playwright基础样例demo大全

安装

pip install pytest-playwright

playwright install

优点

• 支持异步操作（assync_api）
• 同步操作调用：sync_api

基础示例

同步代码

from playwright.sync_api import sync_playwright

with sync_playwright() as playwright:
    browser = playwright.chromium.launch()
    page = browser.new_page()
    page.goto('https://www.baidu.com')
    print(page.title())
    browser.close()

异步代码

• 异步代码需要两个关键字：async和await
• 异步方法启动需要使用导入asyncio包，运行asyncio.run()执行main()方法。

import asyncio
from playwright.async_api import async_playwright

async def main():
    async with async_playwright() as p:
        # headless = False : 是否启动无头模式，无头模式是不弹出浏览器，后台运行
        browser = await p.chromium.launch(headless=False)
        page = await browser.new_page()
        await page.goto('https://www.baidu.com')
        print(await page.title())

        await browser.close()

asyncio.run(main())

启动不同浏览器

• 浏览器默认情况下是以无痕模式启动
• channel：“chrome”, “chrome-beta”, “chrome-dev”, “chrome-canary”, “msedge”, “msedge-beta”, “msedge-dev”, or “msedge-canary”
• chromium：谷歌开源内核

def run(playwright: Playwright) -> None:
    # "chrome", "chrome-beta", "chrome-dev", "chrome-canary", "msedge", "msedge-beta", "msedge-dev", or "msedge-canary"
    browser = playwright.chromium.launch(headless=False, channel='msedge')
    context = browser.new_context()
    page = context.new_page()
    page.goto("https://www.baidu.com/")
    # ---------------------
    context.close()
    browser.close()
    
with sync_playwright() as playwright:
    run(playwright)

• 火狐

from playwright.sync_api import sync_playwright
with sync_playwright() as playwright:
	# 火狐
    browser_f = playwright.firefox.launch()
    page = browser_f.new_page()
    page.goto('https://www.bing.com')
    print(page.title())
    browser_f.close()

启用本地浏览器（使用浏览器cookie信息）

from playwright.sync_api import Playwright, sync_playwright
import getpass

user_data_dir = fr'C:\Users\{getpass.getuser()}\AppData\Local\Google\Chrome\User Data'

def run(playwright: Playwright) -> None:
    context = playwright.chromium.launch_persistent_context(
        # 本地浏览器的数据目录
        user_data_dir=user_data_dir,
        # 指定Google
        channel='chrome',
        # 无头模式
        headless=False
    )
    page = context.new_page()
    page.goto("https://www.baidu.com/")

    page.pause()
    # ---------------------
    context.close()

with sync_playwright() as playwright:
    run(playwright)

playwright页面接管

• 针对场景：退出浏览器就需要重新登录，并且存在复杂的验证信息

设置环境变量和cmd启动浏览器

1. 将起始位置添加到环境变量中，并且保证cmd命令窗口输出chrome直接启动浏览器。
   
2. 在cmd窗口中，输入启动命令和配置参数信息。

• 指定端口：--remote-debugging-port=8888
• 指定浏览器数据目录：--user-data-dir="D:\playwright_chrome_user_data"

chrome --remote-debugging-port=8888 --user-data-dir="D:\playwright_chrome_user_data"

3. 使用cdp链接chrome浏览器。

from playwright.sync_api import Playwright, sync_playwright


def run(playwright: Playwright) -> None:
    browser = playwright.chromium.connect_over_cdp('http://localhost:8888')
    page = browser.contexts[0].pages[0]
    page.goto("https://www.baidu.com/")

    page.pause()
    # ---------------------
    page.close()


with sync_playwright() as playwright:
    run(playwright)

窗口最大化

• --start-maximized：该参数来源是chromium浏览器命令行参数列表，https://peter.sh/experiments/chromium-command-line-switches/。
• no_viewport=True

import re
from playwright.sync_api import Playwright, sync_playwright, expect


def run(playwright: Playwright) -> None:
    browser = playwright.chromium.launch(headless=False, args=['--start-maximized'])
    context = browser.new_context(no_viewport=True)
    page = context.new_page()
    page.goto("https://www.baidu.com/")

    # ---------------------
    context.close()
    browser.close()


with sync_playwright() as playwright:
    run(playwright)

录制脚本

• 命令：

playwright codegen

• 示例：playwright codegen https://www.baidu.com

from playwright.sync_api import Playwright, sync_playwright, expect

def run(playwright: Playwright) -> None:
    browser = playwright.chromium.launch(headless=False)
    context = browser.new_context()
    page = context.new_page()
    page.goto("http://xx.xx.xx.xx:8080/login")
    page.get_by_role("textbox", name="用户名").click()
    page.get_by_role("textbox", name="用户名").fill("admin")
    page.get_by_role("textbox", name="密码").click()
    page.get_by_role("textbox", name="密码").fill("admin123")
    page.get_by_role("button", name="登录").click()
    # ---------------------
    context.close()
    browser.close()

with sync_playwright() as playwright:
    run(playwright)

录制脚本保存身份验证状态

• --save-storage：会保存cookie和localStorage。
• --load-storage：加载保存在本地的cookie信息。
• open ：playwright open启动浏览器与codegen效果相似。

保存cookie信息

playwright codegen --save-storage=auto.json

加载cookie信息

playwright open http://xx.xx.xx.xx:8080/system/user --load-storage=auto.json

代码中保存身份状态信息

• 若导出的文件cookie信息为空，需要确认网站cookie的失效机制，是否关闭浏览器或者关闭页面即失效。

from playwright.sync_api import Playwright, sync_playwright, expect

def run(playwright: Playwright) -> None:
    browser = playwright.chromium.launch(headless=False)
    context = browser.new_context()
    page = context.new_page()
    page.goto("http://xx.xx.xx.xx:8080/login")
    page.get_by_role("textbox", name="用户名").click()
    page.get_by_role("textbox", name="用户名").fill("admin")
    page.get_by_role("textbox", name="密码").click()
    page.get_by_role("textbox", name="密码").fill("admin123")
    page.get_by_role("button", name="登录").click()
	# 添加等待事件，保证登录信息的获取
	page.wait_for_url(url='http://xx.xx.xx.xx:8080/index')

	
    # 保存storage state 到指定的文件
    storage = context.storage_state(path="../auth/ry_auto.json")
    # ---------------------
    context.close()
    browser.close()

with sync_playwright() as playwright:
    run(playwright)

代码中读取身份状态信息

from playwright.sync_api import Playwright, sync_playwright, expect

def run(playwright: Playwright) -> None:
    browser = playwright.chromium.launch(headless=False)
	context = browser.new_context(storage_state="state.json")
	

playwright发送api接口请求

@pytest.fixture(scope="session")
def api_request_context(
    playwright: Playwright,
) -> Generator[APIRequestContext, None, None]:
    headers = {
        # We set this header per GitHub guidelines.
        "Accept": "application/vnd.github.v3+json",
        # Add authorization token to all requests.
        # Assuming personal access token available in the environment.
        "Authorization": f"token {GITHUB_API_TOKEN}",
    }
    request_context = playwright.request.new_context(
        base_url="https://api.github.com", extra_http_headers=headers
    )
    yield request_context
    request_context.dispose()