with Scrape-It.Cloud and Lightpanda?
Initiate the scraping process for a specific endpoint. See the documentation here
The Scrape-It.Cloud API allows you to automate the extraction of data from websites. It can parse, scrape, and retrieve content without the need for manual intervention. With this API on Pipedream, you can build workflows that trigger on various events and use the scraped data for numerous applications like data analysis, lead generation, and content aggregation.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
scrape_it_cloud: {
type: "app",
app: "scrape_it_cloud",
}
},
async run({steps, $}) {
const data = {
"url": `https://pipedream.com`,
}
return await axios($, {
method: "post",
url: `https://api.scrape-it.cloud/scrape`,
headers: {
"Content-Type": `application/json`,
"x-api-key": `${this.scrape_it_cloud.$auth.api_key}`,
},
data,
})
},
})
import puppeteer from "puppeteer-core";
export default defineComponent({
props: {
lightpanda: {
type: "app",
app: "lightpanda",
}
},
async run({ steps, $ }) {
const browser = await puppeteer.connect({
browserWSEndpoint: `wss://cloud.lightpanda.io/ws?token=${this.lightpanda.$auth.api_token}`,
});
const page = await browser.newPage();
await page.goto('https://pipedream.com/');
const title = await page.title();
const content = await page.content();
await browser.close();// The browser needs to be closed, otherwise the step will hang
return { title, content }
},
})