लागत का अनुकूलन

import { Scrapeless } from '@scrapeless-ai/sdk';
import puppeteer from 'puppeteer-core';
 
const client = new Scrapeless({ apiKey: 'API Key' });
 
const { browserWSEndpoint } = client.browser.create({
    session_name: 'sdk_test',
    session_ttl: 180,
    proxy_country: 'ANY',
    session_recording: true,
    fingerprint,
});
 
async function scrapeWithResourceBlocking(url) {
    const browser = await puppeteer.connect({
        browserWSEndpoint,
        defaultViewport: null
    });
    const page = await browser.newPage();
 
    // Enable request interception
    await page.setRequestInterception(true);
 
    // Define resource types to block
    const BLOCKED_TYPES = new Set([
        'image',
        'font',
        'media',
        'stylesheet',
    ]);
 
    // Intercept requests
    page.on('request', (request) => {
        if (BLOCKED_TYPES.has(request.resourceType())) {
            request.abort();
            console.log(`Blocked: ${request.resourceType()} - ${request.url().substring(0, 50)}...`);
        } else {
            request.continue();
        }
    });
 
    await page.goto(url, {waitUntil: 'domcontentloaded'});
 
    // Extract data
    const data = await page.evaluate(() => {
        return {
            title: document.title,
            content: document.body.innerText.substring(0, 1000)
        };
    });
 
    await browser.close();
    return data;
}
 
// Usage
scrapeWithResourceBlocking('https://www.scrapeless.com')
    .then(data => console.log('Scraping result:', data))
    .catch(error => console.error('Scraping failed:', error));

import puppeteer from 'puppeteer-core';
 
const scrapelessUrl = 'wss://browser.scrapeless.com/browser?token=your_api_key&session_ttl=180&proxy_country=ANY';
 
async function scrapeWithResourceBlocking(url) {
    const browser = await puppeteer.connect({
        browserWSEndpoint: scrapelessUrl,
        defaultViewport: null
    });
    const page = await browser.newPage();
 
    // Enable request interception
    await page.setRequestInterception(true);
 
    // Define resource types to block
    const BLOCKED_TYPES = new Set([
        'image',
        'font',
        'media',
        'stylesheet',
    ]);
 
    // Intercept requests
    page.on('request', (request) => {
        if (BLOCKED_TYPES.has(request.resourceType())) {
            request.abort();
            console.log(`Blocked: ${request.resourceType()} - ${request.url().substring(0, 50)}...`);
        } else {
            request.continue();
        }
    });
 
    await page.goto(url, {waitUntil: 'domcontentloaded'});
 
    // Extract data
    const data = await page.evaluate(() => {
        return {
            title: document.title,
            content: document.body.innerText.substring(0, 1000)
        };
    });
 
    await browser.close();
    return data;
}
 
// Usage
scrapeWithResourceBlocking('https://www.scrapeless.com')
    .then(data => console.log('Scraping result:', data))
    .catch(error => console.error('Scraping failed:', error));

import puppeteer from 'puppeteer-core';
import { Scrapeless } from '@scrapeless-ai/sdk';
import puppeteer from 'puppeteer-core';
 
const client = new Scrapeless({ apiKey: 'API Key' });
 
const { browserWSEndpoint } = client.browser.create({
    session_name: 'sdk_test',
    session_ttl: 180,
    proxy_country: 'ANY',
    session_recording: true,
    fingerprint,
});
 
async function scrapeWithUrlBlocking(url) {
    const browser = await puppeteer.connect({
        browserWSEndpoint,
        defaultViewport: null
    });
    const page = await browser.newPage();
 
    // Enable request interception
    await page.setRequestInterception(true);
 
    // Define domains and URL patterns to block
    const BLOCKED_DOMAINS = [
        'google-analytics.com',
        'googletagmanager.com',
        'doubleclick.net',
        'facebook.net',
        'twitter.com',
        'linkedin.com',
        'adservice.google.com',
    ];
 
    const BLOCKED_PATHS = [
        '/ads/',
        '/analytics/',
        '/pixel/',
        '/tracking/',
        '/stats/',
    ];
 
