From a6deeeb8a53eb7474b16c469cf9915f60704bfad Mon Sep 17 00:00:00 2001
From: calvin <calvin@e7d03fd6-7b0d-0410-9947-9c21f3af8025>
Date: Mon, 16 Jun 2008 09:39:49 +0000
Subject: [PATCH] Support parsing of HTML pages served with content type
 application/xhtml+xml

git-svn-id: https://linkchecker.svn.sourceforge.net/svnroot/linkchecker/trunk/linkchecker@3817 e7d03fd6-7b0d-0410-9947-9c21f3af8025
---
 ChangeLog.txt                | 5 +++++
 linkcheck/checker/httpurl.py | 2 +-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/ChangeLog.txt b/ChangeLog.txt
index bfd34c14..3dfd53c2 100644
--- a/ChangeLog.txt
+++ b/ChangeLog.txt
@@ -42,6 +42,11 @@
     Type: feature
     Closes: SF bug #1985509
 
+  * Support parsing of HTML pages served with application/xhtml+xml
+    content type.
+    Type: bugfix
+    Closes: SF bug #1994104
+
 4.9 "Michael Clayton" (released 25.4.2008)
 
   * Parse Shockwave Flash (SWF) for URLs to check
diff --git a/linkcheck/checker/httpurl.py b/linkcheck/checker/httpurl.py
index 2f06353d..73d75e14 100644
--- a/linkcheck/checker/httpurl.py
+++ b/linkcheck/checker/httpurl.py
@@ -652,7 +652,7 @@ Use URL %(newurl)s instead for checking.""") % {
         Parse file contents for new links to check.
         """
         ctype = headers.get_content_type(self.headers)
-        if ctype == "text/html":
+        if ctype in ("text/html", "application/xhtml+xml"):
             self.parse_html()
         elif ctype == "text/css":
             self.parse_css()