從百度圖片下載原圖

環境

• Google瀏覽器
• selenium
  selenium可以模仿操作瀏覽器的過程。這裏使用selenium的原因主要是因爲使用JSoup暫時沒有找到百度圖片原圖鏈接。查看頁面源碼，可以發現圖片是動態加載出來的。
  

需要注意的是: selenium的版本要和chrome瀏覽器的版本匹配。下面的這條鏈接可以參考一下。

selenium之 chromedriver與chrome版本映射表（更新至v2.43）
【https://blog.csdn.net/qq_40374604/article/details/84430963】

下圖爲項目的結構。需要引入selenium jar包, 以及Chromedriver.exe

F12觀察頁面元素

這個過程就不多說了，選定一個元素從上到下所有的url全部試一遍。

編寫程序

這個沒什麼好說的，只要找對了頁面元素並獲取，都沒什麼問題。
這裏用到了一個頁面滾動的操作。
((JavascriptExecutor) connWeb).executeScript("window.scrollBy(0, document.body.scrollHeight)");
可以參考下面的鏈接：

Selenium之Web頁面滾動條滾操作
【https://blog.csdn.net/jlminghui/article/details/50477283】

package com.nikolazhang.spider;

import java.io.File;
import java.io.IOException;
import java.io.InputStream;
import java.util.Iterator;
import java.util.List;
import java.util.Scanner;

import org.openqa.selenium.By;
import org.openqa.selenium.JavascriptExecutor;
import org.openqa.selenium.WebDriver;
import org.openqa.selenium.WebElement;
import org.openqa.selenium.chrome.ChromeDriver;
import org.openqa.selenium.interactions.Actions;

import com.nikolazhang.util.FileDownload;
import com.nikolazhang.util.HttpRequestUtil;


public class SpiderPicFromBaidu {
	private static int cnt = 0;
	
	public static void main(String[] args) throws IOException {
		Scanner scanner = new Scanner(System.in);
		System.out.println("請輸入參數[參數之間使用一個空格分割] , 回車執行!");		
		String[] params = scanner.nextLine().split(" ");
		String filepath = params[0];
		String keywords = params[1];
		int count = Integer.valueOf(params[2]);
		if(count<=0) {
			System.out.println("下載數量必須大於零！！！程序退出");
			return;
		}
		
		String url = inputBaiduImageUrl(keywords);
		WebDriver connWeb = connWeb(url);
		Iterator<WebElement> imageUrl = null;
		for(int i = 1; i<=count/5; i++) {
			((JavascriptExecutor) connWeb).executeScript("window.scrollBy(0, document.body.scrollHeight)");
		}
		System.out.println("頁面元素加載中...請等待...!");
		try {
			Thread.sleep(count*10);
		} catch (InterruptedException e1) {
			e1.printStackTrace();
		}
		try {
			imageUrl = getImageUrl(connWeb);
		} catch (InterruptedException e) {
			e.printStackTrace();
		}
		if(imageUrl != null) {
			downloadImage(imageUrl, filepath);
		} else {
			System.out.println("圖片下載失敗!!!");
		}
		System.out.println("下載結束----退出瀏覽器!!!");
		connWeb.close();
	}
	
	/**
	 * 鏈接目標網站
	 * @param url
	 * @return
	 */
	public static WebDriver connWeb(String url) {
		System.setProperty("webdriver.chrome.driver", 
				"chromedriver.exe");
		WebDriver webDriver = new ChromeDriver();
		webDriver.get(url);
		System.out.println("*+*+*+*+* 已連接網站: 【"+webDriver.getTitle()+"】");
		return webDriver;
	}
	
	/**
	 * 輸入關鍵詞
	 */
	public static String inputBaiduImageUrl(String text) {
		String url = "https://image.baidu.com"
				+ "/search/index"
				+ "?tn=baiduimage"
				+ "&word="+text;
		return url;
	}
	
	public static Iterator<WebElement> getImageUrl(WebDriver webDriver) throws InterruptedException {
		Actions actions = new Actions(webDriver);
		List<WebElement> imgitem = webDriver.findElements(By.className("imgitem"));
		System.out.println("獲取到的相關的圖片數量: "+imgitem.size());
		Iterator<WebElement> imgItor = imgitem.iterator();
		return imgItor;
	}
	
		public static void downloadImage(Iterator<WebElement> imgItor, String filepath) {
		File file = new File(filepath);
		if(!file.exists()) {
			file.mkdirs();
		}
		while(imgItor.hasNext()) {
			WebElement nextImg = imgItor.next();
			String addrImg = nextImg.getAttribute("data-objurl");
			String filename =  ++cnt + "." + nextImg.getAttribute("data-ext");
			FileDownload.saveImageToDisk(addrImg, filepath+filename);
			System.out.println("下載第"+ cnt +"張圖片地址爲: "+addrImg);
		}
	}
}

