From bcf4d579b06a44067d3055e49a0e689668fe758d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Thu, 11 Sep 2025 08:25:23 +0200
Subject: [PATCH] [formatter] exclude '<>\' from '!R' URLs (#8180)

---
 gallery_dl/formatter.py | 2 +-
 test/test_formatter.py  | 4 +++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/gallery_dl/formatter.py b/gallery_dl/formatter.py
index b09203fb..e1b26f9d 100644
--- a/gallery_dl/formatter.py
+++ b/gallery_dl/formatter.py
@@ -565,7 +565,7 @@ _CONVERSIONS = {
     "U": text.unescape,
     "H": lambda s: text.unescape(text.remove_html(s)),
     "g": text.slugify,
-    "R": text.re(r"https?://[^\s\"']+").findall,
+    "R": text.re(r"https?://[^\s\"'<>\\]+").findall,
     "W": text.sanitize_whitespace,
     "S": util.to_string,
     "s": str,
diff --git a/test/test_formatter.py b/test/test_formatter.py
index 8b35a2bd..a0a5224f 100644
--- a/test/test_formatter.py
+++ b/test/test_formatter.py
@@ -46,7 +46,8 @@ class TestFormatter(unittest.TestCase):
         "h": "<p>foo </p> &amp; bar <p> </p>",
         "H": """<p>
   <a href="http://www.example.com">Lorem ipsum dolor sit amet</a>.
-  Duis aute irure <a href="http://blog.example.org">dolor</a>.
+  Duis aute irure <a href="http://blog.example.org/lorem?foo=bar">
+  http://blog.example.org</a>.
 </p>""",
         "u": "&#x27;&lt; / &gt;&#x27;",
         "t": 1262304000,
@@ -78,6 +79,7 @@ class TestFormatter(unittest.TestCase):
         self._run_test("{n!H}", "")
         self._run_test("{h!R}", [])
         self._run_test("{H!R}", ["http://www.example.com",
+                                 "http://blog.example.org/lorem?foo=bar",
                                  "http://blog.example.org"])
         self._run_test("{a!s}", self.kwdict["a"])
         self._run_test("{a!r}", f"'{self.kwdict['a']}'")