Fix html stripping to get entire html-ish substring

lib/utils.js

@@ -169,7 +169,7 @@ exports.reresolve = reresolve;
  * @private
  */
 function stripHtml (str) {
-  return str.replace(/<.*?>/g, '');
+  return str.replace(/<+[^>]+?>+/g, '');
 }
 
 exports.stripHtml = stripHtml;

test/feeds/title-with-angle-brackets.xml

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<rss version="2.0">
+<channel>
+    <title>Channel title</title>
+    <link>http://example.com/</link>
+    <description>Channel</description>
+    <item>
+      <title>RSS &lt;&lt;&lt; Title &gt;&gt;&gt;</title>
+    </item>
+</channel>
+</rss>

test/strip-html.js

@@ -0,0 +1,18 @@
+describe('strip html', function () {
+
+  var feed = __dirname + '/feeds/title-with-angle-brackets.xml';
+
+  it('should aggressively strip html', function (done) {
+    fs.createReadStream(feed).pipe(new FeedParser())
+      .once('readable', function () {
+        var stream = this;
+        assert.equal(stream.read().title, 'RSS ');
+        done();
+      })
+      .on('error', function (err) {
+        assert.ifError(err);
+        done(err);
+      });
+  });
+
+});