宅男必会技能 springboot, jsoup,html,vue,axios抓取全站美女图片

1 温馨提示:jdk1.8+ ,准备好大硬盘,全站美女套图全归你

2 源码下载

码云:https://gitee.com/gao_zhenzhong/spring-boots/tree/master/ok/98-app/pictures

3 运行程序后 地址栏输入 http://localhost:9090 如下图所示

image.png

image.png

4 推荐使用ACDSee查看图片

5 准备纸巾

6 pom.xml

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
    xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <groupId>com.gzz</groupId>
    <artifactId>spring-boot-girl</artifactId>
    <version>1.0</version>
    <parent>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-parent</artifactId>
        <version>2.5.6</version>
    </parent>
    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <java.version>1.8</java.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter</artifactId>
        </dependency>
        <dependency>
            <groupId>org.jsoup</groupId>
            <artifactId>jsoup</artifactId>
            <version>1.14.3</version>
        </dependency>
        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
        </dependency>
    </dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.springframework.boot</groupId>
                <artifactId>spring-boot-maven-plugin</artifactId>
            </plugin>
        </plugins>
    </build>
    <repositories>
        <repository>
            <id>aliyunmaven</id>
            <name>aliyun</name>
            <url>https://maven.aliyun.com/repository/public</url>
        </repository>
    </repositories>
</project>

7 Application18.java

package com.gzz;

import java.text.DecimalFormat;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import com.gzz.utils.Utils;

import lombok.extern.slf4j.Slf4j;

@Slf4j
public class Application18 {
    private static String rootpath = "D:/aaa/";
    private static int num;
    private static DecimalFormat df = new DecimalFormat("00");
    private static String baseUrl = "https://www.wxytw.com/jgmntp/yuhuajie/page/";

    public static void main(String[] args) throws Exception {
        for (int i = 1; i < 34; i++) {
            Document document = Jsoup.connect(baseUrl + i).get();
//log.info(document);
            Elements selects = document.select("a.thumbnail");
            for (Element element : selects) {
                String href = element.attr("href");
                String setPath = element.select("img").first().attr("alt");
                log.info(setPath);
                Document pages = Jsoup.connect(href).get();
//log.info(document);
                Elements pics = pages.select("a.post-page-numbers");
                String pageNum = pics.last().select("span").first().text();
//log.info(pageNum);
                num = 0;
                for (int j = 1; j <= Integer.parseInt(pageNum); j++) {
                    pages = Jsoup.connect(href + "/" + j).get();
                    Elements images = pages.select(".article-content img");
                    for (Element image : images) {
//log.info(image.attr("src"));
                        String path = rootpath + setPath + "/" + df.format(num) + ".jpg";
                        Utils.down(image.attr("src"), path, href);
                        num++;
                    }
                }
            }
        }
    }
}

8 下载工具类

package com.gzz.utils;

import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.IOException;
import java.io.InputStream;
import java.net.URL;
import java.net.URLConnection;
import java.nio.file.Files;
import java.nio.file.Paths;

import lombok.extern.slf4j.Slf4j;

@Slf4j
public class Utils {
    public static void down(String url, String path, String referer) {
        try {
            File file = new File(path);
            if (!file.exists()) {
                URLConnection connection = new URL(url).openConnection();
                connection.setRequestProperty("Referer", referer);
                if (!file.getParentFile().exists())
                    file.getParentFile().mkdirs();
                ByteArrayOutputStream swapStream = new ByteArrayOutputStream();
                byte[] buff = new byte[1000];
                int rc = 0;
                InputStream inputStream = connection.getInputStream();
                while ((rc = inputStream.read(buff, 0, 1000)) > 0) {
                    swapStream.write(buff, 0, rc);
                }
                Files.write(Paths.get(path), swapStream.toByteArray());

                inputStream.close();
            }
        } catch (IOException e) {
            log.error("抛锚了...", path, url, e);
        }
    }
}

9 页面文件

<!DOCTYPE html>
<html>

<head>
    <meta charset="UTF-8">
    <title>down-picture</title>
</head>
<script type="text/javascript" src="vue.min.js"></script>
<script type="text/javascript" src="axios.min.js"></script>

<body>
    <div id="app">
        <template v-for="item in dicts" :key="item.url">
            <span style="width:220px;height:20; display:inline-block;border:1px solid black;padding:6px"  >
                <button :disabled="item.pageCount > '0'"  @click="queryCount(item)" style="width:130px;" >{{item.label}}[共{{item.pageCount}}页]</button>
                <button :disabled="!item.pageCount" @click="downPictures()">下载</button>
            </span>
        </template>
    </div>
    <script>
        axios.defaults.headers.post['Content-Type'] = 'application/json;charset=UTF-8';
        new Vue({
            el: '#app',
            data: function () {
                return { form: { setName: '', pageCount: '', setUrl: '', }, dicts: [], messages: [] }
            },
            created: function () { this.queryDicts(); },
            methods: {
                queryCount(item) {
                    console.log("item", item)
                    this.form.setName = item.label;
                    this.form.setUrl = item.url;
                    axios.post("/queryCount?url=" + item.url).then(res => {
                        if (res.data.code == 200) {
                            this.form.pageCount = res.data.data;
                            item.pageCount = res.data.data;
                        }
                        else this.$message.error(res.data.msg);
                    });
                },
                queryDicts() {
                    axios.post("/queryDicts").then(res => {
                        if (res.data.code == 200) { this.dicts = res.data.data; }
                        else this.$message.error(res.data.msg);
                    });
                },
                downPictures() {
                    axios.post("/downPictures", JSON.stringify(this.form)).then(res => {
                        if (res.data.code == 200) { this.$message.success('已开始下载有耐心等待') }
                        else this.$message.error(res.data.msg);
                    })
                },
            },
        });
    </script>
</body>

</html>
最后编辑于
©著作权归作者所有,转载或内容合作请联系作者
平台声明:文章内容(如有图片或视频亦包括在内)由作者上传并发布,文章内容仅代表作者本人观点,简书系信息发布平台,仅提供信息存储服务。

推荐阅读更多精彩内容