JsoupTest.java

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import java.io.File;
import java.io.IOException;

/**
 * Created by Administrator on 2017/5/26.
 */
public class JsoupTest {
    public static void main(String args[]) {

        // Parse HTML String using JSoup library
        String HTMLSTring = "<!DOCTYPE html>"
                + "<html>"
                + "<head>"
                + "<title>JSoup Example</title>"

                + "</head>"
                + "<body>"
//                + "<table>"
//                + "<tr>"
//                + "<td>"
                + "<h1>"
                + "HelloWorld"
                + "<h1>"
//                + "<td>"
//                + "<tr>"
//                + "<table>"
                + "</body>"
                + "</html>";

        Document html = Jsoup.parse(HTMLSTring);
        String title = html.title();
        String h1 = html.body().getElementsByTag("h1").text();

        System.out.println("Input HTML String to JSoup :" + HTMLSTring);
        System.out.println("After parsing, Title : " + title);
        System.out.println("Afte parsing, Heading : " + h1);

        // JSoup Example 2 - Reading HTML page from URL
        Document doc = null;
//        String h = null;
        try {
            doc = Jsoup.connect("http://www.baidu.com/").get();
            title = doc.title();

//            h = doc.html();
        } catch (IOException e) {
            e.printStackTrace();
        }

        System.out.println("Input HTML String to JSoup :" + doc.html());
        System.out.println("Jsoup Can read HTML page from URL, title : " + title);

        // JSoup Example 3 - Parsing an HTML file in Java
        //Document htmlFile = Jsoup.parse("login.html", "ISO-8859-1"); // wrong
        Document htmlFile = null;
        try {
            htmlFile = Jsoup.parse(new File("D:\\Test\\228.html"), "UTF-8");
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } // right
        title = htmlFile.title();
        Element div = htmlFile.getElementById("team_box");



        //测试1
        /*Elements div1 = htmlFile.getElementsContainingText("工商注册");
        Elements div2 = htmlFile.getElementsMatchingText("法定代表人");*/

//        String cssClass = div.className(); // getting class form HTML element

        System.out.println("Jsoup can also parse HTML file directly");
        System.out.println("title : " + title);
//        System.out.println("class of div tag : " + cssClass);


        //增加内容
        Elements spans = htmlFile.select("[span='注册号:']");
        System.out.println("\n" + spans.toString() + "\n");


        //测试1
        /*System.out.println("found: " + div1);
        System.out.println("found: " + div2);*/
    }

}

  

posted @ 2017-06-02 12:03  tangyongathuse  阅读(236)  评论(0编辑  收藏  举报