4.1.7 - Remove any invalid XML schema tags before parsing the XML (#18)

CHANGELOG.md

@@ -1,3 +1,8 @@
+4.1.7
+-----
+
+- Remove any invalid XML schema tags before parsing the XML (#18)
+
 4.1.6
 -----
 

parsedmarc/__init__.py

@@ -44,12 +44,13 @@ import imapclient.exceptions
 import dateparser
 import mailparser
 
-__version__ = "4.1.6"
+__version__ = "4.1.7"
 
 logger = logging.getLogger(__name__)
 logger.setLevel(logging.ERROR)
 
 feedback_report_regex = re.compile(r"^([\w\-]+): (.+)$", re.MULTILINE)
+xml_schema_regex = re.compile(r"\s*<xs:schema.*>", re.MULTILINE)
 
 MAGIC_ZIP = b"\x50\x4B\x03\x04"
 MAGIC_GZIP = b"\x1F\x8B"
@@ -457,6 +458,8 @@ def parse_aggregate_report_xml(xml, nameservers=None, timeout=2.0):
         OrderedDict: The parsed aggregate DMARC report
     """
     try:
+        # Remove invalid schema tags
+        xml = xml_schema_regex.sub("", xml)
         report = xmltodict.parse(xml)["feedback"]
         report_metadata = report["report_metadata"]
         schema = "draft"

samples/ikea.com!xxxxxx.de!1538690400!1538776800.xml.sample

@@ -0,0 +1,47 @@
+<?xml version="1.0"?> <xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema" targetNamespace="http://dmarc.org/dmarc-xml/0.1">
+<feedback>
+  <report_metadata>
+    <org_name>ikea.com</org_name>
+    <email>double-bounce@ikea.com</email>
+    <report_id>aggr_report_2018_10_05_5bc7e9b4f3e8a</report_id>
+    <date_range>
+      <begin>1538690400</begin>
+      <end>1538776800</end>
+    </date_range>
+  </report_metadata>
+  <policy_published>
+    <domain>xxxxxx.de</domain>
+    <adkim>r</adkim>
+    <aspf>r</aspf>
+    <p>none</p>
+    <sp>none</sp>
+    <pct>100</pct>
+    <fo>0</fo>
+  </policy_published>
+  <record>
+    <row>
+      <source_ip>234.234.234.234</source_ip>
+      <count>1</count>
+      <policy_evaluated>
+        <disposition>none</disposition>
+        <dkim>fail</dkim>
+        <spf>fail</spf>
+      </policy_evaluated>
+    </row>
+    <identifiers>
+      <header_from>xxxxxx.de</header_from>
+      <envelope_from>xxxxxx.de</envelope_from>
+    </identifiers>
+    <auth_results>
+      <dkim>
+        <domain>xxxxxx.de</domain>
+        <result>pass</result>
+      </dkim>
+      <spf>
+        <domain>mailrelay.com</domain>
+        <scope>helo</scope>
+        <result>none</result>
+      </spf>
+    </auth_results>
+  </record>
+</feedback>

setup.py

@@ -14,7 +14,7 @@ from setuptools import setup
 from codecs import open
 from os import path
 
-__version__ = "4.1.6"
+__version__ = "4.1.7"
 description = "A Python package and CLI for parsing aggregate and " \
               "forensic DMARC reports"