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
|
# -*- coding: utf-8 -*-
# Copyright 2025 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://xfolio.jp/"""
from .common import Extractor, Message
from .. import text, exception
BASE_PATTERN = r"(?:https?://)?xfolio\.jp(?:/[^/?#]+)?"
class XfolioExtractor(Extractor):
"""Base class for xfolio extractors"""
category = "xfolio"
root = "https://xfolio.jp"
cookies_domain = ".xfolio.jp"
directory_fmt = ("{category}", "{creator_slug}", "{work_id}")
filename_fmt = "{work_id}_{image_id}.{extension}"
archive_fmt = "{work_id}_{image_id}"
request_interval = (0.5, 1.5)
def _init(self):
XfolioExtractor._init = Extractor._init
if not self.cookies_check(("xfolio_session",)):
self.log.error("'xfolio_session' cookie required")
def items(self):
data = {"_extractor": XfolioWorkExtractor}
for work in self.works():
yield Message.Queue, work, data
def request(self, url, **kwargs):
response = Extractor.request(self, url, **kwargs)
if "/system/recaptcha" in response.url:
raise exception.AbortExtraction("Bot check / CAPTCHA page")
return response
class XfolioWorkExtractor(XfolioExtractor):
subcategory = "work"
pattern = BASE_PATTERN + r"/portfolio/([^/?#]+)/works/(\d+)"
example = "https://xfolio.jp/portfolio/USER/works/12345"
def items(self):
creator, work_id = self.groups
url = f"{self.root}/portfolio/{creator}/works/{work_id}"
html = self.request(url).text
work = self._extract_data(html)
files = self._extract_files(html, work)
work["count"] = len(files)
yield Message.Directory, "", work
for work["num"], file in enumerate(files, 1):
file.update(work)
yield Message.Url, file["url"], file
def _extract_data(self, html):
creator, work_id = self.groups
extr = text.extract_from(html)
return {
"title" : text.unescape(extr(
'property="og:title" content="', '"').rpartition(" - ")[0]),
"description" : text.unescape(extr(
'property="og:description" content="', '"')),
"creator_id" : extr(' data-creator-id="', '"'),
"creator_userid" : extr(' data-creator-user-id="', '"'),
"creator_name" : extr(' data-creator-name="', '"'),
"creator_profile": text.unescape(extr(
' data-creator-profile="', '"')),
"series_id" : extr("/series/", '"'),
"creator_slug" : creator,
"work_id" : work_id,
}
def _extract_files(self, html, work):
files = []
work_id = work["work_id"]
for img in text.extract_iter(
html, 'class="article__wrap_img', "</div>"):
image_id = text.extr(img, "/fullscale_image?image_id=", "&")
if not image_id:
self.log.warning(
"%s: 'fullscale_image' not available", work_id)
continue
files.append({
"image_id" : image_id,
"extension": "jpg",
"url": (f"{self.root}/user_asset.php?id={image_id}&work_id="
f"{work_id}&work_image_id={image_id}&type=work_image"),
"_http_headers": {"Referer": (
f"{self.root}/fullscale_image"
f"?image_id={image_id}&work_id={work_id}")},
})
return files
class XfolioUserExtractor(XfolioExtractor):
subcategory = "user"
pattern = BASE_PATTERN + r"/portfolio/([^/?#]+)(?:/works)?/?(?:$|\?|#)"
example = "https://xfolio.jp/portfolio/USER"
def works(self):
url = f"{self.root}/portfolio/{self.groups[0]}/works"
while True:
html = self.request(url).text
for item in text.extract_iter(
html, '<div class="postItem', "</div>"):
yield text.extr(item, ' href="', '"')
pager = text.extr(html, ' class="pager__list_next', "</li>")
url = text.extr(pager, ' href="', '"')
if not url:
return
url = text.unescape(url)
class XfolioSeriesExtractor(XfolioExtractor):
subcategory = "series"
pattern = BASE_PATTERN + r"/portfolio/([^/?#]+)/series/(\d+)"
example = "https://xfolio.jp/portfolio/USER/series/12345"
def works(self):
creator, series_id = self.groups
url = f"{self.root}/portfolio/{creator}/series/{series_id}"
html = self.request(url).text
return [
text.extr(item, ' href="', '"')
for item in text.extract_iter(
html, 'class="listWrap--title">', "</a>")
]
|
