npx apify-cli create my-crawler
// The Apify SDK makes it easy to initialize the actor on the platform with the Actor.init() method,
// and to save the scraped data from your Actors to a dataset by simply using the Actor.pushData() method.
import { Actor } from 'apify';
import { PlaywrightCrawler } from 'crawlee';
await Actor.init();
const crawler = new PlaywrightCrawler({
async requestHandler({ request, page, enqueueLinks }) {
const title = await page.title();
console.log(`Title of ${request.loadedUrl} is '${title}'`);
await Actor.pushData({ title, url: request.loadedUrl });
await enqueueLinks();
}
});
await crawler.run(['https://crawlee.dev']);
await Actor.exit();
apify create my-python-actor
# The Apify SDK makes it easy to read the actor input with the Actor.get_input() method,
# and to save the scraped data from your Actors to a dataset by simply using the Actor.push_data() method.
from apify import Actor
from bs4 import BeautifulSoup
import requests
async def main():
async with Actor:
actor_input = await Actor.get_input()
response = requests.get(actor_input['url'])
soup = BeautifulSoup(response.content, 'html.parser')
await Actor.push_data({ 'url': actor_input['url'], 'title': soup.title.string })