From 76040f9d6820b489038f0c75440703c68a3c0733 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Tue, 8 Apr 2025 11:56:26 +0200
Subject: [PATCH] [issuu] fix extractors (#7317)

---
 gallery_dl/extractor/issuu.py | 15 ++++++++-------
 test/results/issuu.py         | 10 ++++++----
 2 files changed, 14 insertions(+), 11 deletions(-)

diff --git a/gallery_dl/extractor/issuu.py b/gallery_dl/extractor/issuu.py
index 65717b49..abbdfd5f 100644
--- a/gallery_dl/extractor/issuu.py
+++ b/gallery_dl/extractor/issuu.py
@@ -29,9 +29,11 @@ class IssuuPublicationExtractor(IssuuBase, GalleryExtractor):
     example = "https://issuu.com/issuu/docs/TITLE/"
 
     def metadata(self, page):
-        pos = page.rindex('id="initial-data"')
-        data = util.json_loads(text.unescape(text.rextract(
-            page, '<script data-json="', '"', pos)[0]))
+
+        data = text.extr(
+            page, '{\\"documentTextVersion\\":', ']\\n"])</script>')
+        data = util.json_loads(text.unescape(
+            '{"":' + data.replace('\\"', '"')))
 
         doc = data["initialDocumentData"]["document"]
         doc["date"] = text.parse_datetime(
@@ -39,7 +41,7 @@ class IssuuPublicationExtractor(IssuuBase, GalleryExtractor):
 
         self._cnt = text.parse_int(doc["pageCount"])
         self._tpl = "https://{}/{}-{}/jpg/page_{{}}.jpg".format(
-            data["config"]["hosts"]["image"],
+            "image.isu.pub",  # data["config"]["hosts"]["image"],
             doc["revisionId"],
             doc["publicationId"],
         )
@@ -66,9 +68,8 @@ class IssuuUserExtractor(IssuuBase, Extractor):
             url = base + "/" + str(pnum) if pnum > 1 else base
             try:
                 html = self.request(url).text
-                data = util.json_loads(text.unescape(text.extr(
-                    html, '</main></div><script data-json="', '" id="')))
-                docs = data["docs"]
+                data = text.extr(html, '\\"docs\\":', '}]\\n"]')
+                docs = util.json_loads(data.replace('\\"', '"'))
             except Exception as exc:
                 self.log.debug("", exc_info=exc)
                 return
diff --git a/test/results/issuu.py b/test/results/issuu.py
index 015464e6..49443a37 100644
--- a/test/results/issuu.py
+++ b/test/results/issuu.py
@@ -5,6 +5,7 @@
 # published by the Free Software Foundation.
 
 from gallery_dl.extractor import issuu
+from gallery_dl import exception
 
 
 __tests__ = (
@@ -35,10 +36,11 @@ __tests__ = (
 },
 
 {
-    "#url"     : "https://issuu.com/foodhome1955/docs/fh_winter2025-issuu-011625",
-    "#comment" : "HTML escapes",
-    "#class"   : issuu.IssuuPublicationExtractor,
-    "#count"   : 84,
+    "#url"      : "https://issuu.com/foodhome1955/docs/fh_winter2025-issuu-011625",
+    "#comment"  : "HTML escapes",
+    "#class"    : issuu.IssuuPublicationExtractor,
+    "#exception": exception.NotFoundError,
+    "#count"    : 84,
 
     "document": {
         "access"          : "PUBLIC",