Node.js abaike图片批量下载Node.js爬虫1.00版

//======================================================// abaike图片批量下载Node.js爬虫1.00// 2017年11月9日//======================================================// 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‘);// 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=[];//--------------------------------------// 爬取网页，找图片地址，再爬// pageUrl sample:http://www.avbaike.net/27812.html// pageUrl sample:http://www.avbaike.net/27812.html/2//--------------------------------------function crawl(pageUrl){ ???console.log("Current page="+pageUrl); ???// 得到hostname和path ???var currUrl=pageUrl.replace("http://",""); ???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:80, ???????????path:path,// 子路径 ?????????method:‘GET‘, ???}; ???req=http.request(options,function(resp){ ???????resp.setEncoding(‘utf8‘); ???????var body=""; ???????resp.on(‘data‘,function(chunk){ ???????????body+=chunk; ???????????????????}); ???????resp.on(‘end‘,function(){ ???????????//console.log("body="+body); ???????????var $ = cheerio.load(body); ???????????????????????// 找图片放入数组 ???????????$("#post_content p a").each(function(index,element){ ???????????????var picUrl=$(element).attr("href"); ???????????????//console.log(picUrl); ???????????????pictures.push(picUrl); ???????????????????????????}) ??????????????????????????????var nextPageUrl=null; ???????????// 找下一页 ???????????$(".pagelist a").each(function(index,element){ ???????????????var text=$(element).text(); ???????????????if(text.indexOf(‘下一页‘)!=-1){ ???????????????????nextPageUrl=$(element).attr("href"); ???????????????} ???????????????????}) ???????????if(nextPageUrl==null){ ???????????????console.log(pageUrl+"已经是最后一页了."); ???????????????download(pictures); ???????????}else{ ???????????????//console.log("下一页是"+nextPageUrl); ???????????????crawl(nextPageUrl); ???????????} ???????}); ???}); ???// 超时处理 ???req.setTimeout(10000,function(){ ???????req.abort(); ???}); ???// 出错处理 ???req.on(‘error‘,function(err){ ???????if(err.code=="ECONNRESET"){ ???????????console.log(‘[crawl]socket端口连接超时。‘); ???????????console.log(err); ???????}else{ ???????????console.log(‘请求发生错误，err.code:‘+err.code); ???????} ???}); ???// 请求结束 ???req.end();}//--------------------------------------// 下载图片//--------------------------------------function download(pictures){ ???var folder=‘pictures‘; ???// 创建目录 ???fs.mkdir(‘./‘+folder,function(err){ ???????if(err){ ???????????console.log("目录"+folder+"已经存在"); ???????} ???}); ???console.log("总计有"+pictures.length+"张图片将被下载."); ???for(var i=0;i<pictures.length;i++){ ???????var picUrl=pictures[i]; ???????downloadPic(picUrl); ???}}//--------------------------------------// 下载单张图片// picUrl sample:http://www.avbaike.net/wp-content/uploads/2016/08/108.jpg//--------------------------------------function downloadPic(picUrl){ ???console.log("图片:"+picUrl+"下载开始"); ???// 得到hostname和path ???var currUrl=picUrl.replace("http://",""); ???var pos=currUrl.indexOf("/"); ???var hostname=currUrl.slice(0,pos); ???????????var path=currUrl.slice(pos); ???????//console.log("hostname="+hostname); ???//console.log("path="+path); ???var picName=currUrl.slice(currUrl.lastIndexOf("/")); ???????// 初始化options ?????options={ ???????hostname:hostname, ???????????port:80, ???????????path:path,// 子路径 ?????????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="./pictures"+picName; ???????????fs.writeFile(fileName, imgData, "binary", function(err){ ???????????????if(err){ ???????????????????console.log("文件"+fileName+"下载失败."); ???????????????????console.log(err); ???????????????}else{ ???????????????????console.log("文件"+fileName+"下载成功"); ???????????????} ???????????}); ???????????}); ???}); ???// 超时处理 ???req.setTimeout(10000,function(){ ???????req.abort(); ???}); ???// 出错处理 ???req.on(‘error‘,function(err){ ???????if(err.code=="ECONNRESET"){ ???????????console.log(‘[downloadPic]socket端口连接超时。‘); ???????????console.log(err); ???????}else{ ???????????console.log(‘[downloadPic]请求发生错误，err.code:‘+err.code); ???????????console.log(err); ???????} ???}); ???// 请求结束 ???req.end();}//--------------------------------------// 程序入口 //--------------------------------------function getInput(){ ???????????process.stdout.write("\033[35m 请输入第一页URL:\033[039m"); ???//紫色 ???process.stdin.resume(); ???process.stdin.setEncoding(‘utf8‘); ???????process.stdin.on(‘data‘,function(text){ ???????process.stdin.end();// 退出输入状态 ???????????????crawl(text.trim());// trim()是必须的！ ???????????}); ???}// 调用getInput函数，程序开始getInput();