Last active
August 16, 2022 20:10
-
-
Save crevulus/76db176b26ce4fab29889a8960aa007f to your computer and use it in GitHub Desktop.
A small script that uses puppeteer to scrape craigslist and return images for a search term
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 puppeteer = require("puppeteer"); | |
async function getImages(searchTerm) { | |
const browser = await puppeteer.launch({ | |
// headless: false, | |
defaultViewport: null, | |
}); | |
const page = await browser.newPage(); | |
const url = `https://nh.craigslist.org/d/for-sale/search/sss?query=${searchTerm}&sort=rel&hasPic=1`; | |
await page.goto(url); | |
await page.waitForSelector(".result-row"); | |
const results = await page.$$eval(".result-row", (rows) => { | |
return rows.map((row) => { | |
const properties = {}; | |
const heading = row.querySelector(".result-info .result-heading"); | |
properties.heading = heading ? heading.innerText : ""; | |
const price = row.querySelector(".result-info .result-price"); | |
properties.price = price ? price.innerText : ""; | |
const postLink = row.querySelector(".result-image").getAttribute("href"); | |
properties.link = postLink; | |
const image = row.querySelector( | |
'.result-image .swipe .swipe-wrap [data-index="0"] img' | |
); | |
properties.image = image ? image.src : ""; | |
return properties; | |
}); | |
}); | |
console.log(results); | |
return results; | |
} | |
getImages("car"); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment