Simple HTML and XHTML parser
Example HTML Parser Application
from html.parser import HTMLParser
class MyHTMLParser(HTMLParser):
def handle_starttag(self, tag, attrs):
print("Encountered a start tag:", tag)
def handle_endtag(self, tag):
print("Encountered an end tag :", tag)
def handle_data(self, data):
print("Encountered some data :", data)
parser = MyHTMLParser()
parser.feed('<html><head><title>Test</title></head>'
'<body><h1>Parse me!</h1></body></html>')
Encountered a start tag: html
Encountered a start tag: head
Encountered a start tag: title
Encountered some data : Test
Encountered an end tag : title
Encountered an end tag : head
Encountered a start tag: body
Encountered a start tag: h1
Encountered some data : Parse me!
Encountered an end tag : h1
Encountered an end tag : body
Encountered an end tag : html
HTMLParser Methods
from html.parser import HTMLParser
from html.entities import name2codepoint
class MyHTMLParser(HTMLParser):
def handle_starttag(self, tag, attrs):
print("Start tag:", tag)
for attr in attrs:
print(" attr:", attr)
def handle_endtag(self, tag):
print("End tag :", tag)
def handle_data(self, data):
print("Data :", data)
def handle_comment(self, data):
print("Comment :", data)
def handle_entityref(self, name):
c = chr(name2codepoint[name])
print("Named ent:", c)
def handle_charref(self, name):
if name.startswith('x'):
c = chr(int(name[1:], 16))
else:
c = chr(int(name))
print("Num ent :", c)
def handle_decl(self, data):
print("Decl :", data)
parser = MyHTMLParser()
>>> parser.feed('<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" '
... '"http://www.w3.org/TR/html4/strict.dtd">')
Decl : DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd"
>>> parser.feed('<img src="python-logo.png" alt="The Python logo">')
Start tag: img
attr: ('src', 'python-logo.png')
attr: ('alt', 'The Python logo')
>>>
>>> parser.feed('<h1>Python</h1>')
Start tag: h1
Data : Python
End tag : h1
>>> parser.feed('<style type="text/css">#python { color: green }</style>')
Start tag: style
attr: ('type', 'text/css')
Data : #python { color: green }
End tag : style
>>> parser.feed('<script type="text/javascript">'
... 'alert("<strong>hello!</strong>");</script>')
Start tag: script
attr: ('type', 'text/javascript')
Data : alert("<strong>hello!</strong>");
End tag : script
>>> parser.feed('<!-- a comment -->'
... '<!--[if IE 9]>IE-specific content<![endif]-->')
Comment : a comment
Comment : [if IE 9]>IE-specific content<![endif]
>>> parser.feed('>>>')
Named ent: >
Num ent : >
Num ent : >
>>> for chunk in ['<sp', 'an>buff', 'ered ', 'text</s', 'pan>']:
... parser.feed(chunk)
...
Start tag: span
Data : buff
Data : ered
Data : text
End tag : span
>>> parser.feed('<p><a class=link href=#main>tag soup</p ></a>')
Start tag: p
Start tag: a
attr: ('class', 'link')
attr: ('href', '#main')
Data : tag soup
End tag : p
End tag : a
