【 java 爬虫】

1.引入Maven

   org.jsoup
   jsoup
   1.8.3
 

      2. 用法

public void test() {
		//地址：
        String url  ="https://www.*******.cn/";
        Connection tempConn = Jsoup.connect(url);
        //模拟浏览器的请求头
        tempConn.header("User-Agent", "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:29.0) Gecko/20100101 Firefox/29.0");
        //开始连接HTTP请求。
        Connection.Response response;
		try {
			response = tempConn.ignoreContentType(true).method(Connection.Method.GET)
			        .execute();
			document documentDemo = response.parse();
			//获取该页面的HTML元素。
			String str = documentDemo.toString();
            System.out.println(str);
            //正则匹配
            Pattern pattern = Pattern.compile("https:/[0-9]{4}/[0-9]{2}/[0-9]{2}/[A-Za-z]+[0-9]+.shtml");
			Matcher matcher = pattern.matcher(str);
			while(matcher.find()) {
				System.out.println(matcher.group());
			}
		} catch (IOException e) {
			e.printStackTrace();
		}  
		
	}