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. 异步模式

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. 代码生成

​ Playwright可以录制在浏览器的操作并自动生成代码。 【codegen】

# 查看codegen命令的参数
playwright codegen --help

# 例如：启动firefox浏览器，并将操作结果输出到script.py文件
playwright codegen -o script.py -b firefox https://www.baidu.com

3. 选择器

1. 文本选择

page.click("text=Log in")

2. CSS选择器

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

3. XPath

# 需在开头自行指定 “xpath=字符串”
page.click("xpath=//button")

4. 事件监听

​ page对象提供一个on方法，用来监听页面中发生的各个事件，例如close, console, load, request, response等。

​ 对于Ajax加载的数据，即使这个Ajax请求中有加密参数，也不用担心，因为我们截获的是最后的响应结果

from playwright.sync_api import Playwright, sync_playwright


# def on_response(response):
#     """
#     输出浏览器Network面板中的所有请求和相应
#     """
#     print(f'Status {response.status}: {response.url}')


def on_response(response):
    """
    通过on_response方法拦截Ajax请求，直接获取响应结果。
    """
    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()
    # 监听response事件，同时将回调方法设为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. 获取网页源码：page.content()

2. 页面点击：page.click(selector, kwargs) 参考官方文档

3. 文本输入：page.fill(selector, value, kwargs)

4. 获取节点属性：page.get_attribute(selector, name, kwargs)

   # 只返回单个节点属性
   href = page.get_attribute("a.name", "href")
   

5. 获取多个节点：query_selector_all()

   1. 节点属性：element.get_attribute(name)
   2. 节点文本：element.text_content()

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

6. 获取单个节点：query_selector()

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