[hdoujin] add support (#6810)

gallery_dl/extractor/__init__.py

@@ -73,6 +73,7 @@ modules = [
     "girlswithmuscle",
     "gofile",
     "hatenablog",
+    "hdoujin",
     "hentai2read",
     "hentaicosplays",
     "hentaifoundry",

gallery_dl/extractor/hdoujin.py

@@ -0,0 +1,42 @@
+# -*- 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://hdoujin.org/"""
+
+from . import schalenetwork
+
+BASE_PATTERN = r"(?:https?://)?(?:www\.)?(hdoujin\.(?:org|net))"
+
+
+class HdoujinBase():
+    """Base class for hdoujin extractors"""
+    category = "hdoujin"
+    root = "https://hdoujin.org"
+    root_api = "https://api.hdoujin.org"
+    root_auth = "https://auth.hdoujin.org"
+
+
+class HdoujinGalleryExtractor(
+        HdoujinBase, schalenetwork.SchalenetworkGalleryExtractor):
+    pattern = rf"{BASE_PATTERN}/(?:g|reader)/(\d+)/(\w+)"
+    example = "https://hdoujin.org/g/12345/67890abcdef/"
+
+
+class HdoujinSearchExtractor(
+        HdoujinBase, schalenetwork.SchalenetworkSearchExtractor):
+    pattern = rf"{BASE_PATTERN}/(?:tag/([^/?#]+)|browse)?(?:/?\?([^#]*))?$"
+    example = "https://hdoujin.org/browse?s=QUERY"
+
+
+class HdoujinFavoriteExtractor(
+        HdoujinBase, schalenetwork.SchalenetworkFavoriteExtractor):
+    pattern = rf"{BASE_PATTERN}/favorites(?:\?([^#]*))?"
+    example = "https://hdoujin.org/favorites"
+
+
+HdoujinBase.extr_class = HdoujinGalleryExtractor

gallery_dl/extractor/schalenetwork.py

@@ -27,6 +27,7 @@ class SchalenetworkExtractor(Extractor):
     root = "https://niyaniya.moe"
     root_api = "https://api.schale.network"
     root_auth = "https://auth.schale.network"
+    extr_class = None
     request_interval = (0.5, 1.5)
 
     def _init(self):
@@ -38,6 +39,7 @@ class SchalenetworkExtractor(Extractor):
 
     def _pagination(self, endpoint, params):
         url_api = self.root_api + endpoint
+        cls = self.extr_class
 
         while True:
             data = self.request_json(
@@ -50,7 +52,7 @@ class SchalenetworkExtractor(Extractor):
 
             for entry in entries:
                 url = f"{self.root}/g/{entry['id']}/{entry['key']}"
-                entry["_extractor"] = SchalenetworkGalleryExtractor
+                entry["_extractor"] = cls
                 yield Message.Queue, url, entry
 
             try:
@@ -236,3 +238,6 @@ class SchalenetworkFavoriteExtractor(SchalenetworkExtractor):
         params["page"] = text.parse_int(params.get("page"), 1)
         self.headers["Authorization"] = self._token()
         return self._pagination(f"/books/favorites?crt={self._crt()}", params)
+
+
+SchalenetworkExtractor.extr_class = SchalenetworkGalleryExtractor