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
|
# -*- coding: utf-8 -*-
# Copyright 2022-2023 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://itaku.ee/"""
from .common import Extractor, Message
from ..cache import memcache
from .. import text
BASE_PATTERN = r"(?:https?://)?itaku\.ee"
class ItakuExtractor(Extractor):
"""Base class for itaku extractors"""
category = "itaku"
root = "https://itaku.ee"
directory_fmt = ("{category}", "{owner_username}")
filename_fmt = ("{id}{title:? //}.{extension}")
archive_fmt = "{id}"
request_interval = (0.5, 1.5)
def _init(self):
self.api = ItakuAPI(self)
self.videos = self.config("videos", True)
def items(self):
for post in self.posts():
post["date"] = text.parse_datetime(
post["date_added"], "%Y-%m-%dT%H:%M:%S.%fZ")
for category, tags in post.pop("categorized_tags").items():
post["tags_" + category.lower()] = [t["name"] for t in tags]
post["tags"] = [t["name"] for t in post["tags"]]
sections = []
for s in post["sections"]:
group = s["group"]
if group:
sections.append(group["title"] + "/" + s["title"])
else:
sections.append(s["title"])
post["sections"] = sections
if post["video"] and self.videos:
url = post["video"]["video"]
else:
url = post["image"]
yield Message.Directory, post
yield Message.Url, url, text.nameext_from_url(url, post)
class ItakuGalleryExtractor(ItakuExtractor):
"""Extractor for posts from an itaku user gallery"""
subcategory = "gallery"
pattern = BASE_PATTERN + r"/profile/([^/?#]+)/gallery(?:/(\d+))?"
example = "https://itaku.ee/profile/USER/gallery"
def posts(self):
return self.api.galleries_images(*self.groups)
class ItakuStarsExtractor(ItakuExtractor):
subcategory = "stars"
pattern = BASE_PATTERN + r"/profile/([^/?#]+)/stars(?:/(\d+))?"
example = "https://itaku.ee/profile/USER/stars"
def posts(self):
return self.api.galleries_images_starred(*self.groups)
class ItakuImageExtractor(ItakuExtractor):
subcategory = "image"
pattern = BASE_PATTERN + r"/images/(\d+)"
example = "https://itaku.ee/images/12345"
def posts(self):
return (self.api.image(self.groups[0]),)
class ItakuSearchExtractor(ItakuExtractor):
subcategory = "search"
pattern = BASE_PATTERN + r"/home/images/?\?([^#]+)"
example = "https://itaku.ee/home/images?tags=SEARCH"
def posts(self):
params = text.parse_query_list(
self.groups[0], {"tags", "maturity_rating"})
return self.api.search_images(params)
class ItakuAPI():
def __init__(self, extractor):
self.extractor = extractor
self.root = extractor.root + "/api"
self.headers = {
"Accept": "application/json, text/plain, */*",
}
def search_images(self, params):
endpoint = "/galleries/images/"
required_tags = []
negative_tags = []
optional_tags = []
for tag in params.pop("tags", None) or ():
if not tag:
pass
elif tag[0] == "-":
negative_tags.append(tag[1:])
elif tag[0] == "~":
optional_tags.append(tag[1:])
else:
required_tags.append(tag)
api_params = {
"required_tags": required_tags,
"negative_tags": negative_tags,
"optional_tags": optional_tags,
"date_range": "",
"maturity_rating": ("SFW", "Questionable", "NSFW"),
"ordering" : "-date_added",
"page" : "1",
"page_size" : "30",
"visibility": ("PUBLIC", "PROFILE_ONLY"),
}
api_params.update(params)
return self._pagination(endpoint, api_params, self.image)
def galleries_images(self, username, section=None):
endpoint = "/galleries/images/"
params = {
"cursor" : None,
"owner" : self.user(username)["owner"],
"sections" : section,
"date_range": "",
"maturity_rating": ("SFW", "Questionable", "NSFW"),
"ordering" : "-date_added",
"page" : "1",
"page_size" : "30",
"visibility": ("PUBLIC", "PROFILE_ONLY"),
}
return self._pagination(endpoint, params, self.image)
def galleries_images_starred(self, username, section=None):
endpoint = "/galleries/images/user_starred_imgs/"
params = {
"cursor" : None,
"stars_of" : self.user(username)["owner"],
"sections" : section,
"date_range": "",
"ordering" : "-date_added",
"maturity_rating": ("SFW", "Questionable", "NSFW"),
"page" : "1",
"page_size" : "30",
"visibility": ("PUBLIC", "PROFILE_ONLY"),
}
return self._pagination(endpoint, params, self.image)
def image(self, image_id):
endpoint = "/galleries/images/{}/".format(image_id)
return self._call(endpoint)
@memcache(keyarg=1)
def user(self, username):
return self._call("/user_profiles/{}/".format(username))
def _call(self, endpoint, params=None):
if not endpoint.startswith("http"):
endpoint = self.root + endpoint
response = self.extractor.request(
endpoint, params=params, headers=self.headers)
return response.json()
def _pagination(self, endpoint, params, extend):
data = self._call(endpoint, params)
while True:
if extend:
for result in data["results"]:
yield extend(result["id"])
else:
yield from data["results"]
url_next = data["links"].get("next")
if not url_next:
return
data = self._call(url_next)
|
