I'm using Node JS, here's the code
import fetch from 'node-fetch';
import { JSDOM } from 'jsdom';
import {Appartment} from "./models/Appartment.mjs"
let applist = []
let multipleDivs = []
async function kijAppartments() {
try {
const kijCall = await fetch(`https://www.kijiji.ca/b-ville-de-montreal/appartement-4-1-2/k0l1700281?rb=true&dc=true`);
if(!kijCall.ok) {
throw new Error (
`HTTP error: ${kijCall.status}`
)
}
const response = await kijCall.text()
const dom = new JSDOM(response)
multipleDivs = dom.window.document.querySelectorAll(".info-container")
// console.log(multipleDivs)
return multipleDivs
}
catch(error) {
console.log("Error Made")
console.log(error)
}
}
async function arrayOfApps() {
await kijAppartments()
.then(data => {
data.forEach(div => {
const newApp = new Appartment
newApp.price = div.childNodes[1].innerText
newApp.title = div.childNodes[3].innerText
newApp.description = div.childNodes[7].innerText
console.log(newApp)
})
})
}
await arrayOfApps()
If you go on this link and try the following const aList = document.querySelectorAll(".info-container"), you get access to all of the nodes, innerHTML and innerText all work and give you access to the actual value but for some reason, when I try to run this code in the terminal, the value of all my objects is undefined.
You should use textContent instead of innerText.
Here's my solution:
const fetch = (...args) => import('node-fetch').then(({default: fetch}) => fetch(...args));
const jsdom = require('jsdom');
const { JSDOM } = jsdom;
class Appartment {
price
title
description
location
}
let multipleDivs = []
const appartments = []
function trim(text){
return text.replace(/(\r\n|\n|\r)/gm, "").trim()
}
async function fetchKijijiAppartments() {
const url = `https://www.kijiji.ca/b-ville-de-montreal/appartement-4-1-2/k0l1700281?rb=true&dc=true`
try {
const kijijiRes = await fetch(url);
if (!kijijiRes.ok) {
throw new Error(
`HTTP error: ${kijijiRes.status}`
)
}
const response = await kijijiRes.text()
// console.log("DB: ", response)
const dom = new JSDOM(response)
multipleDivs = dom.window.document.querySelectorAll(".info-container")
//console.log("DB: " multipleDivs)
return multipleDivs
} catch (error) {
console.log("Error Made")
console.log(error)
}
}
async function scrapeAppartments() {
await fetchKijijiAppartments()
.then(data => {
data.forEach(div => {
const appartement = new Appartment
appartement.price = trim(div.querySelector(".price").textContent)
appartement.title = trim(div.querySelector(".title").textContent)
appartement.description = trim(div.querySelector(".description").textContent)
console.log("DB: ", appartement)
appartments.push(appartement)
})
})
}
scrapeAppartments()