我正在为 T 恤网站构建内容抓取器。
目标是仅通过一个硬编码的 url 进入网站:http://shirts4mike.com
然后,我将找到每件 T 恤的所有产品页面,然后创建一个包含其详细信息的对象。然后将其添加到数组中。
当数组填满 T 恤时,我将处理该数组并将其记录到 CSV 文件中。
现在,我在请求/响应和函数调用的时间安排上遇到了一些麻烦。
如何确保在正确的时间调用 NEXT 函数?我知道它不起作用,因为它是异步的。
我怎样才能打电话secondScrape
, lastScraper
and convertJson2Csv
在正确的时间,以便他们正在使用的变量不是未定义的?
我尝试使用诸如response.end()
但这不起作用。
我假设我需要使用承诺才能使其正常工作?并且要清晰易读?
有任何想法吗?我的代码如下:
//Modules being used:
var cheerio = require('cheerio');
var request = require('request');
var moment = require('moment');
//hardcoded url
var url = 'http://shirts4mike.com/';
//url for tshirt pages
var urlSet = new Set();
var remainder;
var tshirtArray;
// Load front page of shirts4mike
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;
}
}
});
});
}
//call second scrape for remainder
secondScrape();
});
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);
}
}
});
});
}
});
console.log(urlSet);
//call lastScraper so we can grab data from the set (product pages)
lastScraper();
};
function lastScraper(){
//scrape set, product pages
for(var i = 0; i < urlSet.length; i++){
var url = urlSet[i];
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 img = $('.shirt-picture').find("img").attr("src");
var title = $('body').find(".shirt-details > h1").text().slice(4);
var tshirtObject = {};
//add values into tshirt object
tshirtObject.price = price;
tshirtObject.img = img;
tshirtObject.title = title;
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);
}
});
}
//call function to iterate through tshirt objects in array in order to convert to JSON, then into CSV to be logged
convertJson2Csv();
};