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
|
# -*- coding: utf-8 -*-
# Copyright 2020 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://www.furaffinity.net/"""
from .common import Extractor, Message
from .. import text, util
BASE_PATTERN = r"(?:https?://)?(?:www\.|sfw\.)?furaffinity\.net"
class FuraffinityExtractor(Extractor):
"""Base class for furaffinity extractors"""
category = "furaffinity"
directory_fmt = ("{category}", "{user!l}")
filename_fmt = "{id} {title}.{extension}"
archive_fmt = "{id}"
cookiedomain = ".furaffinity.net"
root = "https://www.furaffinity.net"
def __init__(self, match):
Extractor.__init__(self, match)
self.user = match.group(1)
self.offset = 0
def items(self):
for post_id in util.advance(self.posts(), self.offset):
post = self._parse_post(post_id)
if post:
yield Message.Directory, post
yield Message.Url, post["url"], post
def posts(self):
return self._pagination()
def skip(self, num):
self.offset += num
return num
def _parse_post(self, post_id):
url = "{}/view/{}/".format(self.root, post_id)
extr = text.extract_from(self.request(url).text)
title, _, artist = text.unescape(extr(
'property="og:title" content="', '"')).rpartition(" by ")
path = extr('href="//d.facdn.net/', '"')
if not path:
self.log.warning(
"Unable to download post %s (\"%s\")",
post_id, text.remove_html(
extr('System Message', '</section>') or
extr('System Message', '</table>')
)
)
return None
pi = text.parse_int
rh = text.remove_html
data = text.nameext_from_url(path, {
"id" : pi(post_id),
"title" : title,
"artist": artist,
"user" : self.user or artist,
"url" : "https://d.facdn.net/" + path
})
tags = extr('class="tags-row">', '</section>')
if tags:
# new site layout
data["tags"] = text.split_html(tags)
data["description"] = text.unescape(rh(extr(
'class="section-body">', '</div>'), "", ""))
data["views"] = pi(rh(extr('class="views">', '</span>')))
data["favorites"] = pi(rh(extr('class="favorites">', '</span>')))
data["comments"] = pi(rh(extr('class="comments">', '</span>')))
data["rating"] = rh(extr('class="rating">', '</span>'))
data["fa_category"] = rh(extr('>Category</strong>', '</span>'))
data["theme"] = rh(extr('>', '<'))
data["species"] = rh(extr('>Species</strong>', '</div>'))
data["gender"] = rh(extr('>Gender</strong>', '</div>'))
data["width"] = pi(extr("<span>", "x"))
data["height"] = pi(extr("", "p"))
else:
# old site layout
data["fa_category"] = extr("<b>Category:</b>", "<").strip()
data["theme"] = extr("<b>Theme:</b>", "<").strip()
data["species"] = extr("<b>Species:</b>", "<").strip()
data["gender"] = extr("<b>Gender:</b>", "<").strip()
data["favorites"] = pi(extr("<b>Favorites:</b>", "<"))
data["comments"] = pi(extr("<b>Comments:</b>", "<"))
data["views"] = pi(extr("<b>Views:</b>", "<"))
data["width"] = pi(extr("<b>Resolution:</b>", "x"))
data["height"] = pi(extr("", "<"))
data["tags"] = text.split_html(extr(
'id="keywords">', '</div>'))[::2]
data["rating"] = extr('<img alt="', ' ')
data["description"] = text.unescape(text.remove_html(extr(
"</table>", "</table>"), "", ""))
data["date"] = text.parse_timestamp(data["filename"].partition(".")[0])
return data
def _pagination(self):
num = 1
while True:
url = "{}/{}/{}/{}/".format(
self.root, self.subcategory, self.user, num)
page = self.request(url).text
post_id = None
