为了爬妹子图去学python, 学麻木了, 用老本行语言试着写了一下

被遗忘的路人 · 发表于 2020-6-9 16:24

本帖最后由被遗忘的路人于 2020-6-22 15:56 编辑

前段时间弄那个python爬妹子图,有个前端的小伙伴问我能不能用前端的语音写一份,今天补上

本来上个月都发出来了,弄着弄着IP让禁了,一直没管,今天没事干打开一看好了,接着继续弄!

不会因为新建文件夹名字错误停止运行,小伙伴不用操心!

我这字是不是特别大?没事,我女朋友说我无论哪里都大!

一楼给放个使用教程

[JavaScript] 纯文本查看 复制代码

const fs = require("fs");
const https = require("https");
const cheerio = require("cheerio");
const request = require("request");

const requestUrl = "https://www.mzitu.com/";

// 规避文件命名
const regEx = new RegExp("[`~!@#$^&*()=|{}':;',\\[\\].<>/?~！@#￥……&*（）&;|{}【】‘；：”“'。，、？]");

// 请求头部信息
const option = {
    headers: {
        "referer": requestUrl,
        "pragma": "no-cache",
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3314.0 Safari/537.36 SE 2.X MetaSr 1.0"
    }
};

// 开始请求
const requestPlay = () => {
    https.get(requestUrl, option, (res) => {
        let thisHtml = "";
        res.on("data", function (callbackDom) {
            thisHtml += callbackDom;
        });
        res.on("end", function () {
            getPage(thisHtml);
        });
    });
};

// 获取一共有多少页
const getPage = (pageDom) => {
    let $ = cheerio.load(pageDom); // 解析HTML
    let maxPage = Number($(".pagination").find(".nav-links").find(".next").prev().text()); // 总共有多少页
    let pageArr = [];
    pageArr.push(requestUrl);
    for (let i = 2; i <= maxPage; i++) {
        pageArr.push(requestUrl + "page/" + i + "/");
    }
    getPicture(0, pageArr);
};

// 获取每页里面有多少套图
const getPicture = (palyIndex, pageArr) => {
    let requestUrl = pageArr[palyIndex];
    https.get(requestUrl, option, (res) => {
        let thisPicture = "";
        res.on("data", function (callbackDom) {
            thisPicture += callbackDom;
        });
        res.on("end", function () {
            let pictureArr = [];
            let $ = cheerio.load(thisPicture);
            let pictureDom = $("#pins").find("li");
            for (let i = 0; i < pictureDom.length; i++) {
                pictureArr.push({
                    name: pictureDom.eq(i).find("img").attr("alt"),
                    href: pictureDom.eq(i).find("a").attr("href")
                });
            }
            requestPicture(pictureArr, 0, ++palyIndex, pageArr);
        });
    });
};

// 请求每个套图图片
const requestPicture = (Picture, pictureIndex, palyIndex, pageArr) => {
    let requestUrl = Picture[pictureIndex].href;
    https.get(requestUrl, option, (res) => {
        let thisHtml = "";
        res.on("data", function (callbackDom) {
            thisHtml += callbackDom;
        });
        res.on("end", function () {
            pictureDom(Picture, pictureIndex, palyIndex, pageArr, thisHtml);
        });
    });
};

// 处理套图里面的图片
const pictureDom = (Picture, pictureIndex, palyIndex, pageArr, thisHtml) => {
    let $ = cheerio.load(thisHtml);
    let pictureSrc = $(".main-image").find("img").attr("src"); // 获取装载图片的节点个数
    downloadImg(Picture[pictureIndex].name, pictureSrc);
    let nextPage = $(".main-image").find("a").attr("href");
    if (nextPage.indexOf(Picture[pictureIndex].href) !== -1) {
        setTimeout(() => {
            https.get(nextPage, option, function (res) {
                let thisHtml = "";
                res.on("data", function (callbackDom) {
                    thisHtml += callbackDom;
                });
                res.on("end", function () {
                    pictureDom(Picture, pictureIndex, palyIndex, pageArr, thisHtml);
                });
            })
        }, 3000);
    } else {
        if (++pictureIndex < Picture.length) {
            pictureDom(Picture, pictureIndex, palyIndex, pageArr, thisHtml);
        } else {
            getPicture(palyIndex, pageArr);
        }
    }
};

const dealNmae = (name) => {
    let newName = "";
    for (let i = 0; i < name.length; i++) {
        newName = newName + name.substr(i,1).replace(regEx,'');
    }
    return newName;
};

