[hentaiera] add support (#3046 #6952 #7020)

gallery_dl/extractor/__init__.py

@@ -66,6 +66,7 @@ modules = [
     "hatenablog",
     "hentai2read",
     "hentaicosplays",
+    "hentaiera",
     "hentaifoundry",
     "hentaifox",
     "hentaihand",

gallery_dl/extractor/hentaiera.py

@@ -0,0 +1,46 @@
+# -*- 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://hentaiera.com/"""
+
+from . import imhentai
+
+BASE_PATTERN = r"(?:https?://)?(?:www\.)?hentaiera\.com"
+
+
+class HentaieraExtractor():
+    category = "hentaiera"
+    root = "https://hentaiera.com"
+
+
+class HentaieraGalleryExtractor(
+        HentaieraExtractor, imhentai.ImhentaiGalleryExtractor):
+    """Extractor for hentaiera galleries"""
+    pattern = BASE_PATTERN + r"/(?:gallery|view)/(\d+)"
+    example = "https://hentaiera.com/gallery/12345/"
+
+
+class HentaieraTagExtractor(
+        HentaieraExtractor, imhentai.ImhentaiTagExtractor):
+    """Extractor for hentaiera tag searches"""
+    subcategory = "tag"
+    pattern = (BASE_PATTERN + r"(/(?:"
+               r"artist|category|character|group|language|parody|tag"
+               r")/([^/?#]+))")
+    example = "https://hentaiera.com/tag/TAG/"
+
+
+class HentaieraSearchExtractor(
+        HentaieraExtractor, imhentai.ImhentaiSearchExtractor):
+    """Extractor for hentaiera search results"""
+    subcategory = "search"
+    pattern = BASE_PATTERN + r"/search/?\?([^#]+)"
+    example = "https://hentaiera.com/search/?key=QUERY"
+
+
+HentaieraExtractor._gallery_extractor = HentaieraGalleryExtractor

gallery_dl/extractor/imhentai.py

@@ -61,12 +61,12 @@ class ImhentaiGalleryExtractor(ImhentaiExtractor, GalleryExtractor):
             "gallery_id": text.parse_int(self.gallery_id),
             "title"     : text.unescape(extr("<h1>", "<")),
             "title_alt" : text.unescape(extr('class="subtitle">', "<")),
-            "parody"    : self._split(extr(">Parodies:</span>", "</li>")),
-            "character" : self._split(extr(">Characters:</span>", "</li>")),
-            "tags"      : self._split(extr(">Tags:</span>", "</li>")),
-            "artist"    : self._split(extr(">Artists:</span>", "</li>")),
-            "group"     : self._split(extr(">Groups:</span>", "</li>")),
-            "language"  : self._split(extr(">Languages:</span>", "</li>")),
+            "parody"    : self._split(extr(">Parodies", "</li>")),
+            "character" : self._split(extr(">Characters", "</li>")),
+            "tags"      : self._split(extr(">Tags", "</li>")),
+            "artist"    : self._split(extr(">Artists", "</li>")),
+            "group"     : self._split(extr(">Groups", "</li>")),
+            "language"  : self._split(extr(">Languages", "</li>")),
             "type"      : extr("href='/category/", "/"),
         }