Drop integrity attribute in HTML <script> and <link> tags

Since the JS and CSS scripts are rewritten, integrity checks are failing
on purpose. Since we do not really need these integrity checks, we just
drop the attribute when rewritting the HTML

CHANGELOG.md

@@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Fixed
+
+- Drop `integrity` attribute in HTML `<script>` and `<link>` tags (#298)
+
 ## [2.0.0] - 2024-06-04
 
 ### Added

src/warc2zim/content_rewriting/html.py

@@ -128,6 +128,7 @@ def handle_starttag(self, tag: str, attrs: AttrsList, *, auto_close: bool = Fals
             self.transform_attrs(
                 attrs,
                 self.url_rewriter_existing if tag == "a" else self.url_rewriter_all,
+                ["integrity"] if tag == "script" or "link" else [],
             )
         )
 
@@ -226,10 +227,12 @@ def transform_attrs(
         self,
         attrs: AttrsList,
         url_rewriter: UrlRewriterProto,
+        exclude_attrs: list[str],
     ) -> str:
         processed_attrs = (
             self.process_attr(attr_name, attr_value, url_rewriter)
             for attr_name, attr_value in attrs
+            if attr_name not in exclude_attrs
         )
         return " ".join(self.format_attr(*attr) for attr in processed_attrs)
 

tests/test_html_rewriting.py

@@ -185,6 +185,20 @@ def test_escaped_content(escaped_content, no_js_notify):
                 "}</script>"
             ),
         ),
+        ContentForTests(
+            '<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/3.7.0/jquery.min.js"'
+            ' integrity="sha512-3gJwYpMe3QewGELv8k/BX9vcqhryRdzRMxVfq6ngyWXwo03GFEzjsUm'
+            '8Q7RZcHPHksttq7/GFoxjCVUjkjvPdw=="'
+            ' crossorigin="anonymous" referrerpolicy="no-referrer"></script>',
+            '<script src="../cdnjs.cloudflare.com/ajax/libs/jquery/3.7.0/jquery.min.js"'
+            ' crossorigin="anonymous" referrerpolicy="no-referrer"></script>',
+        ),
+        ContentForTests(
+            '<link rel="preload" src="https://cdnjs.cloudflare.com/jquery.min.js"'
+            ' integrity="sha512-3gJwYpMe3QewGELv8k/BX9vcqhryRdzRMxVfq6ngyWXwo03GFEzjsUm'
+            '8Q7RZcHPHksttq7/GFoxjCVUjkjvPdw=="></link>',
+            '<link rel="preload" src="../cdnjs.cloudflare.com/jquery.min.js"></link>',
+        ),
     ]
 )
 def js_rewrites(request):