正则查找脚本（自用）

蕾米莉亚《'';

已于 2024-11-03 12:50:23 修改

阅读量157

点赞数 4

文章标签： python

于 2024-11-03 12:36:05 首次发布

本文链接：https://blog.youkuaiyun.com/2301_80867077/article/details/143463931

版权

import requests

import re
file_path="PaoluGPT.html"
with open(file_path, 'r', encoding='utf-8') as file:
    html_content = file.read()
pattern = r'<a\s+[^>]*href="([^"]*)"'
href_matches = re.findall(pattern, html_content)
print(len(href_matches))


for i in range(len(href_matches)):    
    url =   href_matches[i]    
    headers = {
    'Cookie': 'session=eyJ0b2tlbiI6IjIyMTA6UVZQ0lRREEyN3VTaURGeWs3VE1TQm1QMXE4WERKcWVuaFdiVFFWTGU3NXh0N2twZFFJaEFNYUR0WEJTRjIxM2dUUlhMM2ZvYW9MMGhlbUJwOVZ3dlVJR0UrTjg1dS91In0.Zyb3fg.qBHMDQeR2_nJqnCwrSRl3KaEM4A' ,
}                                                    
    response = requests.get(url,headers=headers)

    if response.status_code == 200:
        print(i)
        if 'flag' in response.text:

            print(i)
            exit()
print('no!!')