Created
August 12, 2020 13:20
-
-
Save andrefa/a2a1650e84331735726858af176bfc86 to your computer and use it in GitHub Desktop.
This file contains 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 got = require('got'); | |
const jsdom = require("jsdom"); | |
const { JSDOM } = jsdom; | |
const cgUrl = 'https://vancouver.craigslist.org/search/van/apa?search_distance=4&postal=V6E1W5&min_bedrooms=2&minSqft=600&availabilityMode=0&pets_cat=1&laundry=1&sale_date=all+dates'; | |
const pageSize = 120; | |
const find = (element, expression) => element.querySelector(expression) || {} | |
const list = (element, expression) => [...element.querySelectorAll(expression)] | |
const cleanText = (text = '') => text.replace(/\n|[-(),$]/g, '').replace(/[ ]+/g, ' ').trim() | |
const fetchApts = async () => { | |
let fullResultSet = []; | |
let currentPage = []; | |
let offset = 0; | |
do { | |
console.log('Fetching for offset ' + offset) | |
currentPage = await process(offset) | |
offset += pageSize | |
fullResultSet = [ ...fullResultSet, ...currentPage ] | |
} while(currentPage.length === pageSize) | |
return fullResultSet | |
} | |
const process = async (offset) => { | |
const response = await got(cgUrl + '&s=' + offset); | |
const dom = new JSDOM(response.body); | |
const listing = list(dom.window.document, '.result-row'); | |
return listing.map( node => { | |
const price = cleanText(find(node, '.result-price').textContent) | |
const posted = find(node, '.result-date').textContent | |
const title = find(node, '.result-title').textContent | |
const hood = cleanText(find(node, '.result-hood').textContent) | |
const housing = cleanText(find(node, '.housing').textContent) | |
const link = find(node, '.result-title').href | |
const img = find(node, 'img').src | |
return { | |
hood, | |
housing, | |
link, | |
price, | |
posted, | |
title, | |
img, | |
} | |
}) | |
} | |
module.exports = { | |
fetchApts | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment