This program extract text from html file.

extract_text.py

# coding: UTF-8

import re

def extract_text(html):
    #First, I deal with tags.
    cleaned = re.sub(r"<[^>]*?>", "", html)
    cleaned = re.sub(r"(?s)<!--(.*?)-->[\n]?", "", cleaned)
    cleaned = re.sub(r"(?s)<.*?>", "", cleaned)
    #Finally, I deal with special chars.
    cleaned = cleaned.replace("&nbsp;", " ")
    cleaned = cleaned.replace("&quot;", "\"")
    cleaned = cleaned.replace("&lt;", "<")
    cleaned = cleaned.replace("&gt;", ">")
    cleaned = cleaned.replace("&amp;", "&")

    return cleaned