Last active
April 15, 2019 20:10
-
-
Save sr2ds/23d9ea54dc80539faef04f2eb3582a73 to your computer and use it in GitHub Desktop.
Initial Implement for scrapper aliexpress category with nodejs
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
const rp = require('request-promise'); | |
const $ = require('cheerio'); | |
const baseLink = `https://pt.aliexpress.com/category/` | |
const categoryPath = `201000005/home-appliances/` | |
const ApiGet = { | |
getMultiplePages(totalPages) { | |
for (let page = 1; page <= totalPages; page++) { | |
ApiGet.getByPageNumber(page) | |
} | |
}, | |
getByPageNumber(pageNumber) { | |
const url = `${baseLink}${categoryPath}${pageNumber}.html` | |
const products = [] | |
rp(url) | |
.then(function(html){ | |
const items = $('li.list-item', html) | |
items.each(function(index,item) { | |
const link = $(item).find('.product').attr('href') | |
const title = $(item).find('.product').attr('title') | |
const total = Number($(item).find('em').text().replace('Pedidos', '').replace(')','').replace('(', '')) | |
const id = $(item).find('input.atc-product-id').val() | |
products.push({ id, title, link, total }) | |
}) | |
console.log(products.length) | |
}) | |
} | |
} | |
ApiGet.getMultiplePages(10) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment