How to use the apify.PuppeteerCrawler function in apify

To help you get started, we’ve selected a few apify examples, based on popular ways it is used in public projects.

github apifytech / apify-js / examples / screenshots.js View on Github external
Apify.main(async () => {
    // Read the actor input configuration containing the URLs for the screenshot.
    // By convention, the input is present in the actor's default key-value store under the "INPUT" key.
    const input = await Apify.getInput();
    if (!input) throw new Error('Have you passed the correct INPUT ?');

    const { sources } = input;

    const requestList = new Apify.RequestList({ sources });
    await requestList.initialize();

    const crawler = new Apify.PuppeteerCrawler({
        requestList,
        handlePageFunction: async ({ page, request }) => {
            console.log(`Processing ${request.url}...`);

            // This is a Puppeteer function that takes a screenshot of the page and returns its buffer.
            const screenshotBuffer = await page.screenshot();

            // The record key may only include the following characters: a-zA-Z0-9!-_.'()
            const key = request.url.replace(/[:/]/g, '_');

            // Save the screenshot. Choosing the right content type will automatically
            // assign the local file the right extension, in this case .png.
            // The screenshots will be stored in ./apify_storage/key_value_stores/default/
            await Apify.setValue(key, screenshotBuffer, { contentType: 'image/png' });
            console.log(`Screenshot of ${request.url} saved.`);
        },
github apifytech / apify-cli / src / templates / cheerio_crawler / main.js View on Github external
// a user interface for it, add INPUT_SCHEMA.json file to your actor.
    // For more information, see https://apify.com/docs/actor/input-schema
    const input = await Apify.getInput();
    console.log('Input:');
    console.dir(input);

    // Open a request queue and add a start URL to it
    const requestQueue = await Apify.openRequestQueue();
    await requestQueue.addRequest({ url: 'https://www.iana.org/' });

    // Define a pattern of URLs that the crawler should visit
    const pseudoUrls = [new Apify.PseudoUrl('https://www.iana.org/[.*]')];

    // Create a crawler that will use headless Chrome / Puppeteer to extract data
    // from pages and recursively add links to newly-found pages
    const crawler = new Apify.PuppeteerCrawler({
        requestQueue,

        // This function is called for every page the crawler visits
        handlePageFunction: async ({ request, page }) => {
            const title = await page.title();
            console.log(`Title of ${request.url}: ${title}`);
            await Apify.pushData({
                title,
                '#debug': Apify.utils.createRequestDebugInfo(request),
            });
            await Apify.utils.enqueueLinks({ page, selector: 'a', pseudoUrls, requestQueue });
        },

        // This function is called for every page the crawler failed to load
        // or for which the handlePageFunction() throws at least "maxRequestRetries"-times
        handleFailedRequestFunction: async ({ request }) => {
github cermak-petr / actor-booking-scraper / src / main.js View on Github external
}

    // Temporary fix, make UI proxy input compatible
    if (input.proxyConfig && input.proxyConfig.apifyProxyGroups) {
        for (let i = 0; i < input.proxyConfig.apifyProxyGroups.length; i++) {
            const gSpl = input.proxyConfig.apifyProxyGroups[i].split('-');
            const nGroup = gSpl[gSpl.length - 1];
            input.proxyConfig.apifyProxyGroups[i] = nGroup;
        }
    }

    // Simulated browser chache
    const cache = {};

    // Main crawler variable.
    const crawler = new Apify.PuppeteerCrawler({
        requestList,

        requestQueue,
        
        handlePageTimeoutSecs: 120,

        // Browser instance creation.
        launchPuppeteerFunction: () => {
            if (!input.testProxy) {
                return Apify.launchPuppeteer(input.proxyConfig || {});
            }
            return getWorkingBrowser(startUrl, input);
        },

        // Main page handling function.
        handlePageFunction: async ({ page, request, puppeteerPool }) => {
github apifytech / apify-js / examples / crawler_puppeteer.js View on Github external
Apify.main(async () => {
    // Get queue and enqueue first url.
    const requestQueue = await Apify.openRequestQueue();

    // Enqueue Start url.
    await requestQueue.addRequest(new Apify.Request({ url: 'https://news.ycombinator.com/' }));

    // Create crawler.
    const crawler = new Apify.PuppeteerCrawler({
        requestQueue,

        // This page is executed for each request.
        // If request failes then it's retried 3 times.
        // Parameter page is Puppeteers page object with loaded page.
        handlePageFunction: async ({ page, request }) => {
            console.log(`Processing ${request.url}...`);

            // Extract all posts.
            const pageFunction = ($posts) => {
                const data = [];

                $posts.forEach(($post) => {
                    data.push({
                        title: $post.querySelector('.title a').innerText,
                        rank: $post.querySelector('.rank').innerText,
github apifytech / apify-cli / src / templates / puppeteer_crawler / main.js View on Github external
Apify.main(async () => {
    // Apify.openRequestQueue() is a factory to get a preconfigured RequestQueue instance.
    // We add our first request to it - the initial page the crawler will visit.
    const requestQueue = await Apify.openRequestQueue();
    await requestQueue.addRequest({ url: 'https://news.ycombinator.com/' });

