Python HTMLParser automatically converts &lt; and &gt; to '<' and '>'... sigh. Convert them back. With Tests.

kata198 · kata198 · commit 454edc78d98d · 2016-07-26T23:57:10.000-04:00
diff --git a/AdvancedHTMLParser/Parser.py b/AdvancedHTMLParser/Parser.py
@@ -133,6 +133,8 @@ def handle_data(self, data):
             Internal for parsing
         '''
         if data:
+            # Python HTMLParser so helpfully automatically replaces &lt; with < and &gt; with >.... sigh.
+            data = data.replace('<', '&lt;').replace('>', '&gt;')
             if len(self.inTag) > 0:
                 self.inTag[-1].appendText(data)
             elif data.strip(): #and not self.getRoot():
diff --git a/tests/AdvancedHTMLParserTests/test_RefTag.py b/tests/AdvancedHTMLParserTests/test_RefTag.py
@@ -0,0 +1,27 @@
+#!/usr/bin/env GoodTests.py
+'''
+    Test that we retain &lt; and &gt;
+'''
+
+import sys
+import tempfile
+import subprocess
+
+from AdvancedHTMLParser.Parser import AdvancedHTMLParser
+
+
+class TestRefTag(object):
+
+    def test_refTag(self):
+        html = """<html><body><p>This is &lt;html&gt;</p></body></html>"""
+
+        parser = AdvancedHTMLParser()
+        parser.parseStr(html)
+
+        html = parser.getHTML().replace('\n', '').replace('html ', 'html')
+        assert 'This is <html>' not in html, 'Expected to retain &lt; and &gt;, got %s' %(html,)
+        assert 'This is &lt;html&gt;' in html, 'Expected to retain &lt; and &gt;, got %s' %(html,)
+
+
+if __name__ == '__main__':
+    pipe  = subprocess.Popen('GoodTests.py "%s"' %(sys.argv[0],), shell=True).wait()
