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
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
|
# -*- coding: utf-8 -*-
# Copyright 2018-2023 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://idol.sankakucomplex.com/"""
from .sankaku import SankakuExtractor
from .common import Message
from ..cache import cache
from .. import text, util, exception
import collections
import re
BASE_PATTERN = r"(?:https?://)?idol\.sankakucomplex\.com(?:/[a-z]{2})?"
class IdolcomplexExtractor(SankakuExtractor):
"""Base class for idolcomplex extractors"""
category = "idolcomplex"
root = "https://idol.sankakucomplex.com"
cookies_domain = "idol.sankakucomplex.com"
cookies_names = ("_idolcomplex_session",)
referer = False
request_interval = (3.0, 6.0)
def __init__(self, match):
SankakuExtractor.__init__(self, match)
self.logged_in = True
self.start_page = 1
self.start_post = 0
def _init(self):
self.find_pids = re.compile(
r" href=[\"#]/\w\w/posts/([0-9a-f]+)"
).findall
self.find_tags = re.compile(
r'tag-type-([^"]+)">\s*<a [^>]*?href="/[^?]*\?tags=([^"]+)'
).findall
def items(self):
self.login()
data = self.metadata()
for post_id in util.advance(self.post_ids(), self.start_post):
post = self._extract_post(post_id)
url = post["file_url"]
post.update(data)
text.nameext_from_url(url, post)
yield Message.Directory, post
yield Message.Url, url, post
def skip(self, num):
self.start_post += num
return num
def post_ids(self):
"""Return an iterable containing all relevant post ids"""
def login(self):
if self.cookies_check(self.cookies_names):
return
username, password = self._get_auth_info()
if username:
return self.cookies_update(self._login_impl(username, password))
self.logged_in = False
@cache(maxage=90*86400, keyarg=1)
def _login_impl(self, username, password):
self.log.info("Logging in as %s", username)
url = self.root + "/users/login"
page = self.request(url).text
headers = {
"Referer": url,
}
url = self.root + (text.extr(page, '<form action="', '"') or
"/en/user/authenticate")
data = {
"authenticity_token": text.unescape(text.extr(
page, 'name="authenticity_token" value="', '"')),
"url" : "",
"user[name]" : username,
"user[password]": password,
"commit" : "Login",
}
response = self.request(url, method="POST", headers=headers, data=data)
if not response.history or response.url.endswith("/user/home"):
raise exception.AuthenticationError()
return {c.name: c.value for c in response.history[0].cookies}
def _extract_post(self, post_id):
url = self.root + "/posts/" + post_id
page = self.request(url, retries=10).text
extr = text.extract_from(page)
tags = extr("<title>", " | ")
vavg = extr('itemprop="ratingValue">', "<")
vcnt = extr('itemprop="reviewCount">', "<")
pid = extr(">Post ID:", "<")
created = extr(' title="', '"')
file_url = extr('>Original:', 'id=')
if file_url:
file_url = extr(' href="', '"')
width = extr(">", "x")
height = extr("", " ")
else:
width = extr('<object width=', ' ')
height = extr('height=', '>')
file_url = extr('<embed src="', '"')
rating = extr(">Rating:", "<br")
data = {
"id" : text.parse_int(pid),
"md5" : file_url.rpartition("/")[2].partition(".")[0],
"tags" : text.unescape(tags),
"vote_average": text.parse_float(vavg),
"vote_count" : text.parse_int(vcnt),
"created_at" : created,
"date" : text.parse_datetime(
created, "%Y-%m-%d %H:%M:%S.%f"),
"rating" : text.remove_html(rating).lower(),
"file_url" : "https:" + text.unescape(file_url),
"width" : text.parse_int(width),
"height" : text.parse_int(height),
}
tags = collections.defaultdict(list)
tags_list = []
tags_html = text.extr(page, '<ul id="tag-sidebar"', '</ul>')
