파이썬 간단한 문자열 파싱: 줄 단위로 나누고 - 붙임

string_parser.py

import re

def trim(line):
    return line.replace("        ", "")

def strip_html(data):
    p = re.compile(r'<.*?>')
    return p.sub('', data)

def make_bullet(line):
    return "- " + line + "\n"

doc = strip_html(doc)
lines = doc.splitlines()

for line in lines:
    str_check = set()
    words = line.split()
    for word in words:
        str_check.add(word)
    
    if (len(str_check) < 2):
        continue

    line = trim(line)
    line = make_bullet(line)
    print(line)