Extracting text from HTML file using Python

Question

I\'d like to extract the text from an HTML file using Python. I want essentially the same output I would get if I copied the text from a browser and pasted it into notepad.

Answer 1

Here is a version of xperroni's answer which is a bit more complete. It skips script and style sections and translates charrefs (e.g., ') and HTML entities (e.g., &).

It also includes a trivial plain-text-to-html inverse converter.

"""
HTML <-> text conversions.
"""
from HTMLParser import HTMLParser, HTMLParseError
from htmlentitydefs import name2codepoint
import re

class _HTMLToText(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)
        self._buf = []
        self.hide_output = False

    def handle_starttag(self, tag, attrs):
        if tag in ('p', 'br') and not self.hide_output:
            self._buf.append('\n')
        elif tag in ('script', 'style'):
            self.hide_output = True

    def handle_startendtag(self, tag, attrs):
        if tag == 'br':
            self._buf.append('\n')

    def handle_endtag(self, tag):
        if tag == 'p':
            self._buf.append('\n')
        elif tag in ('script', 'style'):
            self.hide_output = False

    def handle_data(self, text):
        if text and not self.hide_output:
            self._buf.append(re.sub(r'\s+', ' ', text))

    def handle_entityref(self, name):
        if name in name2codepoint and not self.hide_output:
            c = unichr(name2codepoint[name])
            self._buf.append(c)

    def handle_charref(self, name):
        if not self.hide_output:
            n = int(name[1:], 16) if name.startswith('x') else int(name)
            self._buf.append(unichr(n))

    def get_text(self):
        return re.sub(r' +', ' ', ''.join(self._buf))

def html_to_text(html):
    """
    Given a piece of HTML, return the plain text it contains.
    This handles entities and char refs, but not javascript and stylesheets.
    """
    parser = _HTMLToText()
    try:
        parser.feed(html)
        parser.close()
    except HTMLParseError:
        pass
    return parser.get_text()

def text_to_html(text):
    """
    Convert the given text to html, wrapping what looks like URLs with  tags,
    converting newlines to 
 tags and converting confusing chars into html
    entities.
    """
    def f(mo):
        t = mo.group()
        if len(t) == 1:
            return {'&':'&', "'":''', '"':'"', '<':'<', '>':'>'}.get(t)
        return '%s' % (t, t)
    return re.sub(r'https?://[^] ()"\';]+|[&\'"<>]', f, text)