Function html_unescape

module/plugins/internal/misc.py:354–382

Decode HTML or XML escape character references and entities from a text string

(text)

def html_unescape(text):
    """
    Decode HTML or XML escape character references and entities from a text string
    """
    def fixup(m):
        text = m.group(0)
        if text[:2] == "&#":
            # character reference
            try:
                if text[:3] == "&#x":
                    return unichr(int(text[3:-1], 16))
                else:
                    return unichr(int(text[2:-1]))
            except ValueError:
                pass
        else:
            # named entity
            try:
                name = text[1:-1]
                text = unichr(name2codepoint[name])
            except KeyError:
                pass

        return text # leave as is

    return re.sub("&#?\w+;", fixup, text)
    #@TODO: Replace in 0.4.10 with:
    # h = HTMLParser.HTMLParser()
    # return h.unescape(text)


def isiterable(obj):