// 下载图片
const downloadImg = (folderName, imgSrc) => {
    let newFolderName = dealNmae(folderName);
    if (!fs.existsSync(newFolderName)) {
        fs.mkdirSync(newFolderName);
    }
    let imgName = imgSrc.split("/").pop();
    request(imgSrc, option, (err,res) => {
        if(!err && res.statusCode === 200){
            console.info("文件夹名称【" + newFolderName + "】图片链接: " + imgSrc + " 已爬取完成!");
        }
    }).pipe(fs.createWriteStream(newFolderName + "/" + imgName));

};

// 调用开始请求
requestPlay();

再来一个爬自拍图的

[JavaScript] 纯文本查看 复制代码

const fs = require("fs");
const https = require("https");
const cheerio = require("cheerio");
const request = require("request");

const requestServerUrl = "https://自拍图.xyz/";

// 规避文件命名
const regEx = new RegExp("[`~!@#$^&*()=|{}':;',\\[\\].<>/?~！@#￥……&*（）&;|{}【】‘；：”“'。，、？]");

// 请求头部信息
const option = {
    headers: {
        "referer": "https://xn--wcsr8yy8y.xyz/",
        "pragma": "no-cache",
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3314.0 Safari/537.36 SE 2.X MetaSr 1.0"
    }
};

// 开始请求
const requestPlay = () => {
    https.get(requestServerUrl, option, (res) => {
        let thisHtml = "";
        res.on("data", function (callbackDom) {
            thisHtml += callbackDom;
        });
        res.on("end", function () {
            getPage(thisHtml);
        });
    });
};

// 获取一共有多少页
const getPage = (pageDom) => {
    let $ = cheerio.load(pageDom); // 解析HTML
    let maxPage = Number($(".num").text().split("/").pop()); // 总共有多少页
    let pageArr = [];
    pageArr.push(requestServerUrl);
    for (let i = 2; i <= maxPage; i++) {
        pageArr.push(requestServerUrl + "index_" + i + ".html");
    }
    getPicture(0, pageArr);
};

// 获取每页里面有多少套图
const getPicture = (palyIndex, pageArr) => {
    let requestUrl = pageArr[palyIndex];
    https.get(requestUrl, option, (res) => {
        let thisPicture = "";
        res.on("data", function (callbackDom) {
            thisPicture += callbackDom;
        });
        res.on("end", function () {
            let pictureArr = [];
            let $ = cheerio.load(thisPicture);
            let pictureDom = $("#tiles").find("li");
            for (let i = 0; i < pictureDom.length; i++) {
                pictureArr.push({
                    name: pictureDom.eq(i).find("a").text(),
                    href: requestServerUrl + JSON.stringify(pictureDom.eq(i) + '0').split(''')[1]
                });
            }
            requestPicture(pictureArr, 0, ++palyIndex, pageArr);
        });
    });
};

// 请求每个套图图片
const requestPicture = (Picture, pictureIndex, palyIndex, pageArr) => {
    let requestUrl = Picture[pictureIndex].href;
    https.get(requestUrl, option, (res) => {
        let thisHtml = "";
        res.on("data", function (callbackDom) {
            thisHtml += callbackDom;
        });
        res.on("end", function () {
            pictureDom(Picture, pictureIndex, palyIndex, pageArr, thisHtml);
        });
    });
};

// 处理套图里面的图片
const pictureDom = (Picture, pictureIndex, palyIndex, pageArr, thisHtml) => {
    let pictureArr = [];
    let playPicture = 0;
    let $ = cheerio.load(thisHtml);
    let pictureLen = $(".artical-content").find("img").length; // 获取装载图片的节点个数
    for (let i = 0; i < pictureLen; i++) {
        pictureArr.push($(".artical-content").find("img").eq(i).attr("src"));
    }
    let setDownloadImg = setInterval(() => {
        if (playPicture < pictureLen) {
            downloadImg(Picture[pictureIndex].name, pictureArr[playPicture]);
            ++playPicture;
        } else {
            clearInterval(setDownloadImg);
            if (++pictureIndex < Picture.length) {
                requestPicture(Picture, pictureIndex, palyIndex, pageArr);
            } else {
                getPicture(palyIndex, pageArr);
            }
        }
    }, 2000);
};

const dealNmae = (name) => {
    let newName = "";
    for (let i = 0; i < name.length; i++) {
        newName = newName + name.substr(i, 1).replace(regEx, '');
    }
    return newName;
};

// 下载图片
const downloadImg = (folderName, imgSrc) => {
    let newFolderName = dealNmae(folderName);
    if (!fs.existsSync(newFolderName)) {
        fs.mkdirSync(newFolderName);
    }
    let imgName = imgSrc.split("/").pop();
    request(imgSrc, option, (err, res) => {
        if (!err && res.statusCode === 200) {
            console.info("文件夹名称【" + newFolderName + "】图片链接: " + imgSrc + " 已爬取完成!");
        }
    }).pipe(fs.createWriteStream(newFolderName + "/" + imgName));