• 文件下載公共類

package com.nikolazhang.util;

import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;

public class FileDownload {
	
	
	public static void saveImageToDisk(InputStream inputStream, String filepath) {
		byte[] data = new byte[1024];
		int len = 0;
		FileOutputStream fileOutputStream = null;
		try {
			fileOutputStream = new FileOutputStream(filepath);
			while ((len = inputStream.read(data)) != -1) {
				fileOutputStream.write(data, 0, len);
 
			}
		} catch (IOException e) {
			e.printStackTrace();
		} finally {
 
			if (inputStream != null) {
				try {
					inputStream.close();
				} catch (IOException e) {
					e.printStackTrace();
				}
			}
			if (fileOutputStream != null) {
				try {
					fileOutputStream.close();
				} catch (IOException e) {
					e.printStackTrace();
				}
			}
		}
 
	}
}

Http請求公共類：

package com.nikolazhang.util;

import java.io.BufferedReader;  
import java.io.IOException;
import java.io.InputStream;  
import java.io.InputStreamReader;  
import java.io.OutputStreamWriter;
import java.io.UnsupportedEncodingException;  
import java.net.HttpURLConnection;  
import java.net.InetSocketAddress;
import java.net.Proxy;
import java.net.URL; 
import java.net.URLConnection;
import java.util.List;
import java.util.Map;


/** 
 * Http請求工具類 
 */
public class HttpRequestUtil {
    static boolean proxySet = false;
    static String proxyHost = "127.0.0.1";
    static int proxyPort = 8087;
    /** 
     * 編碼 
     * @param source 
     * @return 
     */ 
    public static String urlEncode(String source,String encode) {  
        String result = source;  
        try {  
            result = java.net.URLEncoder.encode(source,encode);  
        } catch (UnsupportedEncodingException e) {  
            return "0";  
        }  
        return result;  
    }
    public static String urlEncodeGBK(String source) {  
        String result = source;  
        try {  
            result = java.net.URLEncoder.encode(source,"GBK");  
        } catch (UnsupportedEncodingException e) {  
            return "0";  
        }  
        return result;  
    }
    /** 
     * 發起http請求獲取返回結果 
     * @param req_url 請求地址 
     * @return 
     */ 
    public static String httpRequest(String req_url, String fmt) {
        StringBuffer buffer = new StringBuffer();  
        try {  
            URL url = new URL(req_url);  
            HttpURLConnection httpUrlConn = (HttpURLConnection) url.openConnection();  

            httpUrlConn.setDoOutput(false);  
            httpUrlConn.setDoInput(true);  
            httpUrlConn.setUseCaches(false);  

            httpUrlConn.setRequestMethod("GET");  
            httpUrlConn.connect();  

            // 將返回的輸入流轉換成字符串  
            InputStream inputStream = httpUrlConn.getInputStream();  
            InputStreamReader inputStreamReader = new InputStreamReader(inputStream, fmt);  
            BufferedReader bufferedReader = new BufferedReader(inputStreamReader);  

            String str = null;  
            while ((str = bufferedReader.readLine()) != null) {  
                buffer.append(str);  
            }  
            bufferedReader.close();  
            inputStreamReader.close();  
            // 釋放資源  
            inputStream.close();  
            inputStream = null;  
            httpUrlConn.disconnect();  

        } catch (Exception e) {  
        }  
        return buffer.toString();  
    }  

    /** 
     * 發送http請求取得返回的輸入流 
     * @param requestUrl 請求地址 
     * @return InputStream 
     */ 
    public static InputStream httpRequestIO(String requestUrl) {  
        InputStream inputStream = null;  
        try {  
            URL url = new URL(requestUrl);  
            HttpURLConnection httpUrlConn = (HttpURLConnection) url.openConnection();  
            httpUrlConn.setDoInput(true);  
            httpUrlConn.setRequestMethod("GET");  
            httpUrlConn.connect();  
            // 獲得返回的輸入流  
            inputStream = httpUrlConn.getInputStream();  
        } catch (Exception e) {  
        }  
        return inputStream;  
    }


