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
240
241
242
243
|
# -*- coding: utf-8 -*-
# Copyright 2015-2020 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.
"""Base classes for extractors for danbooru and co"""
from .common import Extractor, Message, SharedConfigMixin
from .. import text, exception
from xml.etree import ElementTree
import collections
import datetime
import operator
import re
class BooruExtractor(SharedConfigMixin, Extractor):
"""Base class for all booru extractors"""
basecategory = "booru"
filename_fmt = "{category}_{id}_{md5}.{extension}"
api_url = ""
post_url = ""
per_page = 50
page_start = 1
page_limit = None
sort = False
def __init__(self, match):
super().__init__(match)
self.params = {}
self.extags = self.post_url and self.config("tags", False)
def skip(self, num):
pages = num // self.per_page
if self.page_limit and pages + self.page_start > self.page_limit:
pages = self.page_limit - self.page_start
self.page_start += pages
return pages * self.per_page
def items(self):
yield Message.Version, 1
data = self.get_metadata()
self.reset_page()
while True:
images = self.parse_response(
self.request(self.api_url, params=self.params))
for image in images:
try:
url = image["file_url"]
except KeyError:
continue
if url.startswith("/"):
url = text.urljoin(self.api_url, url)
image.update(data)
text.nameext_from_url(url, image)
if self.extags:
self.extended_tags(image)
yield Message.Directory, image
yield Message.Url, url, image
if len(images) < self.per_page:
return
self.update_page(image)
def reset_page(self):
"""Initialize params to point to the first page"""
self.params["page"] = self.page_start
def update_page(self, data):
"""Update params to point to the next page"""
def parse_response(self, response):
"""Parse JSON API response"""
images = response.json()
if self.sort:
images.sort(key=operator.itemgetter("score", "id"),
reverse=True)
return images
def get_metadata(self):
"""Collect metadata for extractor-job"""
return {}
def extended_tags(self, image, page=None):
"""Retrieve extended tag information"""
if not page:
url = self.post_url.format(image["id"])
page = self.request(url).text
tags = collections.defaultdict(list)
tags_html = text.extract(page, '<ul id="tag-', '</ul>')[0]
pattern = re.compile(r"tag-type-([^\"' ]+).*?[?;]tags=([^\"']+)", re.S)
for tag_type, tag_name in pattern.findall(tags_html or ""):
tags[tag_type].append(text.unquote(tag_name))
for key, value in tags.items():
image["tags_" + key] = " ".join(value)
class XmlParserMixin():
"""Mixin for XML based API responses"""
def parse_response(self, response):
root = ElementTree.fromstring(response.text)
return [post.attrib for post in root]
class MoebooruPageMixin():
"""Pagination for Moebooru and Danbooru v1"""
def update_page(self, data):
if self.page_limit:
self.params["page"] = None
self.params["before_id"] = data["id"]
else:
self.params["page"] += 1
class GelbooruPageMixin():
"""Pagination for Gelbooru-like sites"""
page_start = 0
def reset_page(self):
self.params["pid"] = self.page_start
def update_page(self, data):
self.params["pid"] += 1
class TagMixin():
"""Extraction of images based on search-tags"""
subcategory = "tag"
directory_fmt = ("{category}", "{search_tags}")
archive_fmt = "t_{search_tags}_{id}"
def __init__(self, match):
super().__init__(match)
self.tags = text.unquote(match.group("tags").replace("+", " "))
self.params["tags"] = self.tags
self.params["limit"] = self.per_page
def get_metadata(self):
return {"search_tags": self.tags}
class PoolMixin():
"""Extraction of image-pools"""
subcategory = "pool"
directory_fmt = ("{category}", "pool", "{pool}")
archive_fmt = "p_{pool}_{id}"
def __init__(self, match):
super().__init__(match)
self.pool = match.group("pool")
self.params["tags"] = "pool:" + self.pool
self.params["limit"] = self.per_page
def get_metadata(self):
return {"pool": text.parse_int(self.pool)}
class GelbooruPoolMixin(PoolMixin):
"""Image-pool extraction for Gelbooru-like sites"""
per_page = 1
def get_metadata(self):
page = self.request(self.pool_url.format(self.pool)).text
name, pos = text.extract(page, "<h3>Now Viewing: ", "</h3>")
if not name:
name, pos = text.extract(page, "<h4>Pool: ", "</h4>")
if not name:
raise exception.NotFoundError("pool")
self.posts = list(text.extract_iter(
page, 'class="thumb" id="p', '"', pos))
return {
"pool": text.parse_int(self.pool),
"pool_name": text.unescape(name),
"count": len(self.posts),
}
def reset_page(self):
self.index = self.page_start
self.update_page(None)
def update_page(self, data):
try:
post = self.posts[self.index]
self.index += 1
except IndexError:
post = "0"
self.params["tags"] = "id:" + post
class PostMixin():
"""Extraction of a single image-post"""
subcategory = "post"
archive_fmt = "{id}"
def __init__(self, match):
super().__init__(match)
self.post = match.group("post")
self.params["tags"] = "id:" + self.post
class MoebooruPopularMixin():
"""Extraction and metadata handling for Moebooru and Danbooru v1"""
subcategory = "popular"
directory_fmt = ("{category}", "popular", "{scale}", "{date}")
archive_fmt = "P_{scale[0]}_{date}_{id}"
page_start = None
sort = True
def __init__(self, match):
super().__init__(match)
self.params.update(text.parse_query(match.group("query")))
self.scale = match.group("scale")
def get_metadata(self, fmt="%Y-%m-%d"):
date = self.get_date() or datetime.date.today().isoformat()
scale = self.get_scale() or "day"
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 get_date(self):
if "year" in self.params:
return "{:>04}-{:>02}-{:>02}".format(
self.params["year"],
self.params.get("month", "01"),
self.params.get("day", "01"))
return None
def get_scale(self):
if self.scale and self.scale.startswith("by_"):
return self.scale[3:]
return self.scale
|