};

// 调用开始请求
requestPlay();

xiaohanGG · 发表于 2020-6-22 16:53

本帖最后由 xiaohanGG 于 2020-6-22 16:54 编辑

"C:\Program Files\nodejs\node.exe" E:\webstorm\mzt\index.js
E:\webstorm\mzt\index.js:60
href: requestServerUrl + JSON.stringify(pictureDom.eq(i) + '0').split(''')[1]
^^

SyntaxError: missing ) after argument list
at wrapSafe (internal/modules/cjs/loader.js:1054:16)
at Module._compile (internal/modules/cjs/loader.js:1102:27)
at Object.Module._extensions..js (internal/modules/cjs/loader.js:1158:10)
at Module.load (internal/modules/cjs/loader.js:986:32)
at Function.Module._load (internal/modules/cjs/loader.js:879:14)
at Function.executeUserEntryPoint [as runMain] (internal/modules/run_main.js:71:12)
at internal/main/run_main_module.js:17:47

进程已结束，退出代码 1

xiaohanGG · 发表于 2020-6-22 15:52

大佬看一下。运行不了。报错
"C:\Program Files\nodejs\node.exe" E:\webstorm\mzt\index.js
internal/modules/cjs/loader.js:969
  throw err;
  ^

Error: Cannot find module 'cheerio'
Require stack:
- E:\webstorm\mzt\index.js
at Function.Module._resolveFilename (internal/modules/cjs/loader.js:966:15)
at Function.Module._load (internal/modules/cjs/loader.js:842:27)
at Module.require (internal/modules/cjs/loader.js:1026:19)
at require (internal/modules/cjs/helpers.js:72:18)
at Object.<anonymous> (E:\webstorm\mzt\index.js:3:17)
at Module._compile (internal/modules/cjs/loader.js:1138:30)
at Object.Module._extensions..js (internal/modules/cjs/loader.js:1158:10)
at Module.load (internal/modules/cjs/loader.js:986:32)
at Function.Module._load (internal/modules/cjs/loader.js:879:14)
at Function.executeUserEntryPoint [as runMain] (internal/modules/run_main.js:71:12) {
  code: 'MODULE_NOT_FOUND',
  requireStack: [ 'E:\\webstorm\\mzt\\index.js' ]
}

进程已结束，退出代码 1

被遗忘的路人 · 发表于 2020-6-9 16:25

本帖最后由被遗忘的路人于 2020-6-10 09:39 编辑

我自己的运行方式:
1. 安装nodeJS 链接:https://nodejs.org/dist/v12.18.0/node-v12.18.0-x64.msi

2.安装webstorm 链接:https://www.jetbrains.com/webstorm/download/download-thanks.html

3.桌面新建 webstorm 文件夹

4.打开安装好的webstorm软件,目录选择刚才新建的 webstorm 文件夹

5.在webstorm文件夹里面新建项目名文件夹,比如 mzt

5.在项目名文件夹,右击新建 package.json 文件

6.在项目名文件夹,右击新建 index.js 文件,并且粘贴代码

7.在 index.js 编辑状态里面右击选择 Run 'index.js' 启动

这好像就是全部了

漁滒 · 发表于 2020-6-9 16:27

这是nodejs吗？以后有准备学习的计划

流浪星空 · 发表于 2020-6-9 16:28

社会的进步大多都是应为欲望

1983 · 发表于 2020-6-9 16:36

哈哈哈，4楼说的很对

被遗忘的路人 · 发表于 2020-6-9 16:36

aiai 发表于 2020-6-9 16:27
这是nodejs吗？以后有准备学习的计划

是的 nodeJS

ankoku · 发表于 2020-6-9 16:37

这是python？怎么感觉像是Nodejs？

kesai · 发表于 2020-6-9 16:37

高手高手啊

被遗忘的路人 · 发表于 2020-6-9 16:37

流浪星空发表于 2020-6-9 16:28
社会的进步大多都是应为欲望

我是为了学习,欲望是其次

被遗忘的路人 · 发表于 2020-6-9 16:38

kesai 发表于 2020-6-9 16:37
高手高手啊

你的头像很好看,小妹妹

帐号		自动登录	找回密码
密码			注册[Register]

[其他转载] 为了爬妹子图去学python, 学麻木了, 用老本行语言试着写了一下

免费评分

本帖被以下淘专辑推荐:

个人中心