Java如何取得http和https網址對應html資料（附程式碼）

這篇文章帶給大家的內容是關於Java如何取得http和https網址對應html資料（附程式碼），有一定的參考價值，有需要的朋友可以參考一下，希望對你有幫助。

由於先前在公司一直用的C#做的軟體開發，近些天有同學需要用Java來做一個從指定網址取得資訊的Java程式。正好不是很難，順便複習了一下Java的知識。

要求如下，在https://www.marinetraffic.com/en/ais/details/ships/shipid:650235/mmsi:414726000/vessel:YU MING網址中得到如下圖框中標記的數據。

程式如下：GetWebPosition類別是主要程式類別

package yinhang.wang;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.URL;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import javax.net.ssl.HttpsURLConnection;
import javax.net.ssl.SSLContext;
import javax.net.ssl.SSLSocketFactory;
import javax.net.ssl.TrustManager;
public class GetWebPosition {
    /**
     * @param args
     */
    public static void main(String[] args) {
        // TODO Auto-generated method stub
        String info = GetDataByTwo();
        System.out.println(info);
    }
    // 从指定的url中获取数据
    //https://www.marinetraffic.com/en/ais/details/ships/shipid:650235/mmsi:414726000/vessel:YU%20MING
        private static String HttpRequest(String requestUrl) {
   
            StringBuffer buffer = null;
            BufferedReader bufferedReader = null;
            InputStreamReader inputStreamReader = null;
            InputStream inputStream = null;
            HttpsURLConnection httpUrlConn = null;
            // 建立并向网页发送请求
            try {
                TrustManager[] tm = { new MyX509TrustManager() };
                SSLContext sslContext = SSLContext.getInstance("SSL", "SunJSSE");
                sslContext.init(null, tm, new java.security.SecureRandom());
                // 从上述SSLContext对象中得到SSLSocketFactory对象
                SSLSocketFactory ssf = sslContext.getSocketFactory();
                URL url = new URL(requestUrl);
                // 描述状态
                httpUrlConn = (HttpsURLConnection) url.openConnection();
                httpUrlConn.setSSLSocketFactory(ssf);
                httpUrlConn
                .setRequestProperty("User-Agent", "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36)");
                //防止报403错误。
                httpUrlConn.setDoOutput(true);
                httpUrlConn.setDoInput(true);
                httpUrlConn.setUseCaches(false);
                // 请求的类型
                httpUrlConn.setRequestMethod("GET");
                // 获取输入流
                inputStream = httpUrlConn.getInputStream();
                inputStreamReader = new InputStreamReader(inputStream, "utf-8");
                bufferedReader = new BufferedReader(inputStreamReader);
                // 从输入流读取结果
                buffer = new StringBuffer();
                String str = null;
                while ((str = bufferedReader.readLine()) != null) {
                    buffer.append(str);
                }
            } catch (Exception e) {
                e.printStackTrace();
            } finally {
                // 释放资源
                if (bufferedReader != null) {
                    try {
                        bufferedReader.close();
                    } catch (IOException e) {
                        e.printStackTrace();
                    }
                }
                if (inputStreamReader != null) {
                    try {
                        inputStreamReader.close();
                    } catch (IOException e) {
                        e.printStackTrace();
                    }
                }
                if (inputStream != null) {
                    try {
                        inputStream.close();
                    } catch (IOException e) {
                        e.printStackTrace();
                    }
                }
                if (httpUrlConn != null) {
                    httpUrlConn.disconnect();
                }
            }
            return buffer.toString();
        }　

private static String HtmlFiter(String html) {

        StringBuffer buffer = new StringBuffer();
        String str1 = "";
        String str2 = "";
        //取出所用的范围,
       
 //Pattern p = Pattern.compile("(.*)(<p class=\"panel panel-primary 
no-border vertical-offset-20\">)(.*)(</p>)(.*)");
        Pattern p = Pattern.compile("(.*)(</script>)(.*)(<p class=\"wind_icon wind_low\")(.*)");
        Matcher m = p.matcher(html);
        if (m.matches()) {
            str1 = m.group(3);
            //取得时间：Vessel&#39;s Local Time:
            p = Pattern.compile("(.*)(time datetime=\")(.*)(\">)(.*)(</time>)(.*)(</span></strong>)(.*)");
            m = p.matcher(str1);
            if (m.matches()) {
                str2 = m.group(5);
                String str3 = m.group(7);
                buffer.append("\nVessel&#39;s Local Time: ");
                buffer.append(str2);
                buffer.append(str3);
                }
            // <a href="/en/ais/home/centerx:120.3903/centery:32.02979/zoom:10/mmsi:414726000/shipid:650235"
            // class="details_data_link">32.02979° / 120.3903°</a>
            //取得当前经纬度：Latitude / Longitude:
            p = Pattern.compile("(.*)(class=\"details_data_link\">)(.*)(</a></strong></span>)(.*)");
            m = p.matcher(str1);
            if (m.matches()) {
                str2 = m.group(3);
                buffer.append("\nLatitude / Longitude: ");
                buffer.append(str2);
            }
            //取得当前速度航线Speed/Course:
            p = Pattern.compile("(.*)(<span><strong>)(.*)(</strong></span>)(.*)");
            m = p.matcher(str1);
            if (m.matches()) {
                str2 = m.group(3);
                buffer.append("\nSpeed/Course: ");
                buffer.append(str2);
            }
            }
        return buffer.toString();
    }
        //封裝上述两个方法
        public static String GetDataByTwo(){
            //调用第一个方法,获得html字符串
  
          String html = 
HttpRequest("https://www.marinetraffic.com/en/ais/details/ships/shipid:650235/mmsi:414726000/vessel:YU%20MING");
            //调用第二个方法,过滤掉无用的信息
            String result = HtmlFiter(html);
            return result;
        }
}

MyX509TrustManager這個類別的作用是提供安全性憑證去存取https類型的網站

package yinhang.wang;
 
import java.security.cert.CertificateException;
import java.security.cert.X509Certificate;
 
import javax.net.ssl.X509TrustManager;
 
public class MyX509TrustManager implements X509TrustManager {
    public void checkClientTrusted(X509Certificate[] chain, String authType)
            throws CertificateException
          {
          }
 
          public void checkServerTrusted(X509Certificate[] chain, String authType)
            throws CertificateException
          {
          }
 
          public X509Certificate[] getAcceptedIssuers()
          {
            return null;
          }
}

希望初步學習正規表示式和爬資料的小夥伴們能夠用到。

以上是Java如何取得http和https網址對應html資料（附程式碼）的詳細內容。更多資訊請關注PHP中文網其他相關文章！