YouTube Suggested Videos

# Specify the base Docker image. You can read more about
# the available images at https://crawlee.dev/docs/guides/docker-images
# You can also use any other image from Docker Hub.
FROM apify/actor-node-puppeteer-chrome:20

# Check preinstalled packages
RUN npm ls crawlee apify puppeteer playwright

# Copy just package.json and package-lock.json
# to speed up the build using Docker layer cache.
COPY --chown=myuser package*.json ./

# Install NPM packages, skip optional and development dependencies to
# keep the image small. Avoid logging too much and print the dependency
# tree for debugging
RUN npm --quiet set progress=false \
    && npm install --omit=dev --omit=optional \
    && echo "Installed NPM packages:" \
    && (npm list --omit=dev --all || true) \
    && echo "Node.js version:" \
    && node --version \
    && echo "NPM version:" \
    && npm --version \
    && rm -r ~/.npm

# Next, copy the remaining files and directories with the source code.
# Since we do this after NPM install, quick build will be really fast
# for most source file changes.
COPY --chown=myuser . ./


# Run the image. If you know you won't need headful browsers,
# you can remove the XVFB start script for a micro perf gain.
CMD ./start_xvfb_and_run_cmd.sh && npm start --silent

{
    "actorSpecification": 1,
    "name": "suggested-videos",
    "title": "Project Puppeteer Crawler JavaScript",
    "description": "Crawlee and Puppeteer project in JavaScript.",
    "version": "0.0",
    "meta": {
        "templateId": "js-crawlee-puppeteer-chrome"
    },
    "input": "./input_schema.json",
    "dockerfile": "./Dockerfile"
}

{
    "title": "PuppeteerCrawler Template",
    "type": "object",
    "schemaVersion": 1,
    "properties": {
        "startUrls": {
            "title": "Start URLs",
            "type": "array",
            "description": "URLs to start with.",
            "editor": "requestListSources",
            "prefill": [
                {
                    "url": "https://apify.com"
                }
            ]
        }
    }
}

1import { Actor } from 'apify';
2import { PuppeteerCrawler, Dataset } from 'crawlee';
3
4await Actor.init();
5
6// Get input configuration from Apify
7const {
8    startUrls = [{
9        "url": "https://www.youtube.com/watch?v=lE4UXdJSJM4"
10    }],
11    maxResults = 10,
12    proxyConfig = null, // Proxy configuration passed in the input
13} = await Actor.getInput() ?? {};
14
15// Create the proxy configuration based on input if available
16const proxyConfiguration = proxyConfig
17    ? await Actor.createProxyConfiguration(proxyConfig)
18    : await Actor.createProxyConfiguration();
19
20const crawler = new PuppeteerCrawler({
21    proxyConfiguration,
22    maxRequestsPerCrawl: 1,
23    launchContext: {
24        useChrome: true,
25        launchOptions: {
26            headless: true, // Run in headless mode
27        },
28    },
29    requestHandler: async ({ page, request, log }) => {
30        // await page.goto(url, { waitUntil: "networkidle2" }); // Wait for network activity to idle
31
32        // Explicitly wait for the related videos section to load
33        await page.waitForSelector("a[href*='watch']");
34
35        const results = await page.evaluate(() => {
36            const links = Array.from(document.querySelectorAll("a[href*='watch']"))
37                .map((a) => a.href)
38                .filter((href) => href);
39
40            return links.map(url => ({ url }))
41        });
42
43        log.info(`Scraped ${results.length} results.`);
44        await Dataset.pushData(results);
45    },
46});
47
48await crawler.run(startUrls);
49await Actor.exit();

1import { Dataset, createPuppeteerRouter } from 'crawlee';
2
3export const router = createPuppeteerRouter();
4
5router.addDefaultHandler(async ({ enqueueLinks, log }) => {
6    log.info(`enqueueing new URLs`);
7    await enqueueLinks({
8        globs: ['https://apify.com/*'],
9        label: 'detail',
10    });
11});
12
13router.addHandler('detail', async ({ request, page, log }) => {
14    const title = await page.title();
15    log.info(`${title}`, { url: request.loadedUrl });
16
17    await Dataset.pushData({
18        url: request.loadedUrl,
19        title,
20    });
21});

# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
node_modules

# git folder
.git

root = true

[*]
indent_style = space
indent_size = 4
charset = utf-8
trim_trailing_whitespace = true
insert_final_newline = true
end_of_line = lf

{
    "extends": "@apify",
    "root": true
}

# This file tells Git which files shouldn't be added to source control

.DS_Store
.idea
dist
node_modules
apify_storage
storage

{
    "name": "crawlee-puppeteer-javascript",
    "version": "0.0.1",
    "type": "module",
    "description": "This is an example of an Apify actor.",
    "dependencies": {
        "apify": "^3.2.6",
        "crawlee": "^3.11.5",
        "puppeteer": "*"
    },
    "devDependencies": {
        "@apify/eslint-config": "^0.4.0",
        "eslint": "^8.50.0"
    },
    "scripts": {
        "start": "node src/main.js",
        "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
    },
    "author": "It's not you it's me",
    "license": "ISC"
}