LISTERINE..

38

此代码取自python docs

from HTMLParser import HTMLParser

# create a subclass and override the handler methods

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

# instantiate the parser and fed it some HTML

parser = MyHTMLParser()

parser.feed('

Test'

'

Parse me!

')

结果如下:

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

使用它并查看HTMLParser中的代码我想出了这个:

class myhtmlparser(HTMLParser):

def __init__(self):

self.reset()

self.NEWTAGS = []

self.NEWATTRS = []

self.HTMLDATA = []

def handle_starttag(self, tag, attrs):

self.NEWTAGS.append(tag)

self.NEWATTRS.append(attrs)

def handle_data(self, data):

self.HTMLDATA.append(data)

def clean(self):

self.NEWTAGS = []

self.NEWATTRS = []

self.HTMLDATA = []

你可以像这样使用它:

from HTMLParser import HTMLParser

pstring = source_code = """Martin Elias"""

class myhtmlparser(HTMLParser):

def __init__(self):

self.reset()

self.NEWTAGS = []

self.NEWATTRS = []

self.HTMLDATA = []

def handle_starttag(self, tag, attrs):

self.NEWTAGS.append(tag)

self.NEWATTRS.append(attrs)

def handle_data(self, data):

self.HTMLDATA.append(data)

def clean(self):

self.NEWTAGS = []

self.NEWATTRS = []

self.HTMLDATA = []

parser = myhtmlparser()

parser.feed(pstring)

# Extract data from parser

tags = parser.NEWTAGS

attrs = parser.NEWATTRS

data = parser.HTMLDATA

# Clean the parser

parser.clean()

# Print out our data

print tags

print attrs

print data

现在,您应该能够轻松地从这些列表中提取数据.我希望这有帮助!