add htmlparser sample

michaelliao · michaelliao · commit 99b8bd66eb1f · 2015-04-01T16:11:13.000+08:00
diff --git a/py3/commonlib/use_htmlparser.py b/py3/commonlib/use_htmlparser.py
@@ -0,0 +1,36 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+from html.parser import HTMLParser
+from html.entities import name2codepoint
+
+class MyHTMLParser(HTMLParser):
+
+    def handle_starttag(self, tag, attrs):
+        print('<%s>' % tag)
+
+    def handle_endtag(self, tag):
+        print('</%s>' % tag)
+
+    def handle_startendtag(self, tag, attrs):
+        print('<%s/>' % tag)
+
+    def handle_data(self, data):
+        print(data)
+
+    def handle_comment(self, data):
+        print('<!--', data, '-->')
+
+    def handle_entityref(self, name):
+        print('&%s;' % name)
+
+    def handle_charref(self, name):
+        print('&#%s;' % name)
+
+parser = MyHTMLParser()
+parser.feed('''<html>
+<head></head>
+<body>
+<!-- test html parser -->
+    <p>Some <a href=\"#\">html</a> HTML&nbsp;tutorial...<br>END</p>
+</body></html>''')
