FROM apify/actor-node-puppeteer-chrome:16

COPY package*.json ./

RUN npm --quiet set progress=false \
 && npm install --only=prod --no-optional \
 && echo "Installed NPM packages:" \
 && (npm list --all || true) \
 && echo "Node.js version:" \
 && node --version \
 && echo "NPM version:" \
 && npm --version

COPY . ./

ENV APIFY_DISABLE_OUTDATED_WARNING 1
ENV npm_config_loglevel=silent

main.js

1const Apify = require('apify');
2
3Apify.main(async () => {
4    const input = await Apify.getInput();
5 
6    const requestList = await Apify.openRequestList('my-list', input.requestListSources);
7    const proxyConfiguration = await Apify.createProxyConfiguration(input.proxyConfiguration);
8
9    const handlePageFunction = async ({ request, response, page }) => {
10        const { waitForSelector } = request.userData;
11
12        if (waitForSelector) {
13            await page.waitForSelector(waitForSelector);
14        }
15    
16        await Apify.pushData({
17            url: request.url,
18            finishedAt: new Date(),
19            fullHtml: await page.content(),
20            html: await page.evaluate(() => document.body.outerHTML),
21            '#debug': Apify.utils.createRequestDebugInfo(request, response),
22            '#error': false,
23        });
24    };
25    
26    const handleFailedRequestFunction = async ({ request }) => {
27        await Apify.pushData({
28            url: request.url,
29            finishedAt: new Date(),
30            '#debug': Apify.utils.createRequestDebugInfo(request),
31            '#error': true,
32        });
33    };
34
35    const puppeteerCrawler = new Apify.PuppeteerCrawler({
36        requestList,
37        handlePageFunction,
38        handleFailedRequestFunction,
39        proxyConfiguration,
40        useSessionPool: true,
41        sessionPoolOptions: {
42            sessionOptions: {
43                maxErrorScore: 0.5,
44            },
45        },
46        browserPoolOptions: {
47            useFingerprints: true,
48            retireBrowserAfterPageCount: 1,
49            maxOpenPagesPerBrowser: 1, // required to use one IP per tab
50        },
51        persistCookiesPerSession: false,
52        maxRequestRetries: typeof input.maxRequestRetries === 'number' ? input.maxRequestRetries : 1,
53        handlePageTimeoutSecs: input.handlePageTimeoutSecs || 60,
54        launchContext: {
55            useChrome: input.useChrome || false,
56            launchOptions: {
57                headless: false,
58                ignoreHTTPSErrors: true,
59                args: ['--ignore-certificate-errors']
60            }
61        },
62    });
63    
64    await puppeteerCrawler.run();
65});

package.json

{
    "name": "my-actor",
    "version": "0.0.1",
    "dependencies": {
        "apify": "^2.3.2",
        "puppeteer": "^13"
    },
    "scripts": {
        "start": "node main.js"
    },
    "author": "Me!"
}

HTML Scraper pro

scrapingxpert/html-scraper-pro

The HTML Scraper Pro is a powerful tool designed to extract the HTML source code and metadata from websites. It uses advanced web scraping techniques to retrieve the full HTML content of web pages,page title and HTTP status code.This tool is ideal for data extraction, website analysis, and archiving

scrapingxpert

154

5.0

🔗✨ Link Extractor Pro: URL to HTML List Downloader

dainty_screw/link-extractor-pro-url-to-html-list-downloader

Maximize productivity with HTML URL List Downloader. Quickly extract, manage, and organize URLs from HTML pages. Ideal for SEO professionals and digital marketers. Streamline your workflow today!

codemaster devops

156

HTML Extractor

dataguru/html-extractor

Fetch raw HTML from any URL. Inputs: url, headers (textarea), timeout, mobile UA toggle, optional proxy. Outputs: Dataset + KV “OUTPUT” with {url, statusCode, contentType, length, html}. Perfect for Make.com, debugging, and pipelines.

Achraf Mannani

Cheerio Scraper

apify/cheerio-scraper

Crawls websites using raw HTTP requests, parses the HTML with the Cheerio library, and extracts data from the pages using a Node.js code. Supports both recursive crawling and lists of URLs. This actor is a high-performance alternative to apify/web-scraper for websites that do not require JavaScript.

Apify

11K

4.9

Web Scraper

apify/web-scraper

Crawls arbitrary websites using a web browser and extracts structured data from web pages using a provided JavaScript function. The Actor supports both recursive crawling and lists of URLs, and automatically manages concurrency for maximum performance.

Apify

100K

3.4

Puppeteer Scraper

apify/puppeteer-scraper

Crawls websites with the headless Chrome and Puppeteer library using a provided server-side Node.js code. This crawler is an alternative to apify/web-scraper that gives you finer control over the process. Supports both recursive crawling and list of URLs. Supports login to website.

Apify

9.9K

5.0

Website Content Crawler

apify/website-content-crawler

Crawl websites and extract text content to feed AI models, LLM applications, vector databases, or RAG pipelines. The Actor supports rich formatting using Markdown, cleans the HTML, downloads files, and integrates well with 🦜🔗 LangChain, LlamaIndex, and the wider LLM ecosystem.

Apify

80K

4.6

Html To Markdown Converter 📄

powerful_bachelor/html-to-markdown-converter

📄✨ HTML to Markdown Converter transforms web pages into clean, portable Markdown. Simply input a URL to extract content while preserving structure, formatting, and media elements.🔄 Perfect for content repurposing, documentation, and creating readable, platform-independent text from any webpage! 🚀

Powerful Bachelor

HTML/Website Media Scraper

hlymrk/html-web-media-scraper

The Website Media scraper extracts all media files, i.e images, videos, audio, and other related media elements, from multiple websites. It then provides the corresponding descriptions or the alt="" content. You'll need to use proxies to run this actor for some websites with bot blocking features.