1 from __future__
import unicode_literals
6 from .common
import InfoExtractor
7 from ..compat
import compat_urlparse
17 class MotherlessIE(InfoExtractor
):
18 _VALID_URL
= r
'https?://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/)?(?P<id>[A-Z0-9]+)'
20 'url': 'http://motherless.com/AC3FFE1',
21 'md5': '310f62e325a9fafe64f68c0bccb6e75f',
25 'title': 'Fucked in the ass while playing PS3',
26 'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'],
27 'upload_date': '20100913',
28 'uploader_id': 'famouslyfuckedup',
29 'thumbnail': r
're:http://.*\.jpg',
33 'url': 'http://motherless.com/532291B',
34 'md5': 'bc59a6b47d1f958e61fbd38a4d31b131',
38 'title': 'Amazing girl playing the omegle game, PERFECT!',
39 'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen',
41 'upload_date': '20140622',
42 'uploader_id': 'Sulivana7x',
43 'thumbnail': r
're:http://.*\.jpg',
48 'url': 'http://motherless.com/g/cosplay/633979F',
49 'md5': '0b2a43f447a49c3e649c93ad1fafa4a0',
54 'categories': ['superheroine heroine superher'],
55 'upload_date': '20140827',
56 'uploader_id': 'shade0230',
57 'thumbnail': r
're:http://.*\.jpg',
62 'url': 'http://motherless.com/8B4BBC1',
63 'only_matching': True,
66 def _real_extract(self
, url
):
67 video_id
= self
._match
_id
(url
)
68 webpage
= self
._download
_webpage
(url
, video_id
)
70 if any(p
in webpage
for p
in (
71 '<title>404 - MOTHERLESS.COM<',
72 ">The page you're looking for cannot be found.<")):
73 raise ExtractorError('Video %s does not exist' % video_id
, expected
=True)
75 if '>The content you are trying to view is for friends only.' in webpage
:
76 raise ExtractorError('Video %s is for friends only' % video_id
, expected
=True)
78 title
= self
._html
_search
_regex
(
79 r
'id="view-upload-title">\s+([^<]+)<', webpage
, 'title')
80 video_url
= (self
._html
_search
_regex
(
81 (r
'setup\(\{\s*["\']file["\']\s*:\s*(["\'])(?P
<url
>(?
:(?
!\
1).)+)\
1',
82 r'fileurl\s
*=\s
*(["\'])(?P<url>(?:(?!\1).)+)\1'),
83 webpage, 'video URL', default=None, group='url')
84 or 'http://cdn4.videos.motherlessmedia.com/videos/%s.mp4?fs=opencloud' % video_id)
85 age_limit = self._rta_search(webpage)
86 view_count = str_to_int(self._html_search_regex(
87 r'<strong>Views</strong>\s+([^<]+)<',
88 webpage, 'view count', fatal=False))
89 like_count = str_to_int(self._html_search_regex(
90 r'<strong>Favorited</strong>\s+([^<]+)<',
91 webpage, 'like count', fatal=False))
93 upload_date = self._html_search_regex(
94 r'<strong>Uploaded</strong>\s+([^<]+)<', webpage, 'upload date')
95 if 'Ago' in upload_date:
96 days = int(re.search(r'([0-9]+)', upload_date).group(1))
97 upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d')
99 upload_date = unified_strdate(upload_date)
101 comment_count = webpage.count('class="media
-comment
-contents
"')
102 uploader_id = self._html_search_regex(
103 r'"thumb
-member
-username
">\s+<a href="/m
/([^
"]+)"',
104 webpage, 'uploader_id
')
106 categories = self._html_search_meta('keywords
', webpage, default=None)
108 categories = [cat.strip() for cat in categories.split(',')]
113 'upload_date
': upload_date,
114 'uploader_id
': uploader_id,
115 'thumbnail
': self._og_search_thumbnail(webpage),
116 'categories
': categories,
117 'view_count
': view_count,
118 'like_count
': like_count,
119 'comment_count
': comment_count,
120 'age_limit
': age_limit,
125 class MotherlessGroupIE(InfoExtractor):
126 _VALID_URL = r'https?
://(?
:www\
.)?motherless\
.com
/gv?
/(?P
<id>[a
-z0
-9_]+)'
128 'url
': 'http
://motherless
.com
/g
/movie_scenes
',
130 'id': 'movie_scenes
',
131 'title
': 'Movie Scenes
',
132 'description
': 'Hot
and sexy scenes
from "regular" movies
... '
133 'Beautiful actresses fully nude
... A looot of
'
136 'playlist_mincount
': 662,
138 'url
': 'http
://motherless
.com
/gv
/sex_must_be_funny
',
140 'id': 'sex_must_be_funny
',
141 'title
': 'Sex must be funny
',
142 'description
': 'Sex can be funny
. Wide smiles
,laugh
, games
, fun of
'
145 'playlist_mincount
': 9,
149 def suitable(cls, url):
150 return (False if MotherlessIE.suitable(url)
151 else super(MotherlessGroupIE, cls).suitable(url))
153 def _extract_entries(self, webpage, base):
155 for mobj in re.finditer(
156 r'href
="(?P<href>/[^"]+)"[^>]*>(?:\s*<img[^>]+alt="[^
-]+-\
s(?P
<title
>[^
"]+)")?
',
158 video_url = compat_urlparse.urljoin(base, mobj.group('href
'))
159 if not MotherlessIE.suitable(video_url):
161 video_id = MotherlessIE._match_id(video_url)
162 title = mobj.group('title
')
163 entries.append(self.url_result(
164 video_url, ie=MotherlessIE.ie_key(), video_id=video_id,
166 # Alternative fallback
170 compat_urlparse.urljoin(base, '/' + entry_id),
171 ie=MotherlessIE.ie_key(), video_id=entry_id)
172 for entry_id in orderedSet(re.findall(
173 r'data
-codename
=["\']([A-Z0-9]+)', webpage))]
176 def _real_extract(self, url):
177 group_id = self._match_id(url)
178 page_url = compat_urlparse.urljoin(url, '/gv/%s' % group_id)
179 webpage = self._download_webpage(page_url, group_id)
180 title = self._search_regex(
181 r'<title>([\w\s]+\w)\s+-', webpage, 'title', fatal=False)
182 description = self._html_search_meta(
183 'description', webpage, fatal=False)
184 page_count = self._int(self._search_regex(
185 r'(\d+)</(?:a|span)><(?:a|span)[^>]+>\s*NEXT',
186 webpage, 'page_count'), 'page_count')
190 webpage = self._download_webpage(
191 page_url, group_id, query={'page': idx + 1},
192 note='Downloading page %d/%d' % (idx + 1, page_count)
194 for entry in self._extract_entries(webpage, url):
197 playlist = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
203 'description': description,