    // Create an instance of the PuppeteerCrawler class - a crawler
    // that automatically loads the URLs in headless Chrome / Puppeteer.
    const crawler = new Apify.PuppeteerCrawler({
        requestQueue,

        // Here you can set options that are passed to the Apify.launchPuppeteer() function.
        // For example, you can set "slowMo" to slow down Puppeteer operations to simplify debugging
        launchPuppeteerOptions: { slowMo: 500 },

        // Stop crawling after several pages
        maxRequestsPerCrawl: 10,

        // This function will be called for each URL to crawl.
        // Here you can write the Puppeteer scripts you are familiar with,
        // with the exception that browsers and pages are automatically managed by the Apify SDK.
        // The function accepts a single parameter, which is an object with the following fields:
        // - request: an instance of the Request class with information such as URL and HTTP method
        // - page: Puppeteer's Page object (see https://pptr.dev/#show=api-class-page)
        handlePageFunction: async ({ request, page }) => {
github apifytech / apify-js / examples / puppeteer_crawler.js View on Github external
Apify.main(async () => {
    // Apify.openRequestQueue() is a factory to get a preconfigured RequestQueue instance.
    // We add our first request to it - the initial page the crawler will visit.
    const requestQueue = await Apify.openRequestQueue();
    await requestQueue.addRequest({ url: 'https://news.ycombinator.com/' });

    // Create an instance of the PuppeteerCrawler class - a crawler
    // that automatically loads the URLs in headless Chrome / Puppeteer.
    const crawler = new Apify.PuppeteerCrawler({
        requestQueue,

        // Here you can set options that are passed to the Apify.launchPuppeteer() function.
        launchPuppeteerOptions: {
            // For example, by adding "slowMo" you'll slow down Puppeteer operations to simplify debugging
            // slowMo: 500,
        },

        // Stop crawling after several pages
        maxRequestsPerCrawl: 10,

        // This function will be called for each URL to crawl.
        // Here you can write the Puppeteer scripts you are familiar with,
        // with the exception that browsers and pages are automatically managed by the Apify SDK.
        // The function accepts a single parameter, which is an object with the following fields:
        // - request: an instance of the Request class with information such as URL and HTTP method
github apifytech / apify-js / examples / puppeteer_sitemap.js View on Github external
Apify.main(async () => {
    const requestList = new Apify.RequestList({
        sources: [{ requestsFromUrl: 'https://edition.cnn.com/sitemaps/cnn/news.xml' }],
    });
    await requestList.initialize();

    const crawler = new Apify.PuppeteerCrawler({
        requestList,
        handlePageFunction: async ({ page, request }) => {
            console.log(`Processing ${request.url}...`);
            await Apify.pushData({
                url: request.url,
                title: await page.title(),
                html: await page.content(),
            });
        },
    });

    await crawler.run();
    console.log('Done.');
});
github apifytech / actor-scraper / puppeteer-scraper / src / crawler_setup.js View on Github external
puppeteerPoolOptions: {
                useLiveView: true,
                recycleDiskCache: true,
            },
            launchPuppeteerOptions: {
                ...(_.omit(this.input.proxyConfiguration, 'proxyUrls')),
                ignoreHTTPSErrors: this.input.ignoreSslErrors,
                defaultViewport: DEFAULT_VIEWPORT,
                devtools: this.devtools,
                useChrome: this.input.useChrome,
                stealth: this.input.useStealth,
                args,
            },
        };

        this.crawler = new Apify.PuppeteerCrawler(options);

        return this.crawler;
    }
github apifytech / apify-js / examples / hello_world.js View on Github external
Apify.main(async () => {
    const requestQueue = await Apify.openRequestQueue();
    await requestQueue.addRequest({ url: 'https://www.iana.org/' });
    const pseudoUrls = [new Apify.PseudoUrl('https://www.iana.org/[.*]')];

    const crawler = new Apify.PuppeteerCrawler({
        requestQueue,
        handlePageFunction: async ({ request, page }) => {
            const title = await page.title();
            console.log(`Title of ${request.url}: ${title}`);
            await Apify.utils.enqueueLinks({ page, selector: 'a', pseudoUrls, requestQueue });
        },
        maxRequestsPerCrawl: 100,
        maxConcurrency: 10,
    });

    await crawler.run();
});
github apifytech / actor-scraper / web-scraper / src / crawler_setup.js View on Github external
puppeteerPoolOptions: {
                useLiveView: true,
                recycleDiskCache: true,
            },
            launchPuppeteerOptions: {
                ...(_.omit(this.input.proxyConfiguration, 'proxyUrls')),
                ignoreHTTPSErrors: this.input.ignoreSslErrors,
                defaultViewport: DEFAULT_VIEWPORT,
                devtools: this.devtools,
                useChrome: this.input.useChrome,
                stealth: this.input.useStealth,
                args,
            },
        };

        this.crawler = new Apify.PuppeteerCrawler(options);

        return this.crawler;
    }

apify

The scalable web crawling and scraping library for JavaScript/Node.js. Enables development of data extraction and web automation jobs (not only) with headless Chrome and Puppeteer.

Apache-2.0
Latest version published 2 months ago

Package Health Score

84 / 100
Full package analysis

Similar packages