CDP 직접 연결로 WebDriver 바이너리 없이 Chrome/Edge를 자동화하고 Pydantic 추출 엔진으로 DOM을 타입된 Python 객체로 변환

pip install pydoll-python

import asyncio
from pydoll.browser import Chrome
from pydoll.constants import Key

async def google_search(query: str):
    async with Chrome() as browser:
        tab = await browser.start()
        await browser.set_window_maximized()
        await tab.go_to('https://www.google.com')
        search_box = await tab.find(tag_name='textarea', name='q')
        await search_box.type_text(query, humanize=True)
        await tab.keyboard.press(Key.ENTER)
        await asyncio.sleep(5)
        print(f"Page loaded: {await tab.title}")

asyncio.run(google_search('pydoll'))

import asyncio
from pydoll.browser.chromium import Chrome
from pydoll.extractor import ExtractionModel, Field

class Quote(ExtractionModel):
    text: str = Field(selector='.text')
    author: str = Field(selector='.author')
    tags: list[str] = Field(selector='.tag')

async def extract_quotes():
    async with Chrome() as browser:
        tab = await browser.start()
        await tab.go_to('https://quotes.toscrape.com')
        quotes = await tab.extract_all(Quote, scope='.quote', timeout=5)
        for q in quotes:
            print(f'{q.author}: {q.text}')

asyncio.run(extract_quotes())