java抓取網頁數據獲取網頁中所有的鏈接實例分享

效果圖



代碼如下：

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class HtmlParser {
 /**
  * 要分析的網頁
  */
 String htmlUrl;

 /**
  * 分析結果
  */
 ArrayList<String> hrefList = new ArrayList();

 /**
  * 網頁編碼方式
  */
 String charSet;

 public HtmlParser(String htmlUrl) {
  // TODO 自動生成的構造函數存根
  this.htmlUrl = htmlUrl;
 }

 /**
  * 獲取分析結果
  *
  * @throws IOException
  */
 public ArrayList<String> getHrefList() throws IOException {

  parser();
  return hrefList;
 }

 /**
  * 解析網頁鏈接
  *
  * @return
  * @throws IOException
  */
 private void parser() throws IOException {
  URL url = new URL(htmlUrl);
  HttpURLConnection connection = (HttpURLConnection) url.openConnection();
  connection.setDoOutput(true);

  String contenttype = connection.getContentType();
  charSet = getCharset(contenttype);

  InputStreamReader isr = new InputStreamReader(
    connection.getInputStream(), charSet);
  BufferedReader br = new BufferedReader(isr);

  String str = null, rs = null;
  while ((str = br.readLine()) != null) {
   rs = getHref(str);

   if (rs != null)
    hrefList.add(rs);
  }

 }

 /**
  * 獲取網頁編碼方式
  *
  * @param str
  */
 private String getCharset(String str) {
  Pattern pattern = Pattern.compile("charset=.*");
  Matcher matcher = pattern.matcher(str);
  if (matcher.find())
   return matcher.group(0).split("charset=")[1];
  return null;
 }

 /**
  * 從一行字符串中讀取鏈接
  *
  * @return
  */
 private String getHref(String str) {
  Pattern pattern = Pattern.compile("<a href=.*</a>");
  Matcher matcher = pattern.matcher(str);
  if (matcher.find())
   return matcher.group(0);
  return null;
 }

 public static void main(String[] arg) throws IOException {
  HtmlParser a = new HtmlParser("http://news.163.com/");
  ArrayList<String> hrefList = a.getHrefList();
  for (int i = 0; i < hrefList.size(); i++)
   System.out.println(hrefList.get(i));

 }

}