Write a custom parser named ListParser. It will find any list element and print of the values to the screen. Note. You should remove any blank list items.

from html.parser import HTMLParser

from urllib.parse import urljoin

from urllib.request import urlopen

def testParser(url):

content = urlopen(url).read().decode()

parser = ListParser()

parser.feed(content)

return parser.getData()

class ListParser(HTMLParser):

def __init__(self):

pass

def handle_starttag(self, tag, attrs):

pass

def handle_data(self, data):

pass

def getData(self):

pass

def testHParser(url):

content = urlopen(url).read().decode()

parser = HeaderParser()

parser.feed(content)

return parser.getHeadings()

import re

from html.parser import HTMLParser

class HeaderParser(HTMLParser):

def __init__(self):

super().__init__()

self.in_header = False

self.headers_list = []

def handle_starttag(self, tag, attrs):

if re.match(r'h[1-6]', tag):

self.in_header = True

def handle_endtag(self, tag):

if re.match(r'h[1-6]', tag):

self.in_header = False

def handle_data(self, data):

if self.in_header:

self.headers_list.append(str(data).strip())

def getHeadings(self):

return self.headers_list

>>> testParser ('http://zoko.cam.depaul.edu/csc242/lists.html' 'Item 1', 'This is a nested 1ist','This is a second item in the nested 1ist', Item 2' Third item', Item A',Item B