参考链接:https: // playwright. bootcss. com/ python/ docs/ intro
目标网站:https: // spa6. scrape. center/
通过观察,页面的信息是通过Ajax请求后返回的信息
下面使用playwright实现绕过token的获取直接拿到返回的数据
import asyncio
import json
from playwright. async_api import async_playwright, Playwright, Response
async def on_respone ( response: Response) :
if '/api/movie/' in response. url:
data = await response. text( )
print ( json. loads( data) )
async def run ( aspw: Playwright) :
browser = await aspw. chromium. launch( headless= False )
ctx = await browser. new_context( )
page = await ctx. new_page( )
page. on( 'response' , lambda response: asyncio. ensure_future( on_respone( response) ) )
await page. goto( 'https://spa6.scrape.center/' )
await page. wait_for_load_state( 'networkidle' )
await browser. close( )
async def main ( ) :
async with async_playwright( ) as aspw:
await run( aspw)
asyncio. run( main( ) )