From 97f36bd097b9c677ef283bc39559b73aea76620b Mon Sep 17 00:00:00 2001
From: Martin Thoma <info@martin-thoma.de>
Date: Thu, 30 Jun 2022 08:42:06 +0200
Subject: [PATCH] MAINT: Handle XML error when reading XmpInformation (#1030)

Closes #585
---
 PyPDF2/xmp.py | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/PyPDF2/xmp.py b/PyPDF2/xmp.py
index 5583d772a..5cb79c750 100644
--- a/PyPDF2/xmp.py
+++ b/PyPDF2/xmp.py
@@ -20,6 +20,9 @@
 from xml.dom.minidom import Document
 from xml.dom.minidom import Element as XmlElement
 from xml.dom.minidom import parseString
+from xml.parsers.expat import ExpatError
+
+from PyPDF2.errors import PdfReadError
 
 from ._utils import StreamType, deprecate_with_replacement
 from .generic import ContentStream, PdfObject
@@ -205,11 +208,17 @@ class XmpInformation(PdfObject):
     """
     An object that represents Adobe XMP metadata.
     Usually accessed by :py:attr:`xmp_metadata()<PyPDF2.PdfReader.xmp_metadata>`
+
+    :raises: PdfReadError if XML is invalid
     """
 
     def __init__(self, stream: ContentStream) -> None:
         self.stream = stream
-        doc_root: Document = parseString(self.stream.get_data())
+        try:
+            data = self.stream.get_data()
+            doc_root: Document = parseString(data)
+        except ExpatError as e:
+            raise PdfReadError(f"XML in XmpInformation was invalid: {e}")
         self.rdf_root: XmlElement = doc_root.getElementsByTagNameNS(
             RDF_NAMESPACE, "RDF"
         )[0]