strip_html.py

try:
    from lxml.html import fromstring
    strip_html = lambda html: fromstring(html).text_content()
except ImportError:
    try:
        from bs4 import BeautifulSoup
        strip_html = lambda html: ''.join(
            BeautifulSoup(html).findAll(text=True))
    except ImportError:
        from HTMLParser import HTMLParser

        class _Parser(HTMLParser):
            def __init__(self):
                self.reset()
                self.items = []

            def handle_data(self, data):
                self.items.append(data)

            def get_text(self):
                return ''.join(self.items)

        def strip_html(html):
            _parser = _Parser()
            _parser.feed(html)
            return _parser.get_text()