80 upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d')
81 else:
82 upload_date = unified_strdate(upload_date)
83
84 comment_count = webpage.count('class="media-comment-contents"')
85 uploader_id = self._html_search_regex(
86 r'"thumb-member-username">\s+<a href="/m/([^"]+)"',
87 webpage, 'uploader_id')
88
89 categories = self._html_search_meta('keywords', webpage)
90 if categories:
91 categories = [cat.strip() for cat in categories.split(',')]
92
93 return {
94 'id': video_id,
95 'title': title,
96 'upload_date': upload_date,
97 'uploader_id': uploader_id,
98 'thumbnail': self._og_search_thumbnail(webpage),
99 'categories': categories,
100 'view_count': view_count,
101 'like_count': like_count,
102 'comment_count': comment_count,
103 'age_limit': age_limit,
104 'url': video_url,
105 }