for post_id in text.extract_iter(page, 'id="sid-', '"'):
yield post_id
if not post_id:
return
num += 1
def _pagination_favorites(self):
path = "/favorites/{}/".format(self.user)
while path:
page = self.request(self.root + path).text
yield from text.extract_iter(page, 'id="sid-', '"')
path = text.extract(page, 'right" href="', '"')[0]
class FuraffinityGalleryExtractor(FuraffinityExtractor):
"""Extractor for a furaffinity user's gallery"""
subcategory = "gallery"
pattern = BASE_PATTERN + r"/gallery/([^/?&#]+)"
test = ("https://www.furaffinity.net/gallery/mirlinthloth/", {
"pattern": r"https://d.facdn.net/art/mirlinthloth/\d+/\d+.\w+\.\w+",
"range": "45-50",
"count": 6,
})
class FuraffinityScrapsExtractor(FuraffinityExtractor):
"""Extractor for a furaffinity user's scraps"""
subcategory = "scraps"
directory_fmt = ("{category}", "{user!l}", "Scraps")
pattern = BASE_PATTERN + r"/scraps/([^/?&#]+)"
test = ("https://www.furaffinity.net/scraps/mirlinthloth/", {
"pattern": r"https://d.facdn.net/art/[^/]+(/stories)?/\d+/\d+.\w+.\w+",
"count": ">= 3",
})
class FuraffinityFavoriteExtractor(FuraffinityExtractor):
"""Extractor for a furaffinity user's favorites"""
subcategory = "favorite"
directory_fmt = ("{category}", "{user!l}", "Favorites")
pattern = BASE_PATTERN + r"/favorites/([^/?&#]+)"
test = ("https://www.furaffinity.net/favorites/mirlinthloth/", {
"pattern": r"https://d.facdn.net/art/[^/]+/\d+/\d+.\w+\.\w+",
"range": "45-50",
"count": 6,
})
def posts(self):
return self._pagination_favorites()
class FuraffinityPostExtractor(FuraffinityExtractor):
"""Extractor for individual posts on furaffinity"""
subcategory = "post"
pattern = BASE_PATTERN + r"/(?:view|full)/(\d+)"
test = (
("https://www.furaffinity.net/view/21835115/", {
"url": "eae4ef93d99365c69b31a37561bd800c03d336ad",
"keyword": {
"artist" : "mirlinthloth",
"date" : "dt:2016-11-27 17:24:06",
"description": "A Song made playing the game Cosmic DJ.",
"extension" : "mp3",
"filename" : r"re:\d+\.\w+_dj_fennmink_-_bude_s_4_ever",
"id" : 21835115,
"tags" : list,
"title" : "Bude's 4 Ever",
"url" : "re:https://d.facdn.net/art/mirlinthloth/music",
"user" : "mirlinthloth",
"views" : int,
"favorites" : int,
"comments" : int,
"rating" : "General",
"fa_category": "Music",
"theme" : "All",
"species" : "Unspecified / Any",
"gender" : "Any",
"width" : 120,
"height" : 120,
},
}),
("https://furaffinity.net/view/21835115/"),
("https://sfw.furaffinity.net/view/21835115/"),
("https://www.furaffinity.net/full/21835115/"),
)
def posts(self):
post_id = self.user
self.user = None
return (post_id,)
class FuraffinityUserExtractor(FuraffinityExtractor):
"""Extractor for furaffinity user profiles"""
subcategory = "user"
cookiedomain = None
pattern = BASE_PATTERN + r"/user/([^/?&#]+)"
test = (
("https://www.furaffinity.net/user/mirlinthloth/", {
"pattern": r"/gallery/mirlinthloth/$",
}),
("https://www.furaffinity.net/user/mirlinthloth/", {
"options": (("include", "all"),),
"pattern": r"/(gallery|scraps|favorites)/mirlinthloth/$",
"count": 3,
}),
)
def items(self):
base = "{}/{{}}/{}/".format(self.root, self.user)
return self._dispatch_extractors((
(FuraffinityGalleryExtractor , base.format("gallery")),
(FuraffinityScrapsExtractor , base.format("scraps")),
(FuraffinityFavoriteExtractor, base.format("favorites")),
), ("gallery",))
|
