爬虫浏览器 - 浏览器 API

                              const pw = require('playwright');

const SBR_CDP = 'wss://brd-customer-CUSTOMER_ID-zone-ZONE_NAME:[email protected]:9222';

async function main() {
    console.log('Connecting to Browser API...');
    const browser = await pw.chromium.connectOverCDP(SBR_CDP);
    try {
        const page = await browser.newPage();
        console.log('Connected! Navigating to https://example.com...');
        await page.goto('https://example.com');
        console.log('Navigated! Scraping page content...');
        const html = await page.content();
        console.log(html);
    } finally {
        await browser.close();
    }
}

main().catch(err => {
    console.error(err.stack || err);
    process.exit(1);
});
                              
                            

                              import asyncio
from playwright.async_api import async_playwright

SBR_WS_CDP = 'wss://brd-customer-CUSTOMER_ID-zone-ZONE_NAME:[email protected]:9222'

async def run(pw):
    print('Connecting to Browser API...')
    browser = await pw.chromium.connect_over_cdp(SBR_WS_CDP)
    try:
        page = await browser.new_page()
        print('Connected! Navigating to https://example.com...')
        await page.goto('https://example.com')
        print('Navigated! Scraping page content...')
        html = await page.content()
        print(html)
    finally:
        await browser.close()

async def main():
    async with async_playwright() as playwright:
        await run(playwright)

if __name__ == '__main__':
    asyncio.run(main())
                              
                            

                              const puppeteer = require('puppeteer-core');

const SBR_WS_ENDPOINT = 'wss://brd-customer-CUSTOMER_ID-zone-ZONE_NAME:[email protected]:9222';

async function main() {
    console.log('Connecting to Browser API...');
    const browser = await puppeteer.connect({
        browserWSEndpoint: SBR_WS_ENDPOINT,
    });
    try {
        const page = await browser.newPage();
        console.log('Connected! Navigating to https://example.com...');
        await page.goto('https://example.com');
        console.log('Navigated! Scraping page content...');
        const html = await page.content();
        console.log(html)
    } finally {
        await browser.close();
    }
}

main().catch(err => {
    console.error(err.stack || err);
    process.exit(1);
});
                              
                            

                              const { Builder, Browser } = require('selenium-webdriver');

const SBR_WEBDRIVER = 'https://brd-customer-CUSTOMER_ID-zone-ZONE_NAME:[email protected]:9515';

async function main() {
    console.log('Connecting to Browser API...');
    const driver = await new Builder()
        .forBrowser(Browser.CHROME)
        .usingServer(SBR_WEBDRIVER)
        .build();
    try {
        console.log('Connected! Navigating to https://example.com...');
        await driver.get('https://example.com');
        console.log('Navigated! Scraping page content...');
        const html = await driver.getPageSource();
        console.log(html);
    } finally {
        driver.quit();
    }
}

main().catch(err => {
    console.error(err.stack || err);
    process.exit(1);
});
                              
                            

                              from selenium.webdriver import Remote, ChromeOptions
from selenium.webdriver.chromium.remote_connection import ChromiumRemoteConnection

SBR_WEBDRIVER = 'https://brd-customer-CUSTOMER_ID-zone-ZONE_NAME:[email protected]:9515'

def main():
    print('Connecting to Browser API...')
    sbr_connection = ChromiumRemoteConnection(SBR_WEBDRIVER, 'goog', 'chrome')
    with Remote(sbr_connection, options=ChromeOptions()) as driver:
        print('Connected! Navigating to https://example.com...')
        driver.get('https://example.com')
        print('Navigated! Scraping page content...')
        html = driver.page_source
        print(html)

if __name__ == '__main__':
    main()