使用HtmlParser的Filter实例：根据id获取相应div文本

最新推荐文章于 2022-06-01 08:54:59 发布

cesul

最新推荐文章于 2022-06-01 08:54:59 发布

阅读量514

点赞数

文章标签： java c#

本文链接：https://blog.csdn.net/cesul/article/details/83872759

版权

public class ParseWork {
	private Parser parser;

	public ParseWork(String htmlAddress) throws ParserException {
		parser = new Parser(htmlAddress);
	}

	/**
	 * 获取网页标题和正文组成的文本
	 * **/
	protected String getText(String elementId) throws ParserException{
		NodeFilter TitleFilter = new NodeClassFilter(TitleTag.class);
		NodeFilter ElementIdFilter = new HasAttributeFilter("id", elementId);
		OrFilter orFilter = new OrFilter(TitleFilter, ElementIdFilter);  //做一个逻辑OR Filter组合
		NodeList list = parser.extractAllNodesThatMatch(orFilter);

		StringBuffer text = new StringBuffer();
		for (int i = 0; i < list.size(); i++)
			text = text.append(list.elementAt(i).toPlainTextString() + "\r\n");
		return text.toString().trim();
	}

	public static void main(String[] args) throws ParserException, IOException {
		ParseWork p = new ParseWork("E://JavaEye新闻.htm");
		String mainText = p.getText("news_content");

		//写网页正文文件
		FileUtils.writeStringToFile(new File("E://javaeye新闻.txt"), mainText, "utf-8");	
		//摘要
	}
}