x-scraper

# 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": "my-actor",
    "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, RequestQueue } from 'crawlee';
3
4await Actor.init();
5
6const {
7    startUrls = [{ url: 'https://x.com/baconbrix/status/1910752770593816703?s=12' }],
8    proxyConfig = null,
9} = await Actor.getInput() ?? {};
10
11if (!startUrls || startUrls.length !== 1) {
12    throw new Error('startUrls must be an array with exactly one URL');
13}
14
15const proxyConfiguration = proxyConfig
16    ? await Actor.createProxyConfiguration(proxyConfig)
17    : await Actor.createProxyConfiguration();
18
19const requestQueue = await RequestQueue.open();
20
21const crawler = new PuppeteerCrawler({
22    proxyConfiguration,
23    requestQueue,
24    maxRequestsPerCrawl: 1,
25
26    launchContext: {
27        useChrome: true,
28        launchOptions: {
29            headless: true,
30        },
31    },
32
33    requestHandler: async ({ page, request, log }) => {
34        log.info(`Scraping X post: ${request.url}`);
35
36        // Wait for tweet content to load with retry
37        const maxRetries = 3;
38        let retries = 0;
39        let articleFound = false;
40
41        while (retries < maxRetries && !articleFound) {
42            try {
43                await page.waitForSelector('article', { timeout: 20000 });
44                articleFound = true;
45            } catch (e) {
46                retries++;
47                if (retries < maxRetries) {
48                    log.warning(`Article not found, retrying (${retries}/${maxRetries})...`);
49                    await page.reload({ waitUntil: 'networkidle2' });
50                } else {
51                    throw new Error(`Article not found after ${maxRetries} attempts on ${request.url}`);
52                }
53            }
54        }
55
56        const data = await page.evaluate(() => {
57            const result = {
58                url: window.location.href,
59                title: '',
60                image: '',
61                ogTitle: '',
62                ogDescription: '',
63                ogImage: '',
64                description: '',
65                rawImages: [],
66            };
67
68            // Grab main tweet content
69            const article = document.querySelector('article');
70            if (article) {
71                const textElement = article.querySelector('div[lang]');
72                if (textElement) result.title = textElement.innerText.trim();
73
74                const textElements = article.querySelectorAll('div[lang]');
75                const allText = Array.from(textElements)
76                    .map(el => el.innerText.trim())
77                    .filter(Boolean)
78                    .join('\n');
79
80                result.content = allText;
81
82                const imgTags = article.querySelectorAll('img');
83                const imgUrls = Array.from(imgTags)
84                    .map(img => img.src)
85                    .filter(src => !src.includes('profile_images') && !src.includes('emoji'));
86                if (imgUrls.length > 0) {
87                    result.image = imgUrls[0];
88                    result.rawImages = imgUrls;
89                }
90            }
91
92            // Fallback metadata
93            const getMeta = (name) =>
94                document.querySelector(`meta[property="${name}"]`)?.content ||
95                document.querySelector(`meta[name="${name}"]`)?.content || '';
96
97            result.ogTitle = getMeta('og:title');
98            result.ogDescription = getMeta('og:description');
99            result.ogImage = getMeta('og:image');
100            result.description = getMeta('description');
101
102            return result;
103        });
104
105        await Dataset.pushData(data);
106    },
107});
108
109await requestQueue.addRequest({ url: startUrls[0].url });
110await crawler.run();
111await 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
.zed
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"
}