1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import datetime
5 import re
6
7 from .common import InfoExtractor
8 from ..compat import compat_urlparse
9 from ..utils import (
10 ExtractorError,
11 InAdvancePagedList,
12 orderedSet,
13 str_to_int,
14 unified_strdate,
15 )
16
17
18 class MotherlessIE(InfoExtractor):
19 _VALID_URL = r'https?://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/)?(?P<id>[A-Z0-9]+)'
20 _TESTS = [{
21 'url': 'http://motherless.com/AC3FFE1',
22 'md5': '310f62e325a9fafe64f68c0bccb6e75f',
23 'info_dict': {
24 'id': 'AC3FFE1',
25 'ext': 'mp4',
26 'title': 'Fucked in the ass while playing PS3',
27 'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'],
28 'upload_date': '20100913',
29 'uploader_id': 'famouslyfuckedup',
30 'thumbnail': r're:https?://.*\.jpg',
31 'age_limit': 18,
32 }
33 }, {
34 'url': 'http://motherless.com/532291B',
35 'md5': 'bc59a6b47d1f958e61fbd38a4d31b131',
36 'info_dict': {
37 'id': '532291B',
38 'ext': 'mp4',
39 'title': 'Amazing girl playing the omegle game, PERFECT!',
40 'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen',
41 'game', 'hairy'],
42 'upload_date': '20140622',
43 'uploader_id': 'Sulivana7x',
44 'thumbnail': r're:https?://.*\.jpg',
45 'age_limit': 18,
46 },
47 'skip': '404',
48 }, {
49 'url': 'http://motherless.com/g/cosplay/633979F',
50 'md5': '0b2a43f447a49c3e649c93ad1fafa4a0',
51 'info_dict': {
52 'id': '633979F',
53 'ext': 'mp4',
54 'title': 'Turtlette',
55 'categories': ['superheroine heroine superher'],
56 'upload_date': '20140827',
57 'uploader_id': 'shade0230',
58 'thumbnail': r're:https?://.*\.jpg',
59 'age_limit': 18,
60 }
61 }, {
62 # no keywords
63 'url': 'http://motherless.com/8B4BBC1',
64 'only_matching': True,
65 }, {
66 # see https://motherless.com/videos/recent for recent videos with
67 # uploaded date in "ago" format
68 'url': 'https://motherless.com/3C3E2CF',
69 'info_dict': {
70 'id': '3C3E2CF',
71 'ext': 'mp4',
72 'title': 'a/ Hot Teens',
73 'categories': list,
74 'upload_date': '20210104',
75 'uploader_id': 'anonymous',
76 'thumbnail': r're:https?://.*\.jpg',
77 'age_limit': 18,
78 },
79 'params': {
80 'skip_download': True,
81 },
82 }]
83
84 def _real_extract(self, url):
85 video_id = self._match_id(url)
86 webpage = self._download_webpage(url, video_id)
87
88 if any(p in webpage for p in (
89 '<title>404 - MOTHERLESS.COM<',
90 ">The page you're looking for cannot be found.<")):
91 raise ExtractorError('Video %s does not exist' % video_id, expected=True)
92
93 if '>The content you are trying to view is for friends only.' in webpage:
94 raise ExtractorError('Video %s is for friends only' % video_id, expected=True)
95
96 title = self._html_search_regex(
97 (r'(?s)<div[^>]+\bclass=["\']media-meta-title[^>]+>(.+?)</div>',
98 r'id="view-upload-title">\s+([^<]+)<'), webpage, 'title')
99 video_url = (self._html_search_regex(
100 (r'setup\(\{\s*["\']file["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
101 r'fileurl\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1'),
102 webpage, 'video URL', default=None, group='url')
103 or 'http://cdn4.videos.motherlessmedia.com/videos/%s.mp4?fs=opencloud' % video_id)
104 age_limit = self._rta_search(webpage)
105 view_count = str_to_int(self._html_search_regex(
106 (r'>([\d,.]+)\s+Views<', r'<strong>Views</strong>\s+([^<]+)<'),
107 webpage, 'view count', fatal=False))
108 like_count = str_to_int(self._html_search_regex(
109 (r'>([\d,.]+)\s+Favorites<',
110 r'<strong>Favorited</strong>\s+([^<]+)<'),
111 webpage, 'like count', fatal=False))
112
113 upload_date = unified_strdate(self._search_regex(
114 r'class=["\']count[^>]+>(\d+\s+[a-zA-Z]{3}\s+\d{4})<', webpage,
115 'upload date', default=None))
116 if not upload_date:
117 uploaded_ago = self._search_regex(
118 r'>\s*(\d+[hd])\s+[aA]go\b', webpage, 'uploaded ago',
119 default=None)
120 if uploaded_ago:
121 delta = int(uploaded_ago[:-1])
122 _AGO_UNITS = {
123 'h': 'hours',
124 'd': 'days',
125 }
126 kwargs = {_AGO_UNITS.get(uploaded_ago[-1]): delta}
127 upload_date = (datetime.datetime.utcnow() - datetime.timedelta(**kwargs)).strftime('%Y%m%d')
128
129 comment_count = len(re.findall(r'''class\s*=\s*['"]media-comment-contents\b''', webpage))
