Node.js 4493图片批量下载爬虫1.00

//======================================================// 4493图片批量下载爬虫1.00// 2017年11月19日//======================================================// 内置https模块var https=require("https");// 内置http模块var http=require("http");// 内置文件处理模块，用于创建目录和图片文件var fs=require(‘fs‘);// 用于转码。非Utf8的网页如gb2132会有乱码问题，需要iconv将其转码var iconv = require(‘iconv-lite‘);// cheerio模块，提供了类似jQuery的功能，用于从HTML code中查找图片地址和下一页var cheerio = require("cheerio");// 请求参数JSON。http和https都有使用var options;// request请求var req;// 图片数组，找到的图片地址会放到这里var pictures=[];// 存放图片的目录var folder="";//--------------------------------------// 爬取网页，找图片地址，再爬// pageUrl sample:https://www.4493.com/xingganmote/136346/1.htm// pageUrl sample://--------------------------------------function crawl(pageUrl){ ???console.log("Current page="+pageUrl); ???// 得到hostname和path ???var currUrl=pageUrl.replace("https://",""); ???var pos=currUrl.indexOf("/"); ???var hostname=currUrl.slice(0,pos); ???????????var path=currUrl.slice(pos); ???????//console.log("hostname="+hostname); ???//console.log("path="+path); ???????// 初始化options ?????options={ ???????hostname:hostname, ???????????port:443, ???????????path:path,// 子路径 ?????????method:‘GET‘, ???????????}; ???req=https.request(options,function(resp){ ???????var html = []; ???????resp.on("data", function(data) { ???????????html.push(data); ???????}) ???????resp.on("end", function() { ???????????var buffer = Buffer.concat(html); ???????????var body = iconv.decode(buffer,‘gb2312‘); // header里面有<meta http-equiv="Content-Type" content="text/html; charset=gb2312">字样都需要iconv帮忙转码 ???????????//console.log(body); ???????????????????????var $ = cheerio.load(body); ???????????????????var picCount=0; ???????????// 找图片放入数组 ???????????$(".picsbox ?p img").each(function(index,element){ ???????????????var picUrl=$(element).attr("src"); ???????????????console.log(picUrl); ???????????????if(picUrl.indexOf(‘.jpg‘)!=-1){ ???????????????????pictures.push(picUrl); ????????????????????picCount++; ???????????????} ????????????}) ??????????????console.log("找到图片"+picCount+"张."); ???????????????????????????????????????var curr=0; ???????????$(".page a.current").each(function(index,element){ ???????????????var text=$(element).text(); ???????????????curr=parseInt(text); ???????????????//console.log("curr="+curr); ???????????}) ???????????var next=0; ???????????$("#nextpage").each(function(index,element){ ???????????????var text=$(element).attr("href"); ???????????????????????????????var reg=/javascript:gotourl[(]‘(\d+).htm‘[)]/g; ???????????????var res; ???????????????while((res = reg.exec(text)) != null){ ???????????????????next=parseInt(res[1]); ???????????????????//console.log("next="+next); ???????????????????????????????????} ??????????????}) ???????????var nextPageUrl=null; ???????????if(curr!=next){ ???????????????var pos=pageUrl.lastIndexOf("/"); ???????????????nextPageUrl= pageUrl.slice(0,pos+1)+next+".htm"; ???????????????//console.log("nextPageUrl="+nextPageUrl); ???????????} ???????????// 找下一页 ???????????if(nextPageUrl==null){ ???????????????console.log(pageUrl+"已经是最后一页了.\n"); ???????????????saveFile(pageUrl,pictures);// 保存 ???????????????download(pictures); ???????????}else{ ???????????????console.log("继续下一页"); ???????????????crawl(nextPageUrl); ???????????} ???????????????????}).on("error", function() { ???????????saveFile(pageUrl,pictures);// 保存 ???????????console.log("crawl函数失败,请进入断点续传模式继续进行"); ???????}) ???}); ???// 超时处理 ???req.setTimeout(7500,function(){ ???????req.abort(); ???}); ???// 出错处理 ???req.on(‘error‘,function(err){ ???????console.log(‘请求发生错误‘+err); ?????????saveFile(pageUrl,pictures);// 保存 ???????console.log("crawl函数失败,请进入断点续传模式继续进行"); ???}); ???// 请求结束 ???req.end();}//--------------------------------------// 下载图片//--------------------------------------function download(pictures){ ???var total=0; ???total=pictures.length; ???console.log("总计有"+total+"张图片将被下载."); ???appendToLogfile(folder,"总计有"+total+"张图片将被下载.\n"); ???for(var i=0;i<pictures.length;i++){ ???????var picUrl=pictures[i]; ???????downloadPic(picUrl,folder); ???}}//--------------------------------------// 写log文件//--------------------------------------function appendToLogfile(folder,text){ ???fs.appendFile(‘./‘+folder+‘/log.txt‘, text, function (err) { ???????if(err){ ???????????console.log("不能书写log文件"); ???????????console.log(err); ???????} ???