Extracts Kannada language words from the Webpages

kannada_word_extractor.py

#!/usr/local/bin/python3

import re
from urllib.request import urlopen, Request
from urllib.error import HTTPError
from multiprocessing import Process


def get_page(urlstring):
    """
    
    Arguments:
    - `url`:
    """
    request = Request(url=urlstring)
    request.add_header("User-Agent","Mozilla 5.0")

    page_content = ""
    try:
        response = urlopen(request)
        page_content = response.read()
    except HTTPError as e:
        print(("Something went wrong {}".format(e.read())))

    return page_content.decode("utf-8")

def find_kannada_words(content):
    expression = re.compile("([\u0c80-\u0cf2]+)[^\u0c80-\u0cf2]*")

    kannada_words = expression.findall(content)
    with open("Words.txt","a+") as infile:
        for word in kannada_words:
            infile.write(word+"\n")
            

def find_urls(content):
    """
    
    Arguments:
    - `content`:
    """
    urls = re.compile('<a href="(http://\w*\d?\.?\w+\.\w+\S*).*">')
    URLs = urls.findall(content)
    with open("URL.txt","a+") as urlfile:
        for url in URLs:
            urlfile.write(url+"\n")


if __name__ == "__main__":
    content = get_page("http://kn.wikipedia.org/wiki/Karnataka")
    fp = open("content.txt","w")
    fp.write(content)
    fp.close()

    p1 = Process(target=find_kannada_words,args=(content,))
    p2 = Process(target=find_urls,args=(content,))

    p1.start()
    p2.start()

    p1.join()
    p2.join()