Pydoll: scraping, the easier way

Install and automate with a single command. No drivers, no PATH, no setup hell.

from pydoll.browser import Chrome

async def run():
    async with Chrome() as browser:
        tab = await browser.start()
        await tab.go_to('https://example.com')

Run multiple tabs concurrently with true async/await.

import asyncio
from pydoll.browser import Chrome

async def scrape(url, tab):
    await tab.go_to(url)
    return await tab.execute_script('return document.title')

async def main():
    browser = Chrome()
    tab1 = await browser.start()
    tab2 = await browser.new_tab()
    titles = await asyncio.gather(
        scrape('https://google.com', tab1),
        scrape('https://github.com', tab2),
    )
    print(titles)

Your IDE knows exactly what each call returns.

# The IDE knows exactly what each call returns:
await tab.find(id='username')                 # → WebElement
await tab.find(id='username', find_all=True)  # → list[WebElement]
await tab.find(id='username', raise_exc=False)  # → WebElement | None

Perform HTTP in the same context as the tab: cookies, session and CORS are inherited automatically.

await tab.go_to('https://app.example.com/login')
await (await tab.find(id='email')).type_text('user@example.com')
await (await tab.find(id='password')).type_text('secret')
await (await tab.find(type='submit')).click()

response = await tab.request.get('https://app.example.com/api/user/profile')
print(response.json())

Readable element finding using attributes, CSS or XPath.

button = await tab.find(tag_name='button', text='Submit', class_name='btn-primary')
await button.click()

el = await tab.query('div[data-testid="awesome-element"]')

React to page and network changes in real-time using the built-in event system.

# Enable and listen to network events
await tab.enable_network_events()

async def on_response(params):
    info = params.get('response', {})
    print('status:', info.get('status'))

await tab.on('Network.responseReceived', on_response)