wehub-resource-sync
65 lines
2.5 KiB
TypeScript
65 lines
2.5 KiB
TypeScript
import { PlaywrightCrawler } from 'crawlee';
|
|
|
|
// Create an instance of the PlaywrightCrawler class - a crawler
|
|
// that automatically loads the URLs in headless Chrome / Playwright.
|
|
const crawler = new PlaywrightCrawler({
|
|
launchContext: {
|
|
// Here you can set options that are passed to the playwright .launch() function.
|
|
launchOptions: {
|
|
headless: true,
|
|
},
|
|
},
|
|
|
|
// Stop crawling after several pages
|
|
maxRequestsPerCrawl: 50,
|
|
|
|
// This function will be called for each URL to crawl.
|
|
// Here you can write the Playwright scripts you are familiar with,
|
|
// with the exception that browsers and pages are automatically managed by Crawlee.
|
|
// The function accepts a single parameter, which is an object with a lot of properties,
|
|
// the most important being:
|
|
// - request: an instance of the Request class with information such as URL and HTTP method
|
|
// - page: Playwright's Page object (see https://playwright.dev/docs/api/class-page)
|
|
async requestHandler({ pushData, request, page, enqueueLinks, log }) {
|
|
log.info(`Processing ${request.url}...`);
|
|
|
|
// A function to be evaluated by Playwright within the browser context.
|
|
const data = await page.$$eval('.athing', ($posts) => {
|
|
const scrapedData: { title?: string; rank?: string; href?: string }[] = [];
|
|
|
|
// We're getting the title, rank and URL of each post on Hacker News.
|
|
$posts.forEach(($post) => {
|
|
scrapedData.push({
|
|
title: $post.querySelector<HTMLElement>('.title a')?.innerText,
|
|
rank: $post.querySelector<HTMLElement>('.rank')?.innerText,
|
|
href: $post.querySelector<HTMLAnchorElement>('.title a')?.href,
|
|
});
|
|
});
|
|
|
|
return scrapedData;
|
|
});
|
|
|
|
// Store the results to the default dataset.
|
|
await pushData(data);
|
|
|
|
// Find a link to the next page and enqueue it if it exists.
|
|
const infos = await enqueueLinks({
|
|
selector: '.morelink',
|
|
});
|
|
|
|
if (infos.processedRequests.length === 0) log.info(`${request.url} is the last page!`);
|
|
},
|
|
|
|
// This function is called if the page processing failed more than maxRequestRetries+1 times.
|
|
failedRequestHandler({ request, log }) {
|
|
log.info(`Request ${request.url} failed too many times.`);
|
|
},
|
|
});
|
|
|
|
await crawler.addRequests(['https://news.ycombinator.com/']);
|
|
|
|
// Run the crawler and wait for it to finish.
|
|
await crawler.run();
|
|
|
|
console.log('Crawler finished.');
|