这是一个从 T 恤网站上抓取数据然后将产品信息写入 CSV 文件的程序。

有 3 个抓取函数和 1 个写入函数。

现在，我有一个绝对的噩梦，试图弄清楚如何在没有任何 3rd 方库或包的情况下在这里实现Promise。仅使用 ES6 的本机特性就可以做到这一点吗？

由于请求的异步性质，我需要在调用下一个函数之前完全完成每个函数及其请求。这样我就可以使用变量，例如urlSet在下一个函数中。

如何在不重写整个代码的情况下简单地做到这一点？

我应该提到，这些功能中的每一个都在单独的基础上工作，它们都经过了多次测试。

每个功能都成为一个单独的Promise吗？

代码如下，谢谢：

//TASK: Create a command line application that goes to an ecommerce site to get the latest prices.
    //Save the scraped data in a spreadsheet (CSV format).

'use strict';

//Modules being used:
var cheerio = require('cheerio');
var json2csv = require('json2csv');
var request = require('request');
var moment = require('moment');
var fs = require('fs');

//harcoded url
var url = 'http://shirts4mike.com/';

//url for tshirt pages
var urlSet = new Set();

var remainder;
var tshirtArray = [];


// First scrape loads front page of shirts4mike and finds the first product pages/menus
function firstScrape(){
    request(url, function(error, response, html) {
        if(!error && response.statusCode == 200){
            var $ = cheerio.load(html);

        //iterate over links with 'shirt'
            $('a[href*=shirt]').each(function(){
                var a = $(this).attr('href');

                //create new link
                var scrapeLink = url + a;

                //for each new link, go in and find out if there is a submit button. 
                //If there, add it to the set
                request(scrapeLink, function(error,response, html){
                    if(!error && response.statusCode == 200) {
                        var $ = cheerio.load(html);

                        //if page has a submit it must be a product page
                        if($('[type=submit]').length !== 0){

                            //add page to set
                            urlSet.add(scrapeLink);
                        } else if(remainder == undefined) {
                            //if not a product page, add it to remainder so it another scrape can be performed.
                            remainder = scrapeLink;                         
                        }
                    }
                });
            });     
        }
    });
}


//Scrape next level of menus to find remaning product pages to add to urlSet
function secondScrape() {
    request(remainder, function(error, response, html) {
        if(!error && response.statusCode == 200){
            var $ = cheerio.load(html);

            $('a[href*=shirt]').each(function(){
                var a = $(this).attr('href');

                //create new link
                var scrapeLink = url + a;

                request(scrapeLink, function(error,response, html){
                    if(!error && response.statusCode == 200){

                        var $ = cheerio.load(html);

                        //collect remaining product pages and add to set
                        if($('[type=submit]').length !== 0){
                            urlSet.add(scrapeLink);
                        }
                    }
                });
            });     
        }
    });
}


//call lastScraper so we can grab data from the set (product pages)
function lastScraper(){
    //scrape set, product pages
    for(var item of urlSet){
        var url = item;

        request(url, function(error, response, html){
            if(!error && response.statusCode == 200){
                var $ = cheerio.load(html);

                //grab data and store as variables
                var price = $('.price').text();
                var imgURL = $('.shirt-picture').find('img').attr('src');
                var title = $('body').find('.shirt-details > h1').text().slice(4);

                var tshirtObject = {};
                //add values into tshirt object
                tshirtObject.Title = title;
                tshirtObject.Price = price;
                tshirtObject.ImageURL = imgURL;
                tshirtObject.URL = url;
                tshirtObject.Date = moment().format('MMMM Do YYYY, h:mm:ss a');

                //add the object into the array of tshirts
                tshirtArray.push(tshirtObject);
            }
        });
    }
}


//Convert array of tshirt objects and write to CSV file
function convertJson2Csv(){
    //The scraper should generate a folder called `data` if it doesn’t exist.
    var dir ='./data';
    if(!fs.existsSync(dir)){
        fs.mkdirSync(dir);
    }

    var fields = ['Title', 'Price', 'ImageURL', 'URL', 'Date'];

    //convert tshirt data into CSV and pass in fields
    var csv = json2csv({ data: tshirtArray, fields: fields });

    //Name of file will be the date
    var fileDate = moment().format('MM-DD-YY');
    var fileName = dir + '/' + fileDate + '.csv';

    //Write file
    fs.writeFile(fileName, csv, {overwrite: true}, function(err) {
        console.log('file saved');
        if (err) throw err;
    });
}