Sanitize XML strings before parsing (#1452)

Author: JonnyWong16

plexapi/client.py

@@ -197,7 +197,7 @@ def query(self, path, method=None, headers=None, timeout=None, **kwargs):
                 raise NotFound(message)
             else:
                 raise BadRequest(message)
-        data = response.text.encode('utf8')
+        data = utils.cleanXMLString(response.text).encode('utf8')
         return ElementTree.fromstring(data) if data.strip() else None
 
     def sendCommand(self, command, proxy=None, **params):

plexapi/myplex.py

@@ -250,7 +250,7 @@ def query(self, url, method=None, headers=None, timeout=None, **kwargs):
             return response.json()
         elif 'text/plain' in response.headers.get('Content-Type', ''):
             return response.text.strip()
-        data = response.text.encode('utf8')
+        data = utils.cleanXMLString(response.text).encode('utf8')
         return ElementTree.fromstring(data) if data.strip() else None
 
     def ping(self):

plexapi/server.py

@@ -768,7 +768,7 @@ def query(self, key, method=None, headers=None, params=None, timeout=None, **kwa
                 raise NotFound(message)
             else:
                 raise BadRequest(message)
-        data = response.text.encode('utf8')
+        data = utils.cleanXMLString(response.text).encode('utf8')
         return ElementTree.fromstring(data) if data.strip() else None
 
     def search(self, query, mediatype=None, limit=None, sectionId=None):

plexapi/utils.py

@@ -6,6 +6,7 @@
 import os
 import re
 import string
+import sys
 import time
 import unicodedata
 import warnings
@@ -673,3 +674,45 @@ def openOrRead(file):
 def sha1hash(guid):
     """ Return the SHA1 hash of a guid. """
     return sha1(guid.encode('utf-8')).hexdigest()
+
+
+# https://stackoverflow.com/a/64570125
+_illegal_XML_characters = [
+    (0x00, 0x08),
+    (0x0B, 0x0C),
+    (0x0E, 0x1F),
+    (0x7F, 0x84),
+    (0x86, 0x9F),
+    (0xFDD0, 0xFDDF),
+    (0xFFFE, 0xFFFF),
+]
+if sys.maxunicode >= 0x10000:  # not narrow build
+    _illegal_XML_characters.extend(
+        [
+            (0x1FFFE, 0x1FFFF),
+            (0x2FFFE, 0x2FFFF),
+            (0x3FFFE, 0x3FFFF),
+            (0x4FFFE, 0x4FFFF),
+            (0x5FFFE, 0x5FFFF),
+            (0x6FFFE, 0x6FFFF),
+            (0x7FFFE, 0x7FFFF),
+            (0x8FFFE, 0x8FFFF),
+            (0x9FFFE, 0x9FFFF),
+            (0xAFFFE, 0xAFFFF),
+            (0xBFFFE, 0xBFFFF),
+            (0xCFFFE, 0xCFFFF),
+            (0xDFFFE, 0xDFFFF),
+            (0xEFFFE, 0xEFFFF),
+            (0xFFFFE, 0xFFFFF),
+            (0x10FFFE, 0x10FFFF),
+        ]
+    )
+_illegal_XML_ranges = [
+    fr'{chr(low)}-{chr(high)}'
+    for (low, high) in _illegal_XML_characters
+]
+_illegal_XML_re = re.compile(fr'[{"".join(_illegal_XML_ranges)}]')
+
+
+def cleanXMLString(s):
+    return _illegal_XML_re.sub('', s)