htmlparser 我的程序，能用的

时间：2010-12-07 来源：笨笨在成长

            String temp = "";
            //string htmlcode = richTextBox1.Text;//"<HTML><HEAD><TITLE>AAA</TITLE></HEAD><BODY><a href='http://topic.csdn.net/u/20080522/14/0ff402ef-c382-499a-8213-ba6b2f550425.html'>连接1</a><a href='http://topic.csdn.net'>连接2</a></BODY></HTML>";
            // 创建Parser对象根据传给字符串和指定的编码
            Parser parser = Parser.CreateParser(htmlcode, "GBK");
            // 创建HtmlPage对象HtmlPage(Parser parser)
            HtmlPage page = new HtmlPage(parser);
            //parser.VisitAllNodesWith(page);
            NodeFilter filter = new TagNameFilter("div");
            NodeFilter ftie = new AndFilter(new TagNameFilter("dl"), new HasAttributeFilter("id", "miaosha"));
            NodeList nodelist = parser.Parse(ftie);
            int count = nodelist.Count;

            for (int i = 0; i < nodelist.Count; i++)
            {
                temp = nodelist[i].ToHtml();
                Parser vparser = Parser.CreateParser(temp, "");
                TextExtractingVisitor visitor = new TextExtractingVisitor();
                vparser.VisitAllNodesWith(visitor);
                temp = visitor.ExtractedText;
                MessageBox.Show(temp);

}
}

相关阅读更多 +