Merge pull request #111 from bigsan/encodingfix

encoding problem fixed.
jamietre · Jul 29, 2013 · 59724ca · 59724ca
2 parents 30b56cf + 850870e
commit 59724ca
Show file tree

Hide file tree

Showing 2 changed files with 16 additions and 3 deletions.
diff --git a/source/CsQuery.Tests/Core/WebIO/QueryRemoteServer.cs b/source/CsQuery.Tests/Core/WebIO/QueryRemoteServer.cs
@@ -29,8 +29,20 @@ public override void FixtureSetUp()
             base.FixtureSetUp();
             ServerConfig.Default.UserAgent = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.121 Safari/535.2";
         }
-
-        [Test,TestMethod]
+
+        [Test, TestMethod]
+        public void GetHtmlWhoseContentTypeHasNoCharset()
+        {
+            var url = "http://www.pixnet.net";
+
+            Dom = CQ.CreateFromUrl(url);
+
+            Assert.IsTrue(Dom.Document != null, "Dom was created");
+            var csq = Dom.Find("title:contains('痞客邦 PIXNET')");
+            Assert.IsTrue(csq.Length > 0, "I found an expected content container - if Pixnet changed their web site this could fail.");
+        }
+
+        [Test, TestMethod]
         public void GetHtml()
         {
             var url = urls[0];

diff --git a/source/CsQuery/Web/CsqWebRequest.cs b/source/CsQuery/Web/CsqWebRequest.cs
@@ -457,7 +457,8 @@ public static Encoding GetEncoding(IHttpWebResponse response)
         {
             Encoding encoding = null;
 
-            if (!String.IsNullOrEmpty(response.CharacterSet)) {
+            if (!String.IsNullOrEmpty(response.CharacterSet)
+                && response.ContentType.Contains("charset=")) {
                 HtmlParser.HtmlEncoding.TryGetEncoding(response.CharacterSet, out encoding);
             }