Trying to write a html parser using python3 html.parser module with pyquery and lxml

my_html_parser.py

#!/usr/local/bin/python3

import sys
from urllib.request import Request,urlopen
from urllib.error import URLError,HTTPError
from html.parser import HTMLParser,HTMLParseError
from pyquery import PyQuery as pq

class MyHTMLParser(HTMLParser):
    """
    """
    
    def reset(self):
        HTMLParser.reset(self)
        self.buffer = ""
        self.h1 = False
        self.h2 = False
        self.h3 = False
        self.p = False
        self.span = False
        self.ul = False
        self.ol = False
        self.li = False

    def handle_starttag(self,tag,attrs):
        if tag == "h1" :
            self.h1 = True
        elif tag == "h2":
            self.h2 = True
        elif tag == "h3":
            self.h3 = True
        elif tag == "p":
            self.p = True
        elif tag == "span":
            self.span = True
        elif tag == "li":
            self.li = True


    def handle_data(self,data):
        if self.h1 or self.h2 or self.p or self.span or self.li or self.span:
            self.process_buffer(data)


    def handle_endtag(self,tag):            
        if self.h1:
            self.h1 = False
        elif self.h2:
            self.h2 = False
        elif self.h3:
            self.h3 = False
        elif self.p:
            self.p = False
        elif self.span:
            self.span = False
        elif self.li:
            self.li = False


    def process_buffer(self,data):
        fp = open("contents.txt","w+")
        fp.write(data)
        fp.close()


def cleanup(page):
    """
    remove unwanted sections of the page.
    Uses pyquery.

    """
    document = pq(page)
    #If you want to remove any other section, just add the class or id of the section below with comma seperated
    unwanted_sections_list="""
    div#jump-to-nav, div.top, div#column-one, div#siteNotice, div#purl, div#head,div#footer, div#head-base, div#page-base, div#stub, div#noprint,
    div#disambig,div.NavFrame,#colophon,.editsection,.toctoggle,.tochidden,.catlinks,.navbox,.sisterproject,.ambox,
    .toccolours,.topicondiv#f-poweredbyico,div#f-copyrightico,div#featured-star,li#f-viewcount,
    li#f-about,li#f-disclaimer,li#f-privacy,.portal, #footer, #mw-head

    """

    unwanted_divs = unwanted_sections_list.split(",")

    for section in unwanted_divs:
        document.remove(section.strip())

    return document.wrap('<div></div>').html()

if __name__ == "__main__":
    request = Request(url="http://kn.wikipedia.org/wiki/Karnataka")
    request.add_header("User-Agent","Python Crawler")
    try:
        response = urlopen(request).read().decode("utf-8")
        myparser = MyHTMLParser()
        myparser.feed(cleanup(response))
        myparser.close()
        # myparser.process_buffer()
    except HTTPError as e:
        print(("Something Went wrong, Error Code {}".format(e.code)))
        sys.exit(1)
    except URLError as u:
        print(("Something Went Wrong, Reason {}".format(u.reason)))
        sys.exit(1)