[imagetwist:gallery] extract 'gallery_title' & 'gallery_id' metadata

gallery_dl/extractor/imagehosts.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2016-2025 Mike Fährmann
+# Copyright 2016-2026 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
@@ -205,8 +205,8 @@ class ImagevenueImageExtractor(ImagehostImageExtractor):
 class ImagetwistImageExtractor(ImagehostImageExtractor):
     """Extractor for single images from imagetwist.com"""
     category = "imagetwist"
-    pattern = (r"(?:https?://)?((?:www\.|phun\.)?"
-               r"image(?:twist|haha)\.com/([a-z0-9]{12}))")
+    pattern = (r"(?:https?://)?((?:www\.|phun\.)?image(?:twist|haha)\.com"
+               r"/([a-z0-9]{12}))")
     example = "https://imagetwist.com/123456abcdef/NAME.EXT"
 
     @property
@@ -227,18 +227,24 @@ class ImagetwistGalleryExtractor(ImagehostImageExtractor):
     category = "imagetwist"
     subcategory = "gallery"
     pattern = (r"(?:https?://)?((?:www\.|phun\.)?image(?:twist|haha)\.com/("
-               r"p/[^/?#]+/\d+|"
+               r"p/[^/?#]+/(\d+)|"
                r"\?[^#]*\bfld_id=\d+[^#]*&page=\d+))")
     example = "https://imagetwist.com/p/USER/12345/TITLE"
 
     def items(self):
         url = self.page_url
         root = url[:url.find("/", 8)]
-        data = {"_extractor": ImagetwistImageExtractor}
+        page = self.request(url).text
+
+        extr = text.extract_from(page)
+        data = {
+            "_extractor"   : ImagetwistImageExtractor,
+            "gallery_title": text.unescape(extr('page_main_title">', "<")),
+            "gallery_id"   : self.groups[2] or extr("&amp;fld_id=", "&"),
+        }
+        del extr
 
         while True:
-            page = self.request(url).text
-
             gallery = text.extr(page, 'class="gallerys', "</div")
             for path in text.extract_iter(gallery, ' href="', '"'):
                 yield Message.Queue, root + path, data
@@ -247,7 +253,8 @@ class ImagetwistGalleryExtractor(ImagehostImageExtractor):
             if pos < 0:
                 break
             qs = text.unescape(text.rextr(page, "href='", "'", pos))
-            url = f"{root}/{qs}"
+
+            page = self.request(f"{root}/{qs}").text
 
 
 class ImgadultImageExtractor(ImagehostImageExtractor):

test/results/imagetwist.py

@@ -64,6 +64,9 @@ __tests__ = (
         "https://imagetwist.com/n3td3a6vzzed",
         "https://imagetwist.com/8uz6lmg31nmc",
     ),
+
+    "gallery_id"   : "747223",
+    "gallery_title": "digits",
 },
 
 {
@@ -73,6 +76,9 @@ __tests__ = (
     "#class"   : imagehosts.ImagetwistGalleryExtractor,
     "#pattern" : imagehosts.ImagetwistImageExtractor.pattern,
     "#count"   : 100,
+
+    "gallery_id"   : "806105",
+    "gallery_title": "multi",
 },
 
 {
@@ -82,6 +88,9 @@ __tests__ = (
     "#class"   : imagehosts.ImagetwistGalleryExtractor,
     "#pattern" : imagehosts.ImagetwistImageExtractor.pattern,
     "#count"   : 60,
+
+    "gallery_id"   : "806105",
+    "gallery_title": "multi",
 },
 
 )