本文共 891 字,大约阅读时间需要 2 分钟。
package test; import java.io.IOException; import org.jsoup.Connection; import org.jsoup.Jsoup; import org.jsoup.nodes.Document; import org.jsoup.select.Elements; public class Test { @org.junit.Test public void getDatasByCssQueryUserBaidu() { try { parseRequestUrl("http://www.xicidaili.com/nt"); } catch (IOException e) { e.printStackTrace(); } } public static void parseRequestUrl(String url) throws IOException { Connection con = Jsoup.connect(url); // 获取请求连接 // 浏览器可接受的MIME类型。 con.header("User-Agent", "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:45.0) Gecko/20100101 Firefox/45.0"); Document doc = con.get(); Elements tds = doc.getElementsByTag("td"); for (int i = 0; i < tds.size(); i++) { String linkText = tds.get(i).text(); if (linkText.indexOf(".") > 0) { System.out.println("========" + linkText); String port = tds.get(i+1).text(); System.out.println("-----------------"+port); } } }}
转载地址:http://fihji.baihongyu.com/