Web Scraping with Playwright in 2026: The Complete Guide

# Install Playwright
pip install playwright
playwright install chromium

from playwright.sync_api import sync_playwright

with sync_playwright() as p:
    browser = p.chromium.launch(
        proxy={
            "server": "http://gate.zentislabs.com:7777",
            "username": "USER",
            "password": "PASS",
        }
    )
    page = browser.new_page()
    page.goto("https://httpbin.org/ip")
    print(page.text_content("body"))
    browser.close()

from playwright.sync_api import sync_playwright

with sync_playwright() as p:
    browser = p.chromium.launch(
        headless=False,  # Headed mode passes more checks
        proxy={"server": "http://gate.zentislabs.com:7777",
               "username": "USER", "password": "PASS"},
        args=[
            "--disable-blink-features=AutomationControlled",
            "--disable-dev-shm-usage",
        ]
    )
    context = browser.new_context(
        viewport={"width": 1920, "height": 1080},
        user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36",
        locale="en-US",
        timezone_id="America/New_York",
    )
    # Remove webdriver property
    context.add_init_script("Object.defineProperty(navigator, 'webdriver', {get: () => undefined})")
    page = context.new_page()
    page.goto("https://target-site.com")
    print(page.title())
    browser.close()

# Block images, fonts, stylesheets, and trackers
def block_resources(route):
    blocked = ["image", "font", "stylesheet", "media"]
    if route.request.resource_type in blocked:
        route.abort()
    elif any(d in route.request.url for d in ["google-analytics", "facebook", "doubleclick"]):
        route.abort()
    else:
        route.continue_()

page.route("**/*", block_resources)
page.goto("https://target-site.com")

import asyncio
from playwright.async_api import async_playwright

async def scrape_url(browser, url):
    context = await browser.new_context(
        proxy={"server": "http://gate.zentislabs.com:7777",
               "username": "USER", "password": "PASS"}
    )
    page = await context.new_page()
    await page.goto(url, wait_until="domcontentloaded")
    title = await page.title()
    await context.close()
    return {"url": url, "title": title}

async def main():
    urls = ["https://example.com/page/" + str(i) for i in range(100)]
    async with async_playwright() as p:
        browser = await p.chromium.launch(
            proxy={"server": "http://gate.zentislabs.com:7777",
                   "username": "USER", "password": "PASS"}
        )
        # Process 10 pages at a time
        for batch in [urls[i:i+10] for i in range(0, len(urls), 10)]:
            results = await asyncio.gather(*[scrape_url(browser, u) for u in batch])
            for r in results:
                print(r)
        await browser.close()

asyncio.run(main())

import asyncio
from playwright.async_api import async_playwright, TimeoutError

async def scrape_with_retry(browser, url, max_retries=3):
    for attempt in range(max_retries):
        context = await browser.new_context(
            proxy={"server": "http://gate.zentislabs.com:7777",
                   "username": "USER", "password": "PASS"}
        )
        try:
            page = await context.new_page()
            response = await page.goto(url, timeout=30000)
            if response and response.status == 403:
                print(f"Blocked on attempt {attempt + 1}, retrying...")
                continue
            return await page.content()
        except TimeoutError:
            print(f"Timeout on attempt {attempt + 1}")
        finally:
            await context.close()
    return None

FROM mcr.microsoft.com/playwright/python:v1.42.0-jammy

WORKDIR /app
COPY requirements.txt .
RUN pip install -r requirements.txt
COPY . .

CMD ["python", "scraper.py"]