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
|
# -*- coding: utf-8 -*-
# Copyright 2014-2020 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://danbooru.donmai.us/"""
from .common import Extractor, Message, SharedConfigMixin
from .. import text
import datetime
BASE_PATTERN = (
r"(?:https?://)?"
r"(danbooru|hijiribe|sonohara|safebooru)"
r"\.donmai\.us"
)
class DanbooruExtractor(SharedConfigMixin, Extractor):
"""Base class for danbooru extractors"""
basecategory = "booru"
category = "danbooru"
filename_fmt = "{category}_{id}_{md5}.{extension}"
page_limit = 1000
page_start = None
per_page = 200
def __init__(self, match):
super().__init__(match)
self.root = "https://{}.donmai.us".format(match.group(1))
self.ugoira = self.config("ugoira", False)
self.params = {}
username, api_key = self._get_auth_info()
if username:
self.log.debug("Using HTTP Basic Auth for user '%s'", username)
self.session.auth = (username, api_key)
def skip(self, num):
pages = num // self.per_page
if pages >= self.page_limit:
pages = self.page_limit - 1
self.page_start = pages + 1
return pages * self.per_page
def items(self):
data = self.metadata()
for post in self.posts():
try:
url = post["file_url"]
except KeyError:
continue
text.nameext_from_url(url, post)
if post["extension"] == "zip":
if self.ugoira:
post["frames"] = self.request(
"{}/posts/{}.json?only=pixiv_ugoira_frame_data".format(
self.root, post["id"])
).json()["pixiv_ugoira_frame_data"]["data"]
else:
url = post["large_file_url"]
post["extension"] = "webm"
post.update(data)
yield Message.Directory, post
yield Message.Url, url, post
def metadata(self):
return {}
def posts(self):
return self._pagination(self.root + "/posts.json")
def _pagination(self, url, pagenum=False):
params = self.params.copy()
params["limit"] = self.per_page
params["page"] = self.page_start
while True:
posts = self.request(url, params=params).json()
if "posts" in posts:
posts = posts["posts"]
yield from posts
if len(posts) < self.per_page:
return
if pagenum:
params["page"] += 1
else:
for post in reversed(posts):
if "id" in post:
params["page"] = "b{}".format(post["id"])
break
else:
return
class DanbooruTagExtractor(DanbooruExtractor):
"""Extractor for danbooru posts from tag searches"""
subcategory = "tag"
directory_fmt = ("{category}", "{search_tags}")
archive_fmt = "t_{search_tags}_{id}"
pattern = BASE_PATTERN + r"/posts\?(?:[^&#]*&)*tags=([^&#]+)"
test = (
("https://danbooru.donmai.us/posts?tags=bonocho", {
"content": "b196fb9f1668109d7774a0a82efea3ffdda07746",
}),
# test page transitions
("https://danbooru.donmai.us/posts?tags=mushishi", {
"count": ">= 300",
}),
("https://hijiribe.donmai.us/posts?tags=bonocho"),
("https://sonohara.donmai.us/posts?tags=bonocho"),
("https://safebooru.donmai.us/posts?tags=bonocho"),
)
def __init__(self, match):
super().__init__(match)
self.params["tags"] = text.unquote(match.group(2).replace("+", " "))
def metadata(self):
return {"search_tags": self.params["tags"]}
class DanbooruPoolExtractor(DanbooruExtractor):
"""Extractor for posts from danbooru pools"""
subcategory = "pool"
directory_fmt = ("{category}", "pool", "{pool[id]} {pool[name]}")
archive_fmt = "p_{pool[id]}_{id}"
pattern = BASE_PATTERN + r"/pools/(\d+)"
test = ("https://danbooru.donmai.us/pools/7659", {
"content": "b16bab12bea5f7ea9e0a836bf8045f280e113d99",
})
def __init__(self, match):
super().__init__(match)
self.pool_id = match.group(2)
self.params["tags"] = "pool:" + self.pool_id
def metadata(self):
url = "{}/pools/{}.json".format(self.root, self.pool_id)
pool = self.request(url).json()
pool["name"] = pool["name"].replace("_", " ")
del pool["post_ids"]
return {"pool": pool}
class DanbooruPostExtractor(DanbooruExtractor):
"""Extractor for single danbooru posts"""
subcategory = "post"
archive_fmt = "{id}"
pattern = BASE_PATTERN + r"/posts/(\d+)"
test = (
("https://danbooru.donmai.us/posts/294929", {
"content": "5e255713cbf0a8e0801dc423563c34d896bb9229",
}),
("https://danbooru.donmai.us/posts/3613024", {
"pattern": r"https?://.+\.zip$",
"options": (("ugoira", True),)
})
)
def __init__(self, match):
super().__init__(match)
self.post_id = match.group(2)
def posts(self):
url = "{}/posts/{}.json".format(self.root, self.post_id)
post = self.request(url).json()
return (post["post"] if "post" in post else post,)
class DanbooruPopularExtractor(DanbooruExtractor):
"""Extractor for popular images from danbooru"""
subcategory = "popular"
directory_fmt = ("{category}", "popular", "{scale}", "{date}")
archive_fmt = "P_{scale[0]}_{date}_{id}"
pattern = BASE_PATTERN + r"/explore/posts/popular(?:\?([^#]*))?"
test = (
("https://danbooru.donmai.us/explore/posts/popular"),
(("https://danbooru.donmai.us/explore/posts/popular"
"?date=2013-06-06&scale=week"), {
"range": "1-120",
"count": 120,
}),
)
def __init__(self, match):
super().__init__(match)
self.params.update(text.parse_query(match.group(2)))
def metadata(self):
self.page_start = self.page_start or 1
scale = self.params.get("scale", "day")
date = self.params.get("date") or datetime.date.today().isoformat()
if scale == "week":
date = datetime.date.fromisoformat(date)
date = (date - datetime.timedelta(days=date.weekday())).isoformat()
elif scale == "month":
date = date[:-3]
return {"date": date, "scale": scale}
def posts(self):
url = self.root + "/explore/posts/popular.json"
return self._pagination(url, True)
|