});}//--------------------------------------// 取得当前时间//--------------------------------------function getNowFormatDate() { ???var date = new Date(); ???var seperator1 = "-"; ???var seperator2 = "_"; ???var month = date.getMonth() + 1; ???var strDate = date.getDate(); ???if (month >= 1 && month <= 9) { ???????month = "0" + month; ???} ???if (strDate >= 0 && strDate <= 9) { ???????strDate = "0" + strDate; ???} ???var currentdate =date.getFullYear() + seperator1 + month + seperator1 + strDate ???????????+ " " + date.getHours() + seperator2 + date.getMinutes() ???????????+ seperator2 + date.getSeconds(); ???return currentdate;}//--------------------------------------// 下载单张图片// picUrl sample:http://img.1985t.com/uploads/attaches/2017/11/136398-mrani71.jpg//--------------------------------------function downloadPic(picUrl,folder){ ???console.log("图片:"+picUrl+"下载开始"); ???// 得到hostname，path和port ???var currUrl=picUrl.replace("http://",""); ???var pos=currUrl.indexOf("/"); ???var hostname=currUrl.slice(0,pos); ???????????var path=currUrl.slice(pos); ???// 有端口加端口，没有端口默认80 ???var port=80; ???//console.log("hostname="+hostname); ???//console.log("path="+path); ???//console.log("port="+port); ???var picName=currUrl.slice(currUrl.lastIndexOf("/")); ???????// 初始化options ?????options={ ???????hostname:hostname, ???????????port:port, ???????????path:path, ?????????method:‘GET‘, ???}; ???req=http.request(options,function(resp){ ???????var imgData = ""; ???????resp.setEncoding("binary"); ????????resp.on(‘data‘,function(chunk){ ???????????imgData+=chunk; ???????????????????}); ???????resp.on(‘end‘,function(){ ???????????????????// 创建文件 ???????????var fileName="./"+folder+picName; ???????????fs.writeFile(fileName, imgData, "binary", function(err){ ???????????????if(err){ ???????????????????console.log("[downloadPic]文件 ??"+fileName+" ?下载失败."); ???????????????????console.log(err); ???????????????????appendToLogfile(folder,"文件 ?"+picUrl+" ?下载失败.\n"); ???????????????}else{ ???????????????????appendToLogfile(folder,"文件 ?"+picUrl+" ?下载成功.\n"); ???????????????????console.log("文件"+fileName+"下载成功"); ???????????????} ???????????}); ???????????}); ???}); ???// 超时处理 ???req.setTimeout(7500,function(){ ???????req.abort(); ???}); ???// 出错处理 ???req.on(‘error‘,function(err){ ???????if(err){ ???????????console.log(‘[downloadPic]文件 ??‘+picUrl+" ?下载失败,"+‘因为‘+err); ???????????appendToLogfile(folder,"文件"+picUrl+"下载失败.\n"); ???????} ???}); ???// 请求结束 ???req.end();}//--------------------------------------// 程序入口 //--------------------------------------function getInput(){ ???process.stdin.resume(); ???????process.stdout.write("\033[33m 新建模式输入第一页URL，断点续传模式输入0，请输入: \033[39m");// 草黄色 ???process.stdin.setEncoding(‘utf8‘); ???????process.stdin.on(‘data‘,function(text){ ???????var input=text.trim(); ???????process.stdin.end();// 退出输入状态 ???????????if(text.trim()==‘0‘){ ???????????process.stdout.write("\033[36m 进入断点续传模式. \033[39m"); ???// 蓝绿色 ???????????// Read File ???????????fs.readFile(‘./save.dat‘,‘utf8‘,function(err,data){ ???????????????if(err){ ???????????????????console.log(‘读取文件save.dat失败,因为‘+err); ???????????????}else{ ???????????????????//console.log(data); ???????????????????var obj=JSON.parse(data); ???????????????????pictures=obj.pictures; ???????????????????console.log(‘提取图片‘+pictures.length+‘张‘); ???????????????????folder=obj.folder; ???????????????????// 创建目录 ???????????????????fs.mkdir(‘./‘+folder,function(err){ ???????????????????????if(err){ ???????????????????????????console.log("目录"+folder+"已经存在"); ???????????????????????} ???????????????????}); ???????????????????crawl(obj.url); ???????????????????????} ???????????}); ???????????????????????// Resume crawl ???????}else{ ???????????process.stdout.write("\033[35m 进入新建模式. \033[039m"); ???//紫色 ???????????folder=‘pictures(‘+getNowFormatDate()+")"; ???????????// 创建目录 ???????????fs.mkdir(‘./‘+folder,function(err){ ???????????????if(err){ ???????????????????console.log("目录"+folder+"已经存在"); ???????????????} ???????????}); ???????????crawl(input); ???????????????????} ???}); ???}//--------------------------------------// 将爬行中信息存入数据文件//--------------------------------------function saveFile(url,pictures){ ???var obj=new Object; ???obj.url=url; ???obj.pictures=pictures; ???obj.folder=folder; ???var text=JSON.stringify(obj); ???fs.writeFile(‘./save.dat‘,text,function(err){ ???????if(err){ ???????????console.log(‘写入文件save.dat失败,因为‘+err); ???????} ???});}// 调用getInput函数，程序开始getInput();