html_parser.py

#!/usr/bin/python
# -*- coding: utf-8 -*-

from urllib.request import *
from html.parser import *
import re

class MyParser(HTMLParser):
	hyperlinks = []
	def handle_starttag(self, tag, attributes):
		if tag=='a':
			self.start_a(attributes)

	def start_a(self, attributes):
		for name, value in attributes:
			if name=='href':
				self.hyperlinks.append(value)


#web_page = urlopen('http://junaidpv.in')

#print(web_page.info().get('Content-Type'))

#my_parser = MyParser()
#my_parser.feed(str(web_page.read(), encoding='utf-8'))
#web_page.close()

#for link in my_parser.hyperlinks:
#	print(link)
def f5(seq, idfun=None): 
    # order preserving
    if idfun is None:
        def idfun(x): return x
    seen = {}
    result = []
    for item in seq:
        marker = idfun(item)
        # in old Python versions:
        # if seen.has_key(marker)
        # but in new ones:
        if marker in seen: continue
        seen[marker] = 1
        result.append(item)
    return result

i_file = open('input.txt', mode='r', encoding='utf-8')
o_file = open('output.txt', mode='w+', encoding='utf-8')

text = i_file.read()
i_file.close()

pattern = re.compile('[\u0D00-\u0D7F\u200C\u200D]+')

words = re.findall(pattern, text)
unique_words = f5(words)
print(len(words), " words.")
print(len(unique_words), " unique words.")
for line in unique_words:
	o_file.writelines(line+"\n")

o_file.flush()
o_file.close()