    // Intercept requests
    page.on('request', (request) => {
        const url = request.url();
 
        // Check domain
        if (BLOCKED_DOMAINS.some(domain => url.includes(domain))) {
            request.abort();
            console.log(`Blocked domain: ${url.substring(0, 50)}...`);
            return;
        }
 
        // Check path
        if (BLOCKED_PATHS.some(path => url.includes(path))) {
            request.abort();
            console.log(`Blocked path: ${url.substring(0, 50)}...`);
            return;
        }
 
        // Allow other requests
        request.continue();
    });
 
    await page.goto(url, {waitUntil: 'domcontentloaded'});
 
    // Extract data
    const data = await page.evaluate(() => {
        return {
            title: document.title,
            content: document.body.innerText.substring(0, 1000)
        };
    });
 
    await browser.close();
    return data;
}
 
// Usage
scrapeWithUrlBlocking('https://www.scrapeless.com')
    .then(data => console.log('Scraping result:', data))
    .catch(error => console.error('Scraping failed:', error));

import puppeteer from 'puppeteer-core';
 
const scrapelessUrl = 'wss://browser.scrapeless.com/browser?token=your_api_key&session_ttl=180&proxy_country=ANY';
 
async function scrapeWithUrlBlocking(url) {
    const browser = await puppeteer.connect({
        browserWSEndpoint: scrapelessUrl,
        defaultViewport: null
    });
    const page = await browser.newPage();
 
    // Enable request interception
    await page.setRequestInterception(true);
 
    // Define domains and URL patterns to block
    const BLOCKED_DOMAINS = [
        'google-analytics.com',
        'googletagmanager.com',
        'doubleclick.net',
        'facebook.net',
        'twitter.com',
        'linkedin.com',
        'adservice.google.com',
    ];
 
    const BLOCKED_PATHS = [
        '/ads/',
        '/analytics/',
        '/pixel/',
        '/tracking/',
        '/stats/',
    ];
 
    // Intercept requests
    page.on('request', (request) => {
        const url = request.url();
 
        // Check domain
        if (BLOCKED_DOMAINS.some(domain => url.includes(domain))) {
            request.abort();
            console.log(`Blocked domain: ${url.substring(0, 50)}...`);
            return;
        }
 
        // Check path
        if (BLOCKED_PATHS.some(path => url.includes(path))) {
            request.abort();
            console.log(`Blocked path: ${url.substring(0, 50)}...`);
            return;
        }
 
        // Allow other requests
        request.continue();
    });
 
    await page.goto(url, {waitUntil: 'domcontentloaded'});
 
    // Extract data
    const data = await page.evaluate(() => {
        return {
            title: document.title,
            content: document.body.innerText.substring(0, 1000)
        };
    });
 
    await browser.close();
    return data;
}
 
// Usage
scrapeWithUrlBlocking('https://www.scrapeless.com')
    .then(data => console.log('Scraping result:', data))
    .catch(error => console.error('Scraping failed:', error));

import puppeteer from 'puppeteer-core';
import { Scrapeless } from '@scrapeless-ai/sdk';
 
const client = new Scrapeless({ apiKey: 'API Key' });
 
const { browserWSEndpoint } = client.browser.create({
    session_name: 'sdk_test',
    session_ttl: 180,
    proxy_country: 'ANY',
    session_recording: true,
    fingerprint,
});
 
async function scrapeWithMobileEmulation(url) {
    const browser = await puppeteer.connect({
        browserWSEndpoint,
        defaultViewport: null
    });
 
    const page = await browser.newPage();
 