    /**
     * 向指定URL發送GET方法的請求
     * 
     * @param url
     *            發送請求的URL
     * @param param
     *            請求參數，請求參數應該是 name1=value1&name2=value2 的形式。
     * @return URL 所代表遠程資源的響應結果
     */
    public static String sendGet(String url, String param) {
        String result = "";
        BufferedReader in = null;
        try {
            String urlNameString = url + "?" + param;
            URL realUrl = new URL(urlNameString);
            // 打開和URL之間的連接
            URLConnection connection = realUrl.openConnection();
            // 設置通用的請求屬性
            connection.setRequestProperty("accept", "*/*");
            connection.setRequestProperty("connection", "Keep-Alive");
            connection.setRequestProperty("user-agent",
                    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1;SV1)");
            // 建立實際的連接
            connection.connect();
            // 獲取所有響應頭字段
            Map<String, List<String>> map = connection.getHeaderFields();
            // 遍歷所有的響應頭字段
            // 定義 BufferedReader輸入流來讀取URL的響應
            in = new BufferedReader(new InputStreamReader(
                    connection.getInputStream()));
            String line;
            while ((line = in.readLine()) != null) {
                result += line;
            }
        } catch (Exception e) {
        }
        // 使用finally塊來關閉輸入流
        finally {
            try {
                if (in != null) {
                    in.close();
                }
            } catch (Exception e2) {
                e2.printStackTrace();
            }
        }
        return result;
    }

    /**
     * 向指定 URL 發送POST方法的請求
     * 
     * @param url
     *            發送請求的 URL
     * @param param
     *            請求參數，請求參數應該是 name1=value1&name2=value2 的形式。
     * @param isproxy
     *               是否使用代理模式
     * @return 所代表遠程資源的響應結果
     */
    public static String sendPost(String url, String param, String fmt,boolean isproxy) {
        OutputStreamWriter out = null;
        BufferedReader in = null;
        String result = "";
        try {
            URL realUrl = new URL(url);
            HttpURLConnection conn = null;
            if(isproxy){//使用代理模式
                @SuppressWarnings("static-access")
                Proxy proxy = new Proxy(Proxy.Type.DIRECT.HTTP, new InetSocketAddress(proxyHost, proxyPort));
                conn = (HttpURLConnection) realUrl.openConnection(proxy);
            }else{
                conn = (HttpURLConnection) realUrl.openConnection();
            }
            // 打開和URL之間的連接

            // 發送POST請求必須設置如下兩行
            conn.setDoOutput(true);
            conn.setDoInput(true);
            conn.setRequestMethod("POST");    // POST方法


            // 設置通用的請求屬性

//            conn.setRequestProperty("accept", "*/*");
//            conn.setRequestProperty("connection", "Keep-Alive");
//            conn.setRequestProperty("user-agent",
//                    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1;SV1)");
//            conn.setRequestProperty("Content-Type", "application/x-www-form-urlencoded");

            conn.connect();

            // 獲取URLConnection對象對應的輸出流
            out = new OutputStreamWriter(conn.getOutputStream(), fmt);
            // 發送請求參數
            out.write(param);
            // flush輸出流的緩衝
            out.flush();
            // 定義BufferedReader輸入流來讀取URL的響應
            in = new BufferedReader(
                    new InputStreamReader(conn.getInputStream()));
            String line;
            while ((line = in.readLine()) != null) {
                result += line;
            }
        } catch (Exception e) {
        }
        //使用finally塊來關閉輸出流、輸入流
        finally{
            try{
                if(out!=null){
                    out.close();
                }
                if(in!=null){
                    in.close();
                }
            }
            catch(IOException ex){
                ex.printStackTrace();
            }
        }
        return result;
    }    

    public static void main(String[] args) {
        //demo:代理訪問
        String url = "http://api.adf.ly/api.php";
        String para = "key=youkeyid&youuid=uid&advert_type=int&domain=adf.ly&url=http://somewebsite.com";

    }

}

以上程序可以在GitHub上獲取，CSDN上的代碼一般不會更新：
【https://github.com/NikolaZhang/PickPic】

運行

完美~~