Truncate an HTML text to a certain number of words

html_word_truncator.py

from HTMLParser import HTMLParser
import re


re_whitespace = re.compile(r'(\w+)')


class WordTruncatedHTMLParser(HTMLParser):
    """
    Truncate an HTML text to a certain number of words.
    Based on https://late.am/post/2011/12/02/truncating-html-with-python.html
    Example:
        >>> html = ('<p>one, <span class="bar">two</span>, <label>three'
                    '</label>,<label class="baz">four</label>,<div><span>five'
                    '</span>,<span>six</span></div></p><p>seven, '
                    '<img src="img.png"/>, eight, nine, ten</p><p><span>eleven'
                    '</span><span>twelve</span></p>')
        >>> parser = WordTruncatedHTMLParser(maxlength=8)
        >>> parser.feed(html)
        >>> print parser.close()
        <p>one, <span class="bar">two</span>, <label>three</label>,<label class
        ="baz">four</label>,<div><span>five</span>,<span>six</span></div></p><p
        >seven, <img src="img.png"/>, eight</p>
    """

    def __init__(self, maxlength, *args, **kwargs):
        HTMLParser.__init__(self, *args, **kwargs)
        self.stack = []
        self.maxlength = maxlength
        self.length = 0
        self.out = []

    def emit(self, thing, count=False):
        if count:
            self.length += 1
        self.out.append(thing)
        if self.length == self.maxlength:
            # Trim right space.
            self.out[-1] = self.out[-1].rstrip()
            # Close out opened tags.
            for tag in reversed(self.stack):
                self.out.append('</%s>' % tag)

    def handle_starttag(self, tag, attrs):
        if self.length == self.maxlength:
            return
        self.stack.append(tag)
        attrs = ' '.join('%s="%s"' % (k, v) for k, v in attrs)
        self.emit('<%s%s>' % (tag, (' ' + attrs).rstrip()))

    def handle_endtag(self, tag):
        if self.length == self.maxlength:
            return
        if tag == self.stack[-1]:
            self.emit('</%s>' % tag)
            del self.stack[-1]
        else:
            raise Exception(
                'end tag %r does not match stack: %r' % (tag, self.stack))

    def handle_startendtag(self, tag, attrs):
        if self.length == self.maxlength:
            return
        attrs = ' '.join('%s="%s"' % (k, v) for k, v in attrs)
        self.emit('<%s%s/>' % (tag, (' ' + attrs).rstrip()))

    def handle_data(self, data):
        if self.length == self.maxlength:
            return
        for word in re_whitespace.split(data):
            if self.length != self.maxlength:
                self.emit(word, word.isalnum())

    def handle_entityref(self, name):
        if self.length == self.maxlength:
            return
        self.emit('&%s;' % name)

    def handle_charref(self, name):
        return self.handle_entityref('#%s' % name)

    def close(self):
        return ''.join(self.out)