HTML to text

html2text.py

# Based on http://stackoverflow.com/questions/328356/extracting-text-from-html-file-using-python

from cStringIO import StringIO
from formatter import AbstractFormatter, DumbWriter
from htmllib import HTMLParser, HTMLParseError


def html2text(data):
    f = StringIO()
    parser = HTMLParser(AbstractFormatter(DumbWriter(f)))
    try:
        parser.feed(data)
    except HTMLParseError:
        return ''
    else:
        parser.close()
        return f.getvalue()