    // Set mobile device simulation
    const iPhone = KnownDevices['iPhone 15 Pro'];
    await page.emulate(iPhone);
 
    await page.goto(url, {waitUntil: 'domcontentloaded'});
    // Extract data
    const data = await page.evaluate(() => {
        return {
            title: document.title,
            content: document.body.innerText.substring(0, 1000)
        };
    });
 
    await browser.close();
    return data;
}
 
// Usage
scrapeWithMobileEmulation('https://www.scrapeless.com')
    .then(data => console.log('Scraping result:', data))
    .catch(error => console.error('Scraping failed:', error));

import puppeteer, {KnownDevices} from 'puppeteer-core';
 
const scrapelessUrl = 'wss://browser.scrapeless.com/browser?token=your_api_key&session_ttl=180&proxy_country=ANY';
 
async function scrapeWithMobileEmulation(url) {
    const browser = await puppeteer.connect({
        browserWSEndpoint: scrapelessUrl,
        defaultViewport: null
    });
 
    const page = await browser.newPage();
 
    // Set mobile device simulation
    const iPhone = KnownDevices['iPhone 15 Pro'];
    await page.emulate(iPhone);
 
    await page.goto(url, {waitUntil: 'domcontentloaded'});
    // Extract data
    const data = await page.evaluate(() => {
        return {
            title: document.title,
            content: document.body.innerText.substring(0, 1000)
        };
    });
 
    await browser.close();
    return data;
}
 
// Usage
scrapeWithMobileEmulation('https://www.scrapeless.com')
    .then(data => console.log('Scraping result:', data))
    .catch(error => console.error('Scraping failed:', error));

import puppeteer, {KnownDevices} from 'puppeteer-core';
import { Scrapeless } from '@scrapeless-ai/sdk';
 
const client = new Scrapeless({ apiKey: 'API Key' });
 
const { browserWSEndpoint } = client.browser.create({
    session_name: 'sdk_test',
    session_ttl: 180,
    proxy_country: 'ANY',
    session_recording: true,
    fingerprint,
});
 
async function optimizedScraping(url) {
    console.log(`Starting optimized scraping: ${url}`);
 
    // Record traffic usage
    let totalBytesUsed = 0;
 
    const browser = await puppeteer.connect({
        browserWSEndpoint,
        defaultViewport: null
    });
 
    const page = await browser.newPage();
 
    // Set mobile device simulation
    const iPhone = KnownDevices['iPhone 15 Pro'];
    await page.emulate(iPhone);
 
    // Set request interception
    await page.setRequestInterception(true);
 
    // Define resource types to block
    const BLOCKED_TYPES = [
        'image',
        'media',
        'font'
    ];
 
    // Define domains to block
    const BLOCKED_DOMAINS = [
        'google-analytics.com',
        'googletagmanager.com',
        'facebook.net',
        'doubleclick.net',
        'adservice.google.com'
    ];
 
    // Define URL paths to block
    const BLOCKED_PATHS = [
        '/ads/',
        '/analytics/',
        '/tracking/'
    ];
 
    // Intercept requests
    page.on('request', (request) => {
        const url = request.url();
        const resourceType = request.resourceType();
 
        // Check resource type
        if (BLOCKED_TYPES.includes(resourceType)) {
            console.log(`Blocked resource type: ${resourceType} - ${url.substring(0, 50)}...`);
            request.abort();
            return;
        }
 
        // Check domain
        if (BLOCKED_DOMAINS.some(domain => url.includes(domain))) {
            console.log(`Blocked domain: ${url.substring(0, 50)}...`);
            request.abort();
            return;
        }
 
        // Check path
        if (BLOCKED_PATHS.some(path => url.includes(path))) {
            console.log(`Blocked path: ${url.substring(0, 50)}...`);
            request.abort();
            return;
        }
 
        // Allow other requests
        request.continue();
    });
 
    // Monitor network traffic
    page.on('response', async (response) => {
        const headers = response.headers();
        const contentLength = headers['content-length'] ? parseInt(headers['content-length'], 10) : 0;
        totalBytesUsed += contentLength;
    });
 
    await page.goto(url, {waitUntil: 'domcontentloaded'});
 
    // Simulate scrolling to trigger lazy-loading content
    await page.evaluate(() => {
        window.scrollBy(0, window.innerHeight);
    });
 
    await new Promise(resolve => setTimeout(resolve, 1000))
 
