从零学习node.js之简易的网络爬虫（四）

var request = require('request'),
 cheerio = require('cheerio');

request('https://cnodejs.org/', function(err, response, body){
 if( !err && response.statusCode == 200 ){
 // body为源码
 // 使用 cheerio.load 将字符串转换为 cheerio(jQuery) 对象，
 // 按照jQuery方式操作即可
 var $ = cheerio.load(body);
 
 // 输出导航的html代码
 console.log( $('.nav').html() );
 }
});

{
 title : $item.find('.topic_title').text(),
 url : $item.find('.topic_title').attr('href'),
 author : $item.find('.user_avatar img').attr('title'),
 reply : $item.find('.count_of_replies').text(),
 visits : $item.find('.count_of_visits').text()
}

request('https://cnodejs.org/?_t='+Date.now(), function(err, response, body){
 if( !err && response.statusCode == 200 ){
 var $ = cheerio.load(body);

 var data = [];
 $('#topic_list .cell').each(function(){
  var $this = $(this);
 
 // 使用trim去掉数据两端的空格
  data.push({
  title : trim($this.find('.topic_title').text()),
  url : trim($this.find('.topic_title').attr('href')),
  author : trim($this.find('.user_avatar img').attr('title')),
  reply : trim($this.find('.count_of_replies').text()),
  visits : trim($this.find('.count_of_visits').text())
  })
 });
 // console.log( JSON.stringify(data, ' ', 4) );
 console.log(data);
 }
});

// 删除字符串左右两端的空格
function trim(str){ 
 return str.replace(/(^\s*)|(\s*$)/g, "");
}

// 把page作为参数传递进去，然后调用request进行抓取
function getData(page){
 var url = 'https://cnodejs.org/?tab=all&page='+page;
 console.time(url);
 request(url, function(err, response, body){
 if( !err && response.statusCode == 200 ){
  console.timeEnd(url); // 通过time和timeEnd记录抓取url的时间

  var $ = cheerio.load(body);

  var data = [];
  $('#topic_list .cell').each(function(){
  var $this = $(this);

  data.push({
   title : trim($this.find('.topic_title').text()),
   url : trim($this.find('.topic_title').attr('href')),
   author : trim($this.find('.user_avatar img').attr('title')),
   reply : trim($this.find('.count_of_replies').text()),
   visits : trim($this.find('.count_of_visits').text())
  })
  });
  // console.log( JSON.stringify(data, ' ', 4) );
  // console.log(data);
  var filename = './file/cnode_'+page+'.txt';
  fs.writeFile(filename, JSON.stringify(data, ' ', 4), function(){
  console.log( filename + ' 写入成功' );
  })
 }
 });
}

var max = 6;
for(var i=1; i<=max; i++){

 getData(i);
}

$ node test.js
开始请求...
https://cnodejs.org/?tab=all&page=1: 279ms
./file/cnode_1.txt 写入成功
https://cnodejs.org/?tab=all&page=3: 372ms
./file/cnode_3.txt 写入成功
https://cnodejs.org/?tab=all&page=2: 489ms
./file/cnode_2.txt 写入成功
https://cnodejs.org/?tab=all&page=4: 601ms
./file/cnode_4.txt 写入成功
https://cnodejs.org/?tab=all&page=5: 715ms
./file/cnode_5.txt 写入成功
https://cnodejs.org/?tab=all&page=6: 819ms
./file/cnode_6.txt 写入成功

/*
 @param data [] 需要请求的链接的集合
 @param max num 最多同时请求的数量
*/
function Dispatch(data, max){
 var _max = max || 5, // 最多请求的数量
 _dataObj = data || [], // 需要请求的url集合
 _cur = 0, // 当前请求的个数
 _num = _dataObj.length || 0,
 _isEnd = false,
 _callback;

 var ss = function(){
 var s = _max - _cur;
 while(s--){
  if( !_dataObj.length ){
  _isEnd = true;
  break;
  }
  var surl = _dataObj.shift();
  _cur++;

  _callback(surl);
 }
 }

 this.start = function(callback){
 _callback = callback;

 ss();
 },

 this.call = function(){
 if( !_isEnd ){
  _cur--;
  ss();
 }
 }
}

var dis = new Dispatch(urls, max);
dis.start(getData);

var filename = './file/cnode_'+page+'.txt';
fs.writeFile(filename, JSON.stringify(data, ' ', 4), function(){
 console.log( filename + ' 写入成功' );
})
dis.call();

request({
 url:'https://www.zhihu.com/explore',
 headers:{
 // "Referer":"www.zhihu.com"
 cookie : xxx
 }
}, function(error, response, body){
 if (!error && response.statusCode == 200) {
 // console.log( body );
 var $ = cheerio.load(body);

 
 }
})

var request = require('request'),
 cheerio = require('cheerio'),
 fs = require('fs'),
 path = require('path'), // 用于分析图片的名称或者后缀名
 mkdirp = require('mkdirp'); // 用于创建多级目录

var date = new Date(),
 year = date.getFullYear(),
 month = date.getMonth()+1,
 month = ('00'+month).slice(-2), // 添加前置0
 day = date.getDate(),
 day = ('00'+day).slice(-2), // 添加前置0
 dir = './img/'+year+'/'+month+'/'+day+'/';

// 根据日期创建目录 ./img/2017/01/22/
var stats = fs.statSync(dir);
if( stats.isDirectory() ){
 console.log(dir+' 已存在');
}else{
 console.log('正在创建目录 '+dir);
 mkdirp(dir, function(err){
 if(err) throw err;
 })
}

request({
 url : 'http://desk.zol.com.cn/meinv/?_t='+Date.now()
}, function(err, response, body){
 if(err) throw err;

 if( response.statusCode == 200 ){
 var $ = cheerio.load(body);
 
 $('.photo-list-padding img').each(function(){
  var $this = $(this),
  imgurl = $this.attr('src');
  
  var ext = path.extname(imgurl); // 获取图片的后缀名，如 .jpg, .png .gif等
  var filename = Date.now()+'_'+ parseInt(Math.random()*10000)+ext; // 命名方式：毫秒时间戳+随机数+后缀名
  // var filename = path.basename(imgurl); // 直接获取图片的原名称
  // console.log(filename);
  download(imgurl, dir+filename); // 开始下载图片
 })
 }
});

// 保存图片
var download = function(imgurl, filename){
 request.head(imgurl, function(err, res, body) {
 request(imgurl).pipe(fs.createWriteStream(filename));
 console.log(filename+' success!');
 });
}