基于htmllib.HTMLParser的html2text

基于htmllib.HTMLParser的html2text

 

def html2text(strHtml):
    """处理html 4.01和部分xhtml 1.0转义字符"""
    class SimpleParser(htmllib.HTMLParser):
        def anchor_end(self):
            if self.anchor:
                self.anchor = None
        def handle_image(self, src, alt, *args):
            #self.handle_data(alt)  #可以重写为alt属性
            pass                    #图片替换成空
        def convert_entityref(self, name):
            name2codepoint["nbsp"]  = 0x0020
            name2codepoint["apos"]  = 0x0027
            if name in name2codepoint and name<256:
                return chr(name2codepoint[name])
            else:
                return
        def convert_charref(self, name):
            return unichr(int(name)).encode("gb18030")    file = StringIO.StringIO()
    p = SimpleParser(formatter.AbstractFormatter(formatter.DumbWriter(file)))
    p.feed(strHtml)
    p.close()
    return file.getvalue() 基于htmllib.HTMLParser的html2text