21 lines
475 B
Python
21 lines
475 B
Python
from html.parser import HTMLParser
|
|
|
|
class TootHTMLParser(HTMLParser):
|
|
def __init__(self):
|
|
super().__init__()
|
|
self.txt = ""
|
|
def handle_data(self, data):
|
|
self.txt += str(data).lstrip().rstrip().lower() + " "
|
|
#
|
|
#
|
|
# content = ""
|
|
# with open("input") as f:
|
|
# content = f.readlines()
|
|
# content = set(content)
|
|
# parser = TootHTMLParser()
|
|
# for word in content:
|
|
# parser.feed(word)
|
|
# with open("output", "w+") as f:
|
|
# f.write(parser.txt)
|
|
|