    // Extract data
    const data = await page.evaluate(() => {
        return {
            title: document.title,
            content: document.body.innerText.substring(0, 1000),
            links: Array.from(document.querySelectorAll('a')).slice(0, 10).map(a => ({
                text: a.innerText,
                href: a.href
            }))
        };
    });
 
    // Output traffic usage statistics
    console.log(`\nTraffic Usage Statistics:`);
    console.log(`Used: ${(totalBytesUsed / 1024 / 1024).toFixed(2)} MB`);
 
    await browser.close();
    return data;
}
 
// Usage
optimizedScraping('https://www.scrapeless.com')
    .then(data => console.log('Scraping complete:', data))
    .catch(error => console.error('Scraping failed:', error));

import puppeteer, {KnownDevices} from 'puppeteer-core';
 
const scrapelessUrl = 'wss://browser.scrapeless.com/browser?token=your_api_key&session_ttl=180&proxy_country=ANY';
 
async function optimizedScraping(url) {
    console.log(`Starting optimized scraping: ${url}`);
 
    // Record traffic usage
    let totalBytesUsed = 0;
 
    const browser = await puppeteer.connect({
        browserWSEndpoint: scrapelessUrl,
        defaultViewport: null
    });
 
    const page = await browser.newPage();
 
    // Set mobile device simulation
    const iPhone = KnownDevices['iPhone 15 Pro'];
    await page.emulate(iPhone);
 
    // Set request interception
    await page.setRequestInterception(true);
 
    // Define resource types to block
    const BLOCKED_TYPES = [
        'image',
        'media',
        'font'
    ];
 
    // Define domains to block
    const BLOCKED_DOMAINS = [
        'google-analytics.com',
        'googletagmanager.com',
        'facebook.net',
        'doubleclick.net',
        'adservice.google.com'
    ];
 
    // Define URL paths to block
    const BLOCKED_PATHS = [
        '/ads/',
        '/analytics/',
        '/tracking/'
    ];
 
    // Intercept requests
    page.on('request', (request) => {
        const url = request.url();
        const resourceType = request.resourceType();
 
        // Check resource type
        if (BLOCKED_TYPES.includes(resourceType)) {
            console.log(`Blocked resource type: ${resourceType} - ${url.substring(0, 50)}...`);
            request.abort();
            return;
        }
 
        // Check domain
        if (BLOCKED_DOMAINS.some(domain => url.includes(domain))) {
            console.log(`Blocked domain: ${url.substring(0, 50)}...`);
            request.abort();
            return;
        }
 
        // Check path
        if (BLOCKED_PATHS.some(path => url.includes(path))) {
            console.log(`Blocked path: ${url.substring(0, 50)}...`);
            request.abort();
            return;
        }
 
        // Allow other requests
        request.continue();
    });
 
    // Monitor network traffic
    page.on('response', async (response) => {
        const headers = response.headers();
        const contentLength = headers['content-length'] ? parseInt(headers['content-length'], 10) : 0;
        totalBytesUsed += contentLength;
    });
 
    await page.goto(url, {waitUntil: 'domcontentloaded'});
 
    // Simulate scrolling to trigger lazy-loading content
    await page.evaluate(() => {
        window.scrollBy(0, window.innerHeight);
    });
 
    await new Promise(resolve => setTimeout(resolve, 1000))
 
    // Extract data
    const data = await page.evaluate(() => {
        return {
            title: document.title,
            content: document.body.innerText.substring(0, 1000),
            links: Array.from(document.querySelectorAll('a')).slice(0, 10).map(a => ({
                text: a.innerText,
                href: a.href
            }))
        };
    });
 
    // Output traffic usage statistics
    console.log(`\nTraffic Usage Statistics:`);
    console.log(`Used: ${(totalBytesUsed / 1024 / 1024).toFixed(2)} MB`);
 
    await browser.close();
    return data;
}
 
// Usage
optimizedScraping('https://www.scrapeless.com')
    .then(data => console.log('Scraping complete:', data))
    .catch(error => console.error('Scraping failed:', error));

import puppeteer from 'puppeteer-core';
import { Scrapeless } from '@scrapeless-ai/sdk';
 
const client = new Scrapeless({ apiKey: 'API Key' });
 
const { browserWSEndpoint } = client.browser.create({
    session_name: 'sdk_test',
    session_ttl: 180,
    proxy_country: 'ANY',
    session_recording: true,
    fingerprint,
});
 
async function unoptimizedScraping(url) {
  console.log(`Starting unoptimized scraping: ${url}`);
 
