[xfolio] add initial support (#5514, #6351, #6837)

docs/configuration.rst

@@ -401,6 +401,7 @@ Default
         ``urlgalleries``,
         ``vk``,
         ``weebcentral``,
+        ``xfolio``,
         ``zerochan``
     * ``"1.0-2.0"``
         ``flickr``,

docs/gallery-dl.conf

@@ -702,6 +702,10 @@
         {
             "sleep-request": "0.5-1.5"
         },
+        "xfolio":
+        {
+            "sleep-request": "0.5-1.5"
+        },
         "weibo":
         {
             "sleep-request": "1.0-2.0",
@@ -923,7 +927,7 @@
             "config-file"    : null,
             "enabled"        : true,
             "format"         : null,
-            "forward-cookies": false,
+            "forward-cookies": true,
             "logging"        : true,
             "module"         : null,
             "outtmpl"        : null,

docs/supportedsites.md

@@ -1081,6 +1081,12 @@ Consider all listed sites to potentially be NSFW.
     <td>Galleries</td>
     <td></td>
 </tr>
+<tr>
+    <td>Xfolio</td>
+    <td>https://xfolio.jp/</td>
+    <td>Series, User Profiles, Works</td>
+    <td></td>
+</tr>
 <tr>
     <td>xHamster</td>
     <td>https://xhamster.com/</td>

gallery_dl/extractor/__init__.py

@@ -195,6 +195,7 @@
     "wikiart",
     "wikifeet",
     "wikimedia",
+    "xfolio",
     "xhamster",
     "xvideos",
     "yiffverse",

gallery_dl/extractor/xfolio.py

@@ -0,0 +1,146 @@
+# -*- 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.StopExtraction("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"
+    ref_fmt = ("{}/fullscale_image?image_id={}&work_id={}")
+    url_fmt = ("{}/user_asset.php?id={}&work_id={}"
+               "&work_image_id={}&type=work_image")
+
+    def items(self):
+        creator, work_id = self.groups
+        url = "{}/portfolio/{}/works/{}".format(self.root, creator, 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": self.url_fmt.format(
+                    self.root, image_id, work_id, image_id),
+                "_http_headers": {"Referer": self.ref_fmt.format(
+                    self.root, image_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 = "{}/portfolio/{}/works".format(self.root, self.groups[0])
+
+        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 = "{}/portfolio/{}/series/{}".format(self.root, creator, series_id)
+        html = self.request(url).text
+
+        return [
+            text.extr(item, ' href="', '"')
+            for item in text.extract_iter(
+                html, 'class="listWrap--title">', "</a>")
+        ]

test/results/xfolio.py

@@ -0,0 +1,88 @@
+# -*- coding: utf-8 -*-
+
+# 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.
+
+from gallery_dl.extractor import xfolio
+from gallery_dl import exception
+
+
+__tests__ = (
+{
+    "#url"     : "https://xfolio.jp/portfolio/yutakashii/works/23977",
+    "#class"   : xfolio.XfolioWorkExtractor,
+    "#urls"    : (
+        "https://xfolio.jp/user_asset.php?id=113179&work_id=23977&work_image_id=113179&type=work_image",
+        "https://xfolio.jp/user_asset.php?id=113182&work_id=23977&work_image_id=113182&type=work_image",
+        "https://xfolio.jp/user_asset.php?id=113185&work_id=23977&work_image_id=113185&type=work_image",
+        "https://xfolio.jp/user_asset.php?id=113188&work_id=23977&work_image_id=113188&type=work_image",
+        "https://xfolio.jp/user_asset.php?id=113191&work_id=23977&work_image_id=113191&type=work_image",
+        "https://xfolio.jp/user_asset.php?id=113194&work_id=23977&work_image_id=113194&type=work_image",
+        "https://xfolio.jp/user_asset.php?id=113197&work_id=23977&work_image_id=113197&type=work_image",
+        "https://xfolio.jp/user_asset.php?id=113200&work_id=23977&work_image_id=113200&type=work_image",
+        "https://xfolio.jp/user_asset.php?id=113203&work_id=23977&work_image_id=113203&type=work_image",
+    ),
+
+    "count"          : 9,
+    "num"            : range(1, 9),
+    "creator_id"     : "1495",
+    "creator_name"   : "香椎ゆたか",
+    "creator_profile": "連載中：「いつまでも可愛くしてると思うなよ！」 https://booklive.jp/product/index/title_id/10003104/vol_no/001\r\n 過去作：「まじとら！」「男友達ガール」\r\npixiv：http://pixiv.me/yutakashii\r\nskeb：http://skeb.jp/@yutakashii",
+    "creator_slug"   : "yutakashii",
+    "creator_userid" : "3778",
+    "description"    : "BookLive NINOにて「男友達ガール」連載開始しました。ルームシェア＋TSFで、ある日突然同居人が可愛い女の子になったら…という感じのラブ(？)コメディ...",
+    "extension"      : "jpg",
+    "image_id"       : r"re:113\d\d\d",
+    "series_id"      : "",
+    "title"          : "新連載「男友達ガール」冒頭試し読み",
+    "url"            : str,
+    "work_id"        : "23977",
+},
+
+{
+    "#url"     : "https://xfolio.jp/portfolio/yutakashii",
+    "#class"   : xfolio.XfolioUserExtractor,
+    "#pattern" : xfolio.XfolioWorkExtractor.pattern,
+    "#count"   : range(50, 100),
+},
+
+{
+    "#url"     : "https://xfolio.jp/portfolio/yutakashii/works",
+    "#class"   : xfolio.XfolioUserExtractor,
+},
+{
+    "#url"     : "https://xfolio.jp/portfolio/yutakashii/works?page=3",
+    "#class"   : xfolio.XfolioUserExtractor,
+},
+{
+    "#url"     : "https://xfolio.jp/en/portfolio/yutakashii",
+    "#class"   : xfolio.XfolioUserExtractor,
+},
+{
+    "#url"     : "https://xfolio.jp/ko/portfolio/yutakashii",
+    "#class"   : xfolio.XfolioUserExtractor,
+},
+{
+    "#url"     : "https://xfolio.jp/zh-CN/portfolio/yutakashii",
+    "#class"   : xfolio.XfolioUserExtractor,
+},
+
+{
+    "#url"      : "https://xfolio.jp/portfolio/donguri/series/1391402",
+    "#class"    : xfolio.XfolioSeriesExtractor,
+    "#auth"     : False,
+    "#exception": exception.StopExtraction,
+},
+
+{
+    "#url"     : "https://xfolio.jp/portfolio/donguri/series/1391402",
+    "#class"   : xfolio.XfolioSeriesExtractor,
+    "#auth"    : True,
+    "#urls"    : (
+        "https://xfolio.jp/portfolio/donguri/works/2472402",
+        "https://xfolio.jp/portfolio/donguri/works/2470700",
+    ),
+},
+
+)