HTMLParser
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 tutorial...<br>END</p>
</body></html>''')
参考文章
http://www.liaoxuefeng.com/wiki/0014316089557264a6b348958f449949df42a6d3a2e542c000/0014320023122880232500da9dc4a4486ad00426f081c15000