for tag_type, tag_name in self.find_tags(tags_html or ""):
tags[tag_type].append(text.unquote(tag_name))
for key, value in tags.items():
data["tags_" + key] = " ".join(value)
tags_list += value
data["tags"] = " ".join(tags_list)
return data
class IdolcomplexTagExtractor(IdolcomplexExtractor):
"""Extractor for images from idol.sankakucomplex.com by search-tags"""
subcategory = "tag"
directory_fmt = ("{category}", "{search_tags}")
archive_fmt = "t_{search_tags}_{id}"
pattern = BASE_PATTERN + r"/(?:posts/?)?\?([^#]*)"
example = "https://idol.sankakucomplex.com/en/posts?tags=TAGS"
per_page = 20
def __init__(self, match):
IdolcomplexExtractor.__init__(self, match)
query = text.parse_query(match.group(1))
self.tags = text.unquote(query.get("tags", "").replace("+", " "))
self.start_page = text.parse_int(query.get("page"), 1)
self.next = text.parse_int(query.get("next"), 0)
def skip(self, num):
if self.next:
self.start_post += num
else:
pages, posts = divmod(num, self.per_page)
self.start_page += pages
self.start_post += posts
return num
def metadata(self):
if not self.next:
max_page = 50 if self.logged_in else 25
if self.start_page > max_page:
self.log.info("Traversing from page %d to page %d",
max_page, self.start_page)
self.start_post += self.per_page * (self.start_page - max_page)
self.start_page = max_page
tags = self.tags.split()
if not self.logged_in and len(tags) > 4:
raise exception.StopExtraction(
"Non-members can only search up to 4 tags at once")
return {"search_tags": " ".join(tags)}
def post_ids(self):
params = {"tags": self.tags}
if self.next:
params["next"] = self.next
else:
params["page"] = self.start_page
while True:
page = self.request(self.root, params=params, retries=10).text
pos = ((page.find('id="more-popular-posts-link"') + 1) or
(page.find('<span class="thumb') + 1))
yield from self.find_pids(page, pos)
next_url = text.extract(page, 'next-page-url="', '"', pos)[0]
if not next_url:
return
next_params = text.parse_query(text.unescape(text.unescape(
next_url).lstrip("?/")))
if "next" in next_params:
# stop if the same "next" value occurs twice in a row (#265)
if "next" in params and params["next"] == next_params["next"]:
return
next_params["page"] = "2"
params = next_params
class IdolcomplexPoolExtractor(IdolcomplexExtractor):
"""Extractor for image-pools from idol.sankakucomplex.com"""
subcategory = "pool"
directory_fmt = ("{category}", "pool", "{pool}")
archive_fmt = "p_{pool}_{id}"
pattern = BASE_PATTERN + r"/pools?/show/(\d+)"
example = "https://idol.sankakucomplex.com/pools/show/12345"
per_page = 24
def __init__(self, match):
IdolcomplexExtractor.__init__(self, match)
self.pool_id = match.group(1)
def skip(self, num):
pages, posts = divmod(num, self.per_page)
self.start_page += pages
self.start_post += posts
return num
def metadata(self):
return {"pool": self.pool_id}
def post_ids(self):
url = self.root + "/pools/show/" + self.pool_id
params = {"page": self.start_page}
while True:
page = self.request(url, params=params, retries=10).text
pos = page.find('id="pool-show"') + 1
post_ids = self.find_pids(page, pos)
yield from post_ids
if len(post_ids) < self.per_page:
return
params["page"] += 1
class IdolcomplexPostExtractor(IdolcomplexExtractor):
"""Extractor for single images from idol.sankakucomplex.com"""
subcategory = "post"
archive_fmt = "{id}"
pattern = BASE_PATTERN + r"/posts?/(?:show/)?([0-9a-f]+)"
example = "https://idol.sankakucomplex.com/posts/0123456789abcdef"
def __init__(self, match):
IdolcomplexExtractor.__init__(self, match)
self.post_id = match.group(1)
def post_ids(self):
return (self.post_id,)
|
