python爬虫之playWright解密传参

news2024/10/7 1:32:40

参考文章：

Python和js实现逆向之加密参数破解_js btoa python_biyezuopinvip的博客-CSDN博客

JS逆向——借助playwright实现逆向_lishuangbo0123的博客-CSDN博客

简单方便的 JavaScript 逆向辅助模拟方法_token

自己整理的代码

from playwright.sync_api import sync_playwright
import time
import requests

def get_token1(offset):
    result = page.evaluate('''()=>{
        return window.encrypt("%s","%s")
    }''' % ( '/api/movie', offset))
    #print(result)
    return result

def get_token(params):
    result = page.evaluate(
        '()=>{return window.encrypt("%s")}' % params)
    print(result)
    return result
        
BASE_URL = 'https://spa6.scrape.center'
INDEX_URL = BASE_URL + '/api/movie?limit={limit}&offset={offset}&token={token}'
MAX_PAGE = 2

LIMIT = 10

browser = sync_playwright().start().chromium.launch()
page = browser.new_page()

page.route('**/js/chunk-19c920f8.c3a1129d.js', lambda route: route.fulfill(path='./chunk.js'))

#print(BASE_URL)

page.goto(BASE_URL)
#page.wait_for_load_state('networkidle')
print(page.title())

headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36',
            'Connection':'keep-alive',
            #'sec-ch-ua':'"Chromium";v="21", " Not;A Brand";v="99"',
            'Accept':'application/json, text/plain, */*',
            'sec-ch-ua-mobile':'?0',
            #'sec-ch-ua-platform':'"Windows"',
            'Sec-Fetch-Site':'same-origin',
            'Sec-Fetch-Mode':'cors',
            'Sec-Fetch-Dest':'empty',
            'Referer':'https://spa6.scrape.center/',
            'Host':'spa6.scrape.center',
            'Accept-Language':'zh-CN,zh;q=0.9'
}

for i in range(MAX_PAGE):

    offset = i * LIMIT
    token = get_token(offset)
    index_url = INDEX_URL.format(limit=LIMIT, offset=offset, token=token)

    print(index_url)
    

    #response = requests.get(index_url)
    response = requests.get(index_url, headers=headers)
    print( 'response', response.json)
    #print(response)