Proxy Configuration

import { ReaderClient } from "@vakra-dev/reader";

const reader = new ReaderClient();

const result = await reader.scrape({
  urls: ["https://example.com"],
  proxy: {
    host: "proxy.example.com",
    port: 8080,
    username: "user",
    password: "pass",
  },
});

await reader.close();

const result = await reader.scrape({
  urls: ["https://example.com"],
  proxy: {
    url: "http://user:[email protected]:8080",
  },
});

// Datacenter proxy
const result = await reader.scrape({
  urls: ["https://example.com"],
  proxy: {
    type: "datacenter",
    host: "dc-proxy.example.com",
    port: 8080,
    username: "user",
    password: "pass",
  },
});

// Residential proxy
const result = await reader.scrape({
  urls: ["https://example.com"],
  proxy: {
    type: "residential",
    host: "res-proxy.example.com",
    port: 8080,
    username: "user",
    password: "pass",
    country: "us", // Geo-targeting
  },
});

const reader = new ReaderClient({
  proxies: [
    { host: "proxy1.example.com", port: 8080, username: "user", password: "pass" },
    { host: "proxy2.example.com", port: 8080, username: "user", password: "pass" },
    { host: "proxy3.example.com", port: 8080, username: "user", password: "pass" },
  ],
  proxyRotation: "round-robin", // or "random"
});

// Each scrape call uses the next proxy in rotation
await reader.scrape({ urls: ["https://example1.com"] }); // Uses proxy1
await reader.scrape({ urls: ["https://example2.com"] }); // Uses proxy2
await reader.scrape({ urls: ["https://example3.com"] }); // Uses proxy3
await reader.scrape({ urls: ["https://example4.com"] }); // Uses proxy1 again

await reader.close();

const reader = new ReaderClient({
  proxies: [proxy1, proxy2, proxy3],
  proxyRotation: "round-robin",
});
// Request 1 → proxy1
// Request 2 → proxy2
// Request 3 → proxy3
// Request 4 → proxy1 (cycles back)

const reader = new ReaderClient({
  proxies: [proxy1, proxy2, proxy3],
  proxyRotation: "random",
});
// Each request uses a randomly selected proxy

const reader = new ReaderClient({
  proxies: [proxy1, proxy2, proxy3],
  proxyRotation: "round-robin",
});

// Crawl uses one proxy for all requests in the session
const result = await reader.crawl({
  url: "https://example.com",
  depth: 2,
  maxPages: 50,
});
// All 50 pages use the same proxy

const reader = new ReaderClient({
  proxies: [defaultProxy1, defaultProxy2],
});

// Use default rotation
await reader.scrape({ urls: ["https://example.com"] });

// Override with specific proxy
await reader.scrape({
  urls: ["https://special-site.com"],
  proxy: {
    host: "special-proxy.example.com",
    port: 8080,
    username: "user",
    password: "pass",
  },
});

const result = await reader.scrape({
  urls: ["https://example.com"],
  proxy: { host: "proxy.example.com", port: 8080 },
});

// Proxy info in metadata
const proxyUsed = result.data[0].metadata.proxy;
if (proxyUsed) {
  console.log(`Used proxy: ${proxyUsed.host}:${proxyUsed.port}`);
}

# Single proxy
npx reader scrape https://example.com --proxy http://user:[email protected]:8080

# Crawl with proxy
npx reader crawl https://example.com --proxy http://user:[email protected]:8080

import { ReaderClient, ProxyConfig } from "@vakra-dev/reader";

async function scrapeWithProxies() {
  const proxies: ProxyConfig[] = [
    {
      type: "residential",
      host: "us-proxy.example.com",
      port: 8080,
      username: "user",
      password: "pass",
      country: "us",
    },
    {
      type: "residential",
      host: "uk-proxy.example.com",
      port: 8080,
      username: "user",
      password: "pass",
      country: "uk",
    },
    {
      type: "residential",
      host: "de-proxy.example.com",
      port: 8080,
      username: "user",
      password: "pass",
      country: "de",
    },
  ];

  const reader = new ReaderClient({
    proxies,
    proxyRotation: "round-robin",
    browserPool: { size: 5 },
  });

  try {
    const urls = [
      "https://example.com/page1",
      "https://example.com/page2",
      "https://example.com/page3",
      "https://example.com/page4",
      "https://example.com/page5",
    ];

    const result = await reader.scrape({
      urls,
      batchConcurrency: 3,
      onProgress: (p) => {
        console.log(`[${p.completed}/${p.total}] ${p.currentUrl}`);
      },
    });

    console.log(`Scraped ${result.batchMetadata.successfulUrls} URLs`);
  } finally {
    await reader.close();
  }
}

scrapeWithProxies().catch(console.error);