Java实现爬取百度图片的方法分析

private static List<JsoupImageVO> findImageNoURl(String hotelId, String url, int timeOut) {
    List<JsoupImageVO> result = new ArrayList<JsoupImageVO>();
    Document document = null;
    try {
      document = Jsoup.connect(url).data("query", "Java")//请求参数
          .userAgent("Mozilla/4.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)")//设置urer-agent get();
          .timeout(timeOut)
          .get();
      String xmlSource = document.toString();
      result = dealResult(xmlSource, hotelId);
    } catch (Exception e) {
      String defaultURL = "http://qnimg.zowoyoo.com/img/15463/1509533934407.jpg";
      result = dealResult(defaultURL,hotelId);
    }
    return result;
}

public static List<JsoupImageVO> findImage(String hotelName, String hotelId, int page) {
    int number=5;
    String url = "http://image.baidu.com/search/avatarjson?tn=resultjsonavatarnew&ie=utf-8&word=" + hotelName + "&cg=star&pn=" + page * 30 + "&rn="+number+"&itg=0&z=0&fr=&width=&height=&lm=-1&ic=0&s=0&st=-1&gsm=" + Integer.toHexString(page * 30);
    int timeOut = 5000;
    return findImageNoURl(hotelId, url, timeOut);
}

private static List<JsoupImageVO> dealResult(String xmlSource, String hotelId) {
    List<JsoupImageVO> result = new ArrayList<JsoupImageVO>();
    xmlSource = StringEscapeUtils.unescapeHtml3(xmlSource);
    String reg = "objURL\":\"http://.+?\\.(gif|jpeg|png|jpg|bmp)";
    Pattern pattern = Pattern.compile(reg);
    Matcher m = pattern.matcher(xmlSource);
    while (m.find()) {
      JsoupImageVO jsoupImageVO = new JsoupImageVO();
      String imageURL = m.group().substring(9);
      if(imageURL==null || "".equals(imageURL)){
        String defaultURL = "http://qnimg.zowoyoo.com/img/15463/1509533934407.jpg";
        jsoupImageVO.setUrl(defaultURL);
      }else{
        jsoupImageVO.setUrl(imageURL);
      }
      jsoupImageVO.setName(hotelId);
      result.add(jsoupImageVO);
    }
    return result;
}

//根据图片网络地址下载图片
public static void download(String url,String name,String path){
    File file= null;
    File dirFile=null;
    FileOutputStream fos=null;
    HttpURLConnection httpCon = null;
    URLConnection con = null;
    URL urlObj=null;
    InputStream in =null;
    byte[] size = new byte[1024];
    int num=0;
    try {
      dirFile = new File(path);
      if(dirFile.exists()){
        dirFile.delete();
      }
      dirFile.mkdir();
      file = new File(path+"//"+name+".jpg");
      fos = new FileOutputStream(file);
      if(url.startsWith("http")){
        urlObj = new URL(url);
        con = urlObj.openConnection();
        httpCon =(HttpURLConnection) con;
        in = httpCon.getInputStream();
        while((num=in.read(size)) != -1){
          for(int i=0;i<num;i++)
            fos.write(size[i]);
        }
      }
    }catch (FileNotFoundException notFoundE) {
      LogUtils.writeLog("找不到该网络图片....");
    }catch(NullPointerException nullPointerE){
      LogUtils.writeLog("找不到该网络图片....");
    }catch(IOException ioE){
      LogUtils.writeLog("产生IO异常.....");
    }catch (Exception e) {
      e.printStackTrace();
    }finally{
      try {
        fos.close();
      } catch (Exception e) {
        e.printStackTrace();
      }
    }
}