aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/motherless.py
blob: d4bd273b61e756ef71db83bf264752fb2c0182af (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
from __future__ import unicode_literals

import datetime
import re

from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
    ExtractorError,
    InAdvancePagedList,
    orderedSet,
    str_to_int,
    unified_strdate,
)


class MotherlessIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/)?(?P<id>[A-Z0-9]+)'
    _TESTS = [{
        'url': 'http://motherless.com/AC3FFE1',
        'md5': '310f62e325a9fafe64f68c0bccb6e75f',
        'info_dict': {
            'id': 'AC3FFE1',
            'ext': 'mp4',
            'title': 'Fucked in the ass while playing PS3',
            'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'],
            'upload_date': '20100913',
            'uploader_id': 'famouslyfuckedup',
            'thumbnail': r're:http://.*\.jpg',
            'age_limit': 18,
        }
    }, {
        'url': 'http://motherless.com/532291B',
        'md5': 'bc59a6b47d1f958e61fbd38a4d31b131',
        'info_dict': {
            'id': '532291B',
            'ext': 'mp4',
            'title': 'Amazing girl playing the omegle game, PERFECT!',
            'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen',
                           'game', 'hairy'],
            'upload_date': '20140622',
            'uploader_id': 'Sulivana7x',
            'thumbnail': r're:http://.*\.jpg',
            'age_limit': 18,
        },
        'skip': '404',
    }, {
        'url': 'http://motherless.com/g/cosplay/633979F',
        'md5': '0b2a43f447a49c3e649c93ad1fafa4a0',
        'info_dict': {
            'id': '633979F',
            'ext': 'mp4',
            'title': 'Turtlette',
            'categories': ['superheroine heroine  superher'],
            'upload_date': '20140827',
            'uploader_id': 'shade0230',
            'thumbnail': r're:http://.*\.jpg',
            'age_limit': 18,
        }
    }, {
        # no keywords
        'url': 'http://motherless.com/8B4BBC1',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        video_id = self._match_id(url)
        webpage = self._download_webpage(url, video_id)

        if any(p in webpage for p in (
                '<title>404 - MOTHERLESS.COM<',
                ">The page you're looking for cannot be found.<")):
            raise ExtractorError('Video %s does not exist' % video_id, expected=True)

        if '>The content you are trying to view is for friends only.' in webpage:
            raise ExtractorError('Video %s is for friends only' % video_id, expected=True)

        title = self._html_search_regex(
            r'id="view-upload-title">\s+([^<]+)<', webpage, 'title')
        video_url = (self._html_search_regex(
            (r'setup\(\{\s*["\']file["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
             r'fileurl\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1'),
            webpage, 'video URL', default=None, group='url') or
            'http://cdn4.videos.motherlessmedia.com/videos/%s.mp4?fs=opencloud' % video_id)
        age_limit = self._rta_search(webpage)
        view_count = str_to_int(self._html_search_regex(
            r'<strong>Views</strong>\s+([^<]+)<',
            webpage, 'view count', fatal=False))
        like_count = str_to_int(self._html_search_regex(
            r'<strong>Favorited</strong>\s+([^<]+)<',
            webpage, 'like count', fatal=False))

        upload_date = self._html_search_regex(
            r'<strong>Uploaded</strong>\s+([^<]+)<', webpage, 'upload date')
        if 'Ago' in upload_date:
            days = int(re.search(r'([0-9]+)', upload_date).group(1))
            upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d')
        else:
            upload_date = unified_strdate(upload_date)

        comment_count = webpage.count('class="media-comment-contents"')
        uploader_id = self._html_search_regex(
            r'"thumb-member-username">\s+<a href="/m/([^"]+)"',
            webpage, 'uploader_id')

        categories = self._html_search_meta('keywords', webpage, default=None)
        if categories:
            categories = [cat.strip() for cat in categories.split(',')]

        return {
            'id': video_id,
            'title': title,
            'upload_date': upload_date,
            'uploader_id': uploader_id,
            'thumbnail': self._og_search_thumbnail(webpage),
            'categories': categories,
            'view_count': view_count,
            'like_count': like_count,
            'comment_count': comment_count,
            'age_limit': age_limit,
            'url': video_url,
        }


class MotherlessGroupIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?motherless\.com/gv?/(?P<id>[a-z0-9_]+)'
    _TESTS = [{
        'url': 'http://motherless.com/g/movie_scenes',
        'info_dict': {
            'id': 'movie_scenes',
            'title': 'Movie Scenes',
            'description': 'Hot and sexy scenes from "regular" movies... '
                           'Beautiful actresses fully nude... A looot of '
                           'skin! :)Enjoy!',
        },
        'playlist_mincount': 662,
    }, {
        'url': 'http://motherless.com/gv/sex_must_be_funny',
        'info_dict': {
            'id': 'sex_must_be_funny',
            'title': 'Sex must be funny',
            'description': 'Sex can be funny. Wide smiles,laugh, games, fun of '
                           'any kind!'
        },
        'playlist_mincount': 9,
    }]

    @classmethod
    def suitable(cls, url):
        return (False if MotherlessIE.suitable(url)
                else super(MotherlessGroupIE, cls).suitable(url))

    def _extract_entries(self, webpage, base):
        entries = []
        for mobj in re.finditer(
                r'href="(?P<href>/[^"]+)"[^>]*>(?:\s*<img[^>]+alt="[^-]+-\s(?P<title>[^"]+)")?',
                webpage):
            video_url = compat_urlparse.urljoin(base, mobj.group('href'))
            if not MotherlessIE.suitable(video_url):
                continue
            video_id = MotherlessIE._match_id(video_url)
            title = mobj.group('title')
            entries.append(self.url_result(
                video_url, ie=MotherlessIE.ie_key(), video_id=video_id,
                video_title=title))
        # Alternative fallback
        if not entries:
            entries = [
                self.url_result(
                    compat_urlparse.urljoin(base, '/' + entry_id),
                    ie=MotherlessIE.ie_key(), video_id=entry_id)
                for entry_id in orderedSet(re.findall(
                    r'data-codename=["\']([A-Z0-9]+)', webpage))]
        return entries

    def _real_extract(self, url):
        group_id = self._match_id(url)
        page_url = compat_urlparse.urljoin(url, '/gv/%s' % group_id)
        webpage = self._download_webpage(page_url, group_id)
        title = self._search_regex(
            r'<title>([\w\s]+\w)\s+-', webpage, 'title', fatal=False)
        description = self._html_search_meta(
            'description', webpage, fatal=False)
        page_count = self._int(self._search_regex(
            r'(\d+)</(?:a|span)><(?:a|span)[^>]+>\s*NEXT',
            webpage, 'page_count'), 'page_count')
        PAGE_SIZE = 80

        def _get_page(idx):
            webpage = self._download_webpage(
                page_url, group_id, query={'page': idx + 1},
                note='Downloading page %d/%d' % (idx + 1, page_count)
            )
            for entry in self._extract_entries(webpage, url):
                yield entry

        playlist = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)

        return {
            '_type': 'playlist',
            'id': group_id,
            'title': title,
            'description': description,
            'entries': playlist
        }