|
|
package download;
import java.io.DataInputStream;
import java.io.File;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
import org.apache.commons.io.input.ReaderInputStream;
import org.openqa.selenium.By;
import org.openqa.selenium.WebDriver;
import org.openqa.selenium.WebElement;
import org.openqa.selenium.chrome.ChromeDriver;
public class Geturl {
public static List<String> geturls(String baseUrl){
List<String> urllist=new ArrayList<String>();
System.setProperty("webdriver.chrome.driver", "E:\\\\webDriver\\\\chromedriverV2.28.exe");
WebDriver driver = new ChromeDriver();
driver.get(baseUrl);
//获取所有img标签
List<WebElement> imgList = driver.findElements(By.tagName("img"));
System.out.println(imgList.size());
try {
Thread.sleep(10000);
} catch (Exception e) {
e.printStackTrace();
}
//便利所有标签
try {
for (WebElement a : imgList) {
//System.out.println(a.getText());
System.out.println(a.getAttribute("src"));//获取img标签中的data-imgurl data-imgurl
//获取img标签data-imgurl属性值
String urlStr = a.getAttribute("src");
/*if(urlStr.contains(".jpg")) {
urllist.add(urlStr);
}*/
}
} catch (Exception e) {
e.printStackTrace();
}
return urllist;
}
public static void downloadImg(List<String> urllist) throws Exception{
URL url=null;
int imageNumber = 0;
for(String urlString:urllist) {
url = new URL(urlString);
DataInputStream dis = new DataInputStream(url.openStream());
String imageName ="C:\\Users\\0\\Pictures\\插画\\photos"+ imageNumber +".jpg";
FileOutputStream fos =new FileOutputStream(new File(imageName));
byte[] buffer = new byte[1024];
int length;
while((length = dis.read(buffer))>0) {
fos.write(buffer, 0, length);
}
dis.close();
fos.close();
imageNumber++;
}
}
public static void main(String[] args) {
List<String> urllist=geturls("https://image.baidu.com/search/index?tn=baiduimage&ct=201326592&lm=-1&cl=2&ie=gbk&word=%B2%E5%BB%AD&fr=ala&ala=1&alatpl=adress&pos=0&hs=2&xthttps=111111");
System.out.println(urllist.size());
try {
downloadImg(urllist);
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
|
程序猿的技术大观园：www.javathinker.net
[这个贴子最后由 sunweiqin 在 2020-01-10 10:55:46 重新编辑]
|
|
Java技术网站 → 『 Java开发技术 』 → 『 Java编程技术专题 』 → 用Selenium 爬虫API和java.net.URL类保存网页上的图片
消息
查看
搜索
好友
邮件
复制
引用
IP: 已设置保密
