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
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
|
# -*- coding: utf-8 -*-
# Copyright 2024-2025 Mike Fährmann
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation.
"""Extractors for https://motherless.com/"""
from .common import Extractor, Message
from .. import text, dt, exception
from ..cache import memcache
BASE_PATTERN = r"(?:https?://)?motherless\.com"
class MotherlessExtractor(Extractor):
"""Base class for motherless extractors"""
category = "motherless"
root = "https://motherless.com"
filename_fmt = "{id} {title}.{extension}"
archive_fmt = "{id}"
def request(self, url, **kwargs):
response = Extractor.request(self, url, **kwargs)
content = response.content
if (b'<div class="error-page' in content or
b">The page you're looking for cannot be found.<" in content):
raise exception.NotFoundError("page")
self.request = Extractor.request.__get__(self)
return response
def _extract_media(self, path):
url = f"{self.root}/{path}"
page = self.request(url).text
extr = text.extract_from(page)
path, _, media_id = path.rpartition("/")
data = {
"id" : media_id,
"title": text.unescape(
(t := extr("<title>", "<")) and t[:t.rfind(" | ")]),
"type" : extr("__mediatype = '", "'"),
"group": extr("__group = '", "'"),
"url" : extr("__fileurl = '", "'"),
"tags" : [
text.unescape(tag)
for tag in text.extract_iter(
extr('class="media-meta-tags">', "</div>"), ">#", "<")
],
"views": text.parse_int(extr(
'class="count">', " ").replace(",", "")),
"favorites": text.parse_int(extr(
'class="count">', " ").replace(",", "")),
"date" : self._parse_datetime(extr('class="count">', "<")),
"uploader": text.unescape(extr('class="username">', "<").strip()),
}
if not path:
pass
elif path[0] == "G":
data["gallery_id"] = path[1:]
data["gallery_title"] = self._extract_gallery_title(
page, data["gallery_id"])
elif path[0] == "g":
data["group_id"] = path[2:]
data["group_title"] = self._extract_group_title(
page, data["group_id"])
return data
def _pagination(self, page):
while True:
for thumb in text.extract_iter(
page, 'class="thumb-container', "</div>"):
yield thumb
url = text.extr(page, '<link rel="next" href="', '"')
if not url:
return
page = self.request(text.unescape(url)).text
def _extract_data(self, page, category):
extr = text.extract_from(page)
gid = self.groups[-1]
if category == "gallery":
title = self._extract_gallery_title(page, gid)
else:
title = self._extract_group_title(page, gid)
return {
category + "_id": gid,
category + "_title": title,
"uploader": text.remove_html(extr(
f'class="{category}-member-username">', "</")),
"count": text.parse_int(
extr('<span class="active">', ")")
.rpartition("(")[2].replace(",", "")),
}
def _parse_thumb_data(self, thumb):
extr = text.extract_from(thumb)
data = {
"id" : extr('data-codename="', '"'),
"type" : extr('data-mediatype="', '"'),
"thumbnail": extr('class="static" src="', '"'),
"title" : extr(' alt="', '"'),
}
data["url"] = data["thumbnail"].replace("thumb", data["type"])
return data
def _parse_datetime(self, dt_string):
if " ago" not in dt_string:
return dt.parse(dt_string, "%d %b %Y")
value = text.parse_int(dt_string[:-5])
delta = (dt.timedelta(0, value*3600) if dt_string[-5] == "h" else
dt.timedelta(value))
return (dt.now() - delta).replace(hour=0, minute=0, second=0)
@memcache(keyarg=2)
def _extract_gallery_title(self, page, gallery_id):
title = text.extr(
text.extr(page, '<h1 class="content-title">', "</h1>"),
"From the gallery:", "<")
if title:
return text.unescape(title.strip())
if f' href="/G{gallery_id}"' in page:
return text.unescape(
(t := text.extr(page, "<title>", "<")) and t[:t.rfind(" | ")])
return ""
@memcache(keyarg=2)
def _extract_group_title(self, page, group_id):
title = text.extr(
text.extr(page, '<h1 class="group-bio-name">', "</h1>"),
">", "<")
if title:
return text.unescape(title.strip())
return ""
class MotherlessMediaExtractor(MotherlessExtractor):
"""Extractor for a single image/video from motherless.com"""
subcategory = "media"
pattern = (BASE_PATTERN +
r"/((?:g/[^/?#]+/|G[IV]?[A-Z0-9]+/)?"
r"(?!G)[A-Z0-9]+)")
example = "https://motherless.com/ABC123"
def items(self):
file = self._extract_media(self.groups[0])
url = file["url"]
yield Message.Directory, "", file
yield Message.Url, url, text.nameext_from_url(url, file)
class MotherlessGalleryExtractor(MotherlessExtractor):
"""Extractor for a motherless.com gallery"""
subcategory = "gallery"
directory_fmt = ("{category}", "{uploader}",
"{gallery_id} {gallery_title}")
archive_fmt = "{gallery_id}_{id}"
pattern = BASE_PATTERN + "/G([IVG])?([A-Z0-9]+)/?$"
example = "https://motherless.com/GABC123"
def items(self):
type, gid = self.groups
if not type:
data = {"_extractor": MotherlessGalleryExtractor}
yield Message.Queue, f"{self.root}/GI{gid}", data
yield Message.Queue, f"{self.root}/GV{gid}", data
return
url = f"{self.root}/G{type}{gid}"
page = self.request(url).text
data = self._extract_data(page, "gallery")
for num, thumb in enumerate(self._pagination(page), 1):
file = self._parse_thumb_data(thumb)
thumbnail = file["thumbnail"]
if file["type"] == "video":
file = self._extract_media(file["id"])
file.update(data)
file["num"] = num
file["thumbnail"] = thumbnail
url = file["url"]
yield Message.Directory, "", file
yield Message.Url, url, text.nameext_from_url(url, file)
class MotherlessGroupExtractor(MotherlessExtractor):
subcategory = "group"
directory_fmt = ("{category}", "{uploader}",
"{group_id} {group_title}")
archive_fmt = "{group_id}_{id}"
pattern = BASE_PATTERN + "/g([iv]?)/?([a-z0-9_]+)/?$"
example = "https://motherless.com/g/abc123"
def items(self):
type, gid = self.groups
if not type:
data = {"_extractor": MotherlessGroupExtractor}
yield Message.Queue, f"{self.root}/gi/{gid}", data
yield Message.Queue, f"{self.root}/gv/{gid}", data
return
url = f"{self.root}/g{type}/{gid}"
page = self.request(url).text
data = self._extract_data(page, "group")
for num, thumb in enumerate(self._pagination(page), 1):
file = self._parse_thumb_data(thumb)
thumbnail = file["thumbnail"]
file = self._extract_media(file["id"])
uploader = file.get("uploader")
file.update(data)
file["num"] = num
file["thumbnail"] = thumbnail
file["uploader"] = uploader
file["group"] = file["group_id"]
url = file["url"]
yield Message.Directory, "", file
yield Message.Url, url, text.nameext_from_url(url, file)
|
