jancurn

const puppeteer = require('puppeteer');
const proxyChain = require('proxy-chain');

(async() => {
    const oldProxyUrl = 'http://bob:password123@proxy.example.com:8000';
    const newProxyUrl = await proxyChain.anonymizeProxy(oldProxyUrl);

    // Prints something like "http://127.0.0.1:45678"
    console.log(newProxyUrl);

jancurn

# Here you choose the base Docker image for the actor. Apify provides the following images:
#  apify/actor-node-basic
#  apify/actor-node-chrome
#  apify/actor-node-puppeteer
# However, you can use any other image from Docker Hub.
# For more information, see https://apify.com/docs/actor#base-images
FROM apify/actor-node-basic

# Copy all files and directories from the directory to the Docker image
COPY . ./

jancurn

const puppeteer = require('puppeteer');

(async() => {
    const proxyUrl = 'http://proxy.example.com:8000';
    const username = 'bob';
    const password = 'password123';

    const browser = await puppeteer.launch({
        args: [`--proxy-server=${proxyUrl}`],
        headless: false,

jancurn

const { createTunnel, closeTunnel, redactUrl } = require('proxy-chain');

(async () => {
    // Select the proxy to tunnel through. Note that some proxies do not allow
    // HTTP traffic (port 80) over the HTTP CONNECT tunnel, or might not allow connection
    // to target on any other port than 80 (HTTP) or 443 (HTTPS).
    // You might want to try different proxy groups.
    const PROXY_URL = 'http://auto:<PROXY_PASSWORD>@proxy.apify.com:8000';

    // Target server to connect to. Here we use www.example.com and port 443 for HTTPS.

jancurn

const Apify = require('apify');

Apify.main(async () => {
    const requestQueue = await Apify.openRequestQueue();
    await requestQueue.addRequest(new Apify.Request({ url: 'https://www.iana.org/' }));
    const pseudoUrls = [new Apify.PseudoUrl('https://www.iana.org/[.*]')];

    const crawler = new Apify.PuppeteerCrawler({
        requestQueue,
        handlePageFunction: async ({ request, page }) => {

jancurn

import scrapy
import apify
 
class MySpider(scrapy.Spider):
 	name = 'apifySpider'
 
 	def start_requests(self):
 		urls = [
 			'https://apify.com',
 			'https://apify.com/store',

jancurn

const Apify = require('apify');
 
Apify.main(async () => {
  const browser = await Apify.launchPuppeteer({ liveView: true });
  const page = await browser.newPage();
  
  await page.goto('https://news.ycombinator.com/');
  
  const pageTitle = await page.title();
  console.log(`Page loaded: ${pageTitle}`);

jancurn

const Apify = require('apify');

Apify.main(async () => {
    // Get input of your act and print it
    const input = await Apify.getValue('INPUT');
    console.log('My input:');
    console.dir(input);

    // Save the output
    const output = {