Parsing HTML to get text inside an element

Question

I searched “python parse html” and this was the first result:
https://docs.python.org/2/library/htmlparser.html

This code is taken from the 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('<html><head><title>Test</title></head>'
                '<body><h1>Parse me!</h1></body></html>')

Here is the result:

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

Using this and by looking at the code in HTMLParser I came up with this:

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 = []

You can use it like this:

from HTMLParser import HTMLParser

pstring = source_code = """<span class="UserName"><a href="#">Martin Elias</a></span>"""


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

Now you should be able to extract your data from those lists easily. I hope this helped!

Leave a Comment Cancel reply