Playwright的使用

1. 基本使用

1. 同步模式

from playwright.sync_api import sync_playwright

url = 'https://www.baidu.com'

with sync_playwright() as p:
    for browser_type in [p.chromium, p.firefox, p.webkit]:
        browser = browser_type.launch(headless=False)
        page = browser.new_page()
        page.goto(url)
        page.screenshot(path=f'sync-{browser_type.name}.png')
        print(page.title())
        browser.close()

2. 異步模式

import asyncio
from playwright.async_api import async_playwright

url = 'https://www.baidu.com'

async def main():
    async with async_playwright() as p:
        for browser_type in [p.chromium, p.firefox, p.webkit]:
            browser = await browser_type.launch()
            page = await browser.new_page()
            await page.goto(url)
            await page.screenshot(path=f'async-{browser_type.name}.png')
            print(await page.title())
            await browser.close()
asyncio.run(main())

2. 代碼生成

​ Playwright可以錄制在瀏覽器的操作並自動生成代碼。 【codegen】

# 查看codegen命令的參數
playwright codegen --help

# 例如：啟動firefox瀏覽器，並將操作結果輸出到script.py文件
playwright codegen -o script.py -b firefox https://www.baidu.com

3. 選擇器

1. 文本選擇

page.click("text=Log in")

2. CSS選擇器

page.click("button")
page.click("#nav-bar .contact-us-item")
page.click("[data-test=login-button]")
page.click("[aria-label='Sign in']")

3. XPath

# 需在開頭自行指定 “xpath=字符串”
page.click("xpath=//button")

4. 事件監聽

​ page對象提供一個on方法，用來監聽頁面中發生的各個事件，例如close, console, load, request, response等。

​ 對於Ajax加載的數據，即使這個Ajax請求中有加密參數，也不用擔心，因為我們截獲的是最后的響應結果

from playwright.sync_api import Playwright, sync_playwright


# def on_response(response):
#     """
#     輸出瀏覽器Network面板中的所有請求和相應
#     """
#     print(f'Status {response.status}: {response.url}')


def on_response(response):
    """
    通過on_response方法攔截Ajax請求，直接獲取響應結果。
    """
    if "api/movie/" in response.url and response.status == 200:
        print(response.json())


def run(playwright: Playwright) -> None:
    browser = playwright.chromium.launch(headless=False)
    page = browser.new_page()
    # 監聽response事件，同時將回調方法設為on_response
    page.on('response', on_response)
    page.goto("https://spa6.scrape.center/")
    page.wait_for_load_state("networkidle")
    page.close()
    browser.close()


with sync_playwright() as playwright:
    run(playwright)

5. 常用方法

1. 獲取網頁源碼：page.content()

2. 頁面點擊：page.click(selector, kwargs) 參考官方文檔

3. 文本輸入：page.fill(selector, value, kwargs)

4. 獲取節點屬性：page.get_attribute(selector, name, kwargs)

   # 只返回單個節點屬性
   href = page.get_attribute("a.name", "href")
   

5. 獲取多個節點：query_selector_all()

   1. 節點屬性：element.get_attribute(name)
   2. 節點文本：element.text_content()

   elements = page.query_selector_all("a.name")
   for element in elements:
     href = element.get_attribute("href")
     text = element.text_content()
   

6. 獲取單個節點：query_selector()

   element = page.query_selector("a.name")
   href = element.get_attribute("href")
   text = element.text_content()