[ahottie] add aupport (#8710)

docs/supportedsites.md

@@ -85,6 +85,12 @@ Consider all listed sites to potentially be NSFW.
     <td>Posts, Tag Searches</td>
     <td></td>
 </tr>
+<tr id="ahottie" title="ahottie">
+    <td>AHottie</td>
+    <td>https://ahottie.top/</td>
+    <td>Galleries, Search Results, Tag Searches</td>
+    <td></td>
+</tr>
 <tr id="arcalive" title="arcalive">
     <td>Arcalive</td>
     <td>https://arca.live/</td>

gallery_dl/extractor/__init__.py

@@ -23,6 +23,7 @@ modules = [
     "8muses",
     "adultempire",
     "agnph",
+    "ahottie",
     "ao3",
     "arcalive",
     "architizer",

gallery_dl/extractor/ahottie.py

@@ -0,0 +1,102 @@
+# -*- 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://ahottie.top/"""
+
+from .common import Extractor, GalleryExtractor, Message
+from .. import text
+
+BASE_PATTERN = r"(?:https?://)?(?:www\.)?ahottie\.top"
+
+
+class AhottieExtractor(Extractor):
+    """Base class for ahottie extractors"""
+    category = "ahottie"
+    root = "https://ahottie.top"
+
+    def items(self):
+        for album in self.albums():
+            yield Message.Queue, album["url"], album
+
+    def _pagination(self, url, params):
+        params["page"] = text.parse_int(params.get("page"), 1)
+
+        while True:
+            page = self.request(url, params=params).text
+
+            for album in text.extract_iter(
+                    page, '<div class="relative">', '</div>'):
+                yield {
+                    "url"  : text.extr(album, ' href="', '"'),
+                    "title": text.unquote(text.extr(
+                        album, ' alt="', '"')),
+                    "date" : self.parse_datetime_iso(text.extr(
+                        album, ' datetime="', '"')),
+                    "_extractor": AhottieGalleryExtractor,
+                }
+
+            if 'rel="next"' not in page:
+                break
+            params["page"] += 1
+
+
+class AhottieGalleryExtractor(GalleryExtractor, AhottieExtractor):
+    directory_fmt = ("{category}", "{date:%Y-%m-%d} {title} ({gallery_id})")
+    filename_fmt = "{num:>03}.{extension}"
+    archive_fmt = "{gallery_id}_{num}_{filename}"
+    pattern = BASE_PATTERN + r"(/albums/(\w+))"
+    example = "https://ahottie.top/albums/1234567890"
+
+    def metadata(self, page):
+        extr = text.extract_from(page)
+        return {
+            "gallery_id": self.groups[1],
+            "title": text.unescape(extr("<title>", "<").rpartition(" | ")[0]),
+            "date" : self.parse_datetime_iso(extr('datetime="', '"')),
+            "tags" : text.split_html(extr('<i ', '</div>'))[1:],
+        }
+
+    def images(self, page):
+        pos = page.find("<time ") + 1
+        data = {
+            "_http_headers" : {"Referer": None},
+            "_http_validate": self._validate,
+        }
+        return [
+            (url, data)
+            for url in text.extract_iter(page, '" src="', '"', pos)
+        ]
+
+    def _validate(self, response):
+        hget = response.headers.get
+        return not (
+            hget("content-length") == "2421" and
+            hget("content-type") == "image/jpeg"
+        )
+
+
+class AhottieTagExtractor(AhottieExtractor):
+    subcategory = "tag"
+    pattern = BASE_PATTERN + r"/tags/([^/?#]+)"
+    example = "https://ahottie.top/tags/TAG"
+
+    def albums(self):
+        tag = self.groups[0]
+        self.kwdict["search_tags"] = text.unquote(tag)
+        return self._pagination(f"{self.root}/tags/{tag}", {})
+
+
+class AhottieSearchExtractor(AhottieExtractor):
+    subcategory = "search"
+    pattern = BASE_PATTERN + r"/search/?\?([^#]+)"
+    example = "https://ahottie.top/search?kw=QUERY"
+
+    def albums(self):
+        params = text.parse_query(self.groups[0])
+        self.kwdict["search_tags"] = params.get("kw")
+        return self._pagination(f"{self.root}/search", params)

scripts/supportedsites.py

@@ -25,6 +25,7 @@ CATEGORY_MAP = {
     "35photo"        : "35PHOTO",
     "adultempire"    : "Adult Empire",
     "agnph"          : "AGNPH",
+    "ahottie"        : "AHottie",
     "aibooru"        : "AIBooru",
     "allgirlbooru"   : "All girl",
     "ao3"            : "Archive of Our Own",

test/results/ahottie.py

@@ -0,0 +1,55 @@
+# -*- 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 ahottie
+
+
+__tests__ = (
+{
+    "#url"     : "https://ahottie.top/albums/5d54b221c19ff9c9126ffd62859c6603",
+    "#class"   : ahottie.AhottieGalleryExtractor,
+    "#pattern" : r"https://images2\.imgbox\.com/../../\w+_o\.jpg",
+    "#count"   : 10,
+
+    "count"     : 10,
+    "num"       : range(1, 10),
+    "date"      : "dt:2024-12-30 00:00:00",
+    "extension" : "jpg",
+    "filename"  : str,
+    "gallery_id": "5d54b221c19ff9c9126ffd62859c6603",
+    "title"     : "大熊杏優・かれしちゃん, Young Champion 2025 No.02 (ヤングチャンピオン 2025年2号)",
+    "tags"      : [
+        "Ayu Okuma 大熊杏優",
+        "Kareshichan かれしちゃん",
+        "Young Champion ヤングチャンピオン",
+    ],
+},
+
+{
+    "#url"     : "https://ahottie.top/tags/Ayu%20Okuma%20%E5%A4%A7%E7%86%8A%E6%9D%8F%E5%84%AA",
+    "#class"   : ahottie.AhottieTagExtractor,
+    "#pattern" : ahottie.AhottieGalleryExtractor.pattern,
+    "#count"   : 17,
+
+    "date"       : "type:datetime",
+    "search_tags": "Ayu Okuma 大熊杏優",
+    "title"      : str,
+    "url"        : str,
+},
+
+{
+    "#url"     : "https://ahottie.top/search?kw=ayu&page=10",
+    "#class"   : ahottie.AhottieSearchExtractor,
+    "#pattern" : ahottie.AhottieGalleryExtractor.pattern,
+    "#count"   : range(80, 200),
+
+    "date"       : "type:datetime",
+    "search_tags": "ayu",
+    "title"      : str,
+    "url"        : str,
+},
+
+)