java编写登录脚本_用Java编写脚本,定期从网站请求数据

好的,我今天在工作上度过了一段时间,并想着给你一个帮助并为你写下来.请原谅我第一次解析网站时出现的任何错误,我做了一些研究并决定使用jSoup.

好的,这段代码将使用值解析表和系统中的3列,您可以更改代码并根据需要构建它:)

你必须下载jsoup jar Download jSoup

import java.io.BufferedReader;

import java.io.InputStreamReader;

import java.net.URL;

import java.net.URLConnection;

import java.util.Iterator;

import org.jsoup.Jsoup;

import org.jsoup.nodes.Document;

import org.jsoup.nodes.Element;

/**

*

*/

public class ParseWithJsoup{

public static void main(String[] args) {

URL url;

try {

url = new URL("http://www.cbsa-asfc.gc.ca/bwt-taf/menu-eng.html");

URLConnection conn = url.openConnection();

BufferedReader buffRead = new BufferedReader(new InputStreamReader(conn.getInputStream()));

StringBuffer buffer = new StringBuffer("");

String inputLine = "";

// Append the site in a buffer

while (inputLine != null){

inputLine = buffRead.readLine();

buffer.append(inputLine);

}

Document doc = Jsoup.parse(buffer.toString());

// Parse the table

Element table = doc.select("table[class=bwt]").first();

//Office elements iterator

Iterator officeElements = table.select("td[headers=Office]").iterator();

//Commercial Flow iterator

Iterator comElements = table.select("td[headers=Com ComCanada]").iterator();

//Travellers Flow iterator

Iterator travElements = table.select("td[headers=Trav TravCanada]").iterator();

// Iterate all elements through first element row for all columns

while(officeElements.hasNext()){

System.out.println("Office: " + officeElements.next().text());

System.out.println("Commercial Flow: " + comElements.next().text());

System.out.println("Travellers Flow: " + travElements.next().text());

}

}

catch (Exception e){

System.out.println("Exc:"+e.getMessage());

}

}

}

`