130 uploader_id = self._html_search_regex(
131 (r'''<span\b[^>]+\bclass\s*=\s*["']username\b[^>]*>([^<]+)</span>''',
132 r'''(?s)['"](?:media-meta-member|thumb-member-username)\b[^>]+>\s*<a\b[^>]+\bhref\s*=\s*['"]/m/([^"']+)'''),
133 webpage, 'uploader_id')
134
135 categories = self._html_search_meta('keywords', webpage, default=None)
136 if categories:
137 categories = [cat.strip() for cat in categories.split(',')]
138
139 return {
140 'id': video_id,
141 'title': title,
142 'upload_date': upload_date,
143 'uploader_id': uploader_id,
144 'thumbnail': self._og_search_thumbnail(webpage),
145 'categories': categories,
146 'view_count': view_count,
147 'like_count': like_count,
148 'comment_count': comment_count,
149 'age_limit': age_limit,
150 'url': video_url,
151 }
152
153
154 class MotherlessGroupIE(InfoExtractor):
155 _VALID_URL = r'https?://(?:www\.)?motherless\.com/gv?/(?P<id>[a-z0-9_]+)'
156 _TESTS = [{
157 'url': 'http://motherless.com/g/movie_scenes',
158 'info_dict': {
159 'id': 'movie_scenes',
160 'title': 'Movie Scenes',
161 'description': 'Hot and sexy scenes from "regular" movies... '
162 'Beautiful actresses fully nude... A looot of '
163 'skin! :)Enjoy!',
164 },
165 'playlist_mincount': 662,
166 }, {
167 'url': 'http://motherless.com/gv/sex_must_be_funny',
168 'info_dict': {
169 'id': 'sex_must_be_funny',
170 'title': 'Sex must be funny',
171 'description': 'Sex can be funny. Wide smiles,laugh, games, fun of '
172 'any kind!'
173 },
174 'playlist_mincount': 0,
175 'expected_warnings': [
176 'This group has no videos.',
177 ]
178 }, {
179 'url': 'https://motherless.com/g/beautiful_cock',
180 'info_dict': {
181 'id': 'beautiful_cock',
182 'title': 'Beautiful Cock',
183 'description': 'Group for lovely cocks yours, mine, a friends anything human',
184 },
185 'playlist_mincount': 2500,
186 }]
187
188 @classmethod
189 def suitable(cls, url):
190 return (False if MotherlessIE.suitable(url)
191 else super(MotherlessGroupIE, cls).suitable(url))
192
193 def _extract_entries(self, webpage, base):
194 entries = []
195 for mobj in re.finditer(
196 r'href="(?P<href>/[^"]+)"[^>]*>(?:\s*<img[^>]+alt="[^-]+-\s(?P<title>[^"]+)")?',
197 webpage):
198 video_url = compat_urlparse.urljoin(base, mobj.group('href'))
199 if not MotherlessIE.suitable(video_url):
200 continue
201 video_id = MotherlessIE._match_id(video_url)
202 title = mobj.group('title')
203 entries.append(self.url_result(
204 video_url, ie=MotherlessIE.ie_key(), video_id=video_id,
205 video_title=title))
206 # Alternative fallback
207 if not entries:
208 entries = [
209 self.url_result(
210 compat_urlparse.urljoin(base, '/' + entry_id),
211 ie=MotherlessIE.ie_key(), video_id=entry_id)
212 for entry_id in orderedSet(re.findall(
213 r'data-codename=["\']([A-Z0-9]+)', webpage))]
214 return entries
215
216 def _real_extract(self, url):
217 group_id = self._match_id(url)
218 page_url = compat_urlparse.urljoin(url, '/gv/%s' % group_id)
219 webpage = self._download_webpage(page_url, group_id)
220 title = self._search_regex(
221 r'<title>([\w\s]+\w)\s+-', webpage, 'title', fatal=False)
222 description = self._html_search_meta(
223 'description', webpage, fatal=False)
224 page_count = str_to_int(self._search_regex(
225 r'(\d+)\s*</(?:a|span)>\s*<(?:a|span)[^>]+(?:>\s*NEXT|\brel\s*=\s*["\']?next)\b',
226 webpage, 'page_count', default=0))
227 if not page_count:
228 message = self._search_regex(
229 r'''class\s*=\s*['"]error-page\b[^>]*>\s*<p[^>]*>\s*(?P<error_msg>[^<]+)(?<=\S)\s*''',
230 webpage, 'error_msg', default=None) or 'This group has no videos.'
231 self.report_warning(message, group_id)
232 page_count = 1
233 PAGE_SIZE = 80
234
235 def _get_page(idx):
236 if idx > 0:
237 webpage = self._download_webpage(
238 page_url, group_id, query={'page': idx + 1},
239 note='Downloading page %d/%d' % (idx + 1, page_count)
240 )
241 for entry in self._extract_entries(webpage, url):
242 yield entry
243
244 playlist = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
245
246 return {
247 '_type': 'playlist',
248 'id': group_id,
249 'title': title,
250 'description': description,
251 'entries': playlist
252 }
|