  // Record traffic usage
  let totalBytesUsed = 0;
 
  const browser = await puppeteer.connect({
    browserWSEndpoint,
    defaultViewport: null
  });
 
  const page = await browser.newPage();
 
  // Set request interception
  await page.setRequestInterception(true);
 
  // Intercept requests
  page.on('request', (request) => {
    request.continue();
  });
 
  // Monitor network traffic
  page.on('response', async (response) => {
    const headers = response.headers();
    const contentLength = headers['content-length'] ? parseInt(headers['content-length'], 10) : 0;
    totalBytesUsed += contentLength;
  });
 
  await page.goto(url, {waitUntil: 'domcontentloaded'});
 
  // Simulate scrolling to trigger lazy-loading content
  await page.evaluate(() => {
    window.scrollBy(0, window.innerHeight);
  });
 
  await new Promise(resolve => setTimeout(resolve, 1000))
 
  // Extract data
  const data = await page.evaluate(() => {
    return {
      title: document.title,
      content: document.body.innerText.substring(0, 1000),
      links: Array.from(document.querySelectorAll('a')).slice(0, 10).map(a => ({
        text: a.innerText,
        href: a.href
      }))
    };
  });
 
  // Output traffic usage statistics
  console.log(`\nTraffic Usage Statistics:`);
  console.log(`Used: ${(totalBytesUsed / 1024 / 1024).toFixed(2)} MB`);
 
  await browser.close();
  return data;
}
 
// Usage
unoptimizedScraping('https://www.scrapeless.com')
  .then(data => console.log('Scraping complete:', data))
  .catch(error => console.error('Scraping failed:', error));

import puppeteer from 'puppeteer-core';
 
const scrapelessUrl = 'wss://browser.scrapeless.com/browser?token=your_api_key&session_ttl=180&proxy_country=ANY';
 
async function unoptimizedScraping(url) {
  console.log(`Starting unoptimized scraping: ${url}`);
 
  // Record traffic usage
  let totalBytesUsed = 0;
 
  const browser = await puppeteer.connect({
    browserWSEndpoint: scrapelessUrl,
    defaultViewport: null
  });
 
  const page = await browser.newPage();
 
  // Set request interception
  await page.setRequestInterception(true);
 
  // Intercept requests
  page.on('request', (request) => {
    request.continue();
  });
 
  // Monitor network traffic
  page.on('response', async (response) => {
    const headers = response.headers();
    const contentLength = headers['content-length'] ? parseInt(headers['content-length'], 10) : 0;
    totalBytesUsed += contentLength;
  });
 
  await page.goto(url, {waitUntil: 'domcontentloaded'});
 
  // Simulate scrolling to trigger lazy-loading content
  await page.evaluate(() => {
    window.scrollBy(0, window.innerHeight);
  });
 
  await new Promise(resolve => setTimeout(resolve, 1000))
 
  // Extract data
  const data = await page.evaluate(() => {
    return {
      title: document.title,
      content: document.body.innerText.substring(0, 1000),
      links: Array.from(document.querySelectorAll('a')).slice(0, 10).map(a => ({
        text: a.innerText,
        href: a.href
      }))
    };
  });
 
  // Output traffic usage statistics
  console.log(`\nTraffic Usage Statistics:`);
  console.log(`Used: ${(totalBytesUsed / 1024 / 1024).toFixed(2)} MB`);
 
  await browser.close();
  return data;
}
 
// Usage
unoptimizedScraping('https://www.scrapeless.com')
  .then(data => console.log('Scraping complete:', data))
  .catch(error => console.error('Scraping failed:', error));