java爬取图片

import java.io.BufferedReader;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.URL;
import java.util.HashSet;
import java.util.Set;

public class CrawlerPic {

	private static Set<String> imgs = new HashSet<String>();

	public static void main(String[] args) throws IOException {
		URL url = new URL("https://www.qq.com/");
		BufferedReader br = new BufferedReader(new InputStreamReader(url.openStream()));
		String s;
		while ((s = br.readLine()) != null) {
			System.out.println(s);
			if (s.indexOf("<img") != -1) {
				int i = s.indexOf("<img");
				int j = i;
				while (true) {
					char ch = s.charAt(j++);
					if (ch == '>')
						break;
				}
				String img = s.substring(i, j);
				img = img.substring(1, img.length() - 1);			

				String[] imgs = img.split("\" ");
				for (String string : imgs) {
					i = 0;
					while (i != -1) {
						i = string.indexOf("src=");
						if (i != -1) {
							img = string.substring(i + 5);
//							writeToFile(img);
						}
						if ((i = string.indexOf("data-src=")) != -1) {
							img = string.substring(i + 10);
//							writeToFile(img);
						}
						if ((i = string.indexOf("data-original=")) != -1) {
							img = string.substring(i + 15);
//							writeToFile(img);
						}
						i = -1;
					}
				}

			}
		}
		System.out.println(imgs);
	}

	private static void writeToFile(String img) {
		img = img.trim();
		if (img.length() == 0) {
			return;
		}
		if (imgs.contains(img))
			return;
		imgs.add(img);

		if (img.charAt(img.length() - 1) == '"')
			img = img.substring(0, img.length() - 1);
		String fileName = img.substring(img.lastIndexOf("/") + 1);
		if (fileName.indexOf(".") == -1) {
			String[] url = img.split("[/]");
			fileName = url[url.length - 2] + "_" + url[url.length - 1] + ".png";
		}
//		System.out.println(fileName);
		InputStream in = null;
		FileOutputStream out = null;
		try {
			if (!img.startsWith("http"))
				img = "https:" + img;
			URL url = new URL(img);
			in = url.openStream();

			out = new FileOutputStream("E:/tmp/" + fileName);
			int i = 0;
			while ((i = in.read()) != -1) {
				out.write(i);
			}
		} catch (Exception e) {
			System.err.println(e.getMessage());
		} finally {
			if (out != null)
				try {
					out.close();
				} catch (Exception e) {
				
				}
		}

	}
}

 

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值