baijiahao_data_crawl/mitmproxy_capture.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
mitmproxy Cookie捕获脚本
自动捕获百家号账号的Cookie并保存到JSON文件

使用方法：
    mitmdump -s mitmproxy_capture.py -p 8888

在浏览器中设置代理：
    HTTP代理: 127.0.0.1:8888
    HTTPS代理: 127.0.0.1:8888
    
然后访问百家号页面，脚本会自动捕获Cookie
"""

import json
import os
from datetime import datetime
from mitmproxy import http
import requests


class BaijiahaoCapture:
    """百家号Cookie捕获器"""
    
    def __init__(self):
        self.script_dir = os.path.dirname(os.path.abspath(__file__))
        self.output_file = os.path.join(self.script_dir, "captured_account_cookies.json")
        self.captured_cookies = self.load_existing_cookies()
        self.base_url = "https://baijiahao.baidu.com"
        self.processed_cookies = set()  # 记录已处理的Cookie，避免重复
        
        print("\n" + "="*70)
        print("百家号Cookie捕获脚本已启动")
        print("="*70)
        print(f"监听端口: 8888")
        print(f"目标域名: baijiahao.baidu.com")
        print(f"保存路径: {self.output_file}")
        print("\n提示：")
        print("  - 如果在浏览器中使用，请手动设置代理")
        print("  - 如果在小火花客户端中使用，请设置系统代理")
        print("  - Windows系统代理: 127.0.0.1:8888")
        print("="*70 + "\n")
    
    def load_existing_cookies(self):
        """加载已有的Cookie数据"""
        try:
            if os.path.exists(self.output_file):
                with open(self.output_file, 'r', encoding='utf-8') as f:
                    return json.load(f)
        except Exception as e:
            print(f"[!] 加载已有Cookie失败: {e}")
        return {}
    
    def save_cookies(self):
        """保存Cookie到文件"""
        try:
            with open(self.output_file, 'w', encoding='utf-8') as f:
                json.dump(self.captured_cookies, f, ensure_ascii=False, indent=2)
            print(f"[OK] Cookie已保存到: {self.output_file}")
            return True
        except Exception as e:
            print(f"[X] 保存Cookie失败: {e}")
            return False
    
    def parse_cookies(self, cookie_header: str) -> dict:
        """解析Cookie字符串为字典"""
        cookies = {}
        if not cookie_header:
            return cookies
        
        for item in cookie_header.split(';'):
            item = item.strip()
            if '=' in item:
                name, value = item.split('=', 1)
                cookies[name.strip()] = value.strip()
        
        return cookies
    
    def get_account_info(self, cookies: dict) -> dict | None:
        """调用百家号API获取账号信息"""
        try:
            # 获取token
            token = cookies.get('bjhStoken') or cookies.get('devStoken')
            if not token:
                print("  [!] Cookie中未找到 bjhStoken 或 devStoken")
                return None
            
            # 构建请求
            api_url = f"{self.base_url}/builder/app/appinfo"
            headers = {
                'Accept': 'application/json, text/plain, */*',
                'Accept-Language': 'zh-CN',
                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',
                'Referer': f'{self.base_url}/builder/rc/incomecenter',
                'token': token,
            }
            
            # 构建Cookie字符串
            cookie_str = '; '.join([f"{k}={v}" for k, v in cookies.items()])
            headers['Cookie'] = cookie_str
            
            # 创建一个新的session，不使用代理
            import requests
            session = requests.Session()
            session.trust_env = False  # 不使用系统代理
            
            # 发送请求（直连，不走代理）
            response = session.get(api_url, headers=headers, timeout=30, proxies={})
            
            if response.status_code == 200:
                data = response.json()
                if data.get('errno') == 0:
                    return data.get('data', {})
            
            return None
            
        except Exception as e:
            print(f"  [!] 获取账号信息失败: {e}")
            return None
    
    def request(self, flow: http.HTTPFlow) -> None:
        """处理HTTP请求"""
        # 调试：显示所有请求
        print(f"[ALL] {flow.request.method} {flow.request.pretty_url[:100]}")
        
        # 只处理百家号域名的请求
        if "baijiahao.baidu.com" not in flow.request.pretty_host:
            return
        
        # 调试：显示所有百家号请求
        print(f"[DEBUG] 检测到百家号请求: {flow.request.pretty_url}")
        
        # 获取Cookie
        cookie_header = flow.request.headers.get("Cookie", "")
        if not cookie_header:
            print("[DEBUG] 请求中没有Cookie")
            return
        
        # 解析Cookie
        cookies = self.parse_cookies(cookie_header)
        print(f"[DEBUG] Cookie数量: {len(cookies)}")
        
        # 检查是否包含关键Cookie（bjhStoken或devStoken）
        if 'bjhStoken' not in cookies and 'devStoken' not in cookies:
            print("[DEBUG] 缺少关键Cookie: bjhStoken或devStoken")
            return
        
        # 检查是否包含BDUSS（百度登录凭证）
        if 'BDUSS' not in cookies:
            print("[DEBUG] 缺少BDUSS登录凭证")
            return
        
        # 生成Cookie指纹，避免重复处理
        cookie_fingerprint = cookies.get('BDUSS', '')[:20]  # 使用BDUSS前20位作为指纹
        if cookie_fingerprint in self.processed_cookies:
            print(f"[DEBUG] Cookie已处理过，跳过 (指纹: {cookie_fingerprint})")
            return
        
        print("\n" + "-"*70)
        print(f"[√] 捕获到Cookie")
        print(f"    URL: {flow.request.pretty_url}")
        print(f"    Cookie数量: {len(cookies)}")
        print(f"    来源: {flow.request.headers.get('User-Agent', 'Unknown')[:50]}...")
        
        # 获取账号信息
        print("    正在获取账号信息...")
        account_info = self.get_account_info(cookies)
        
        if account_info:
            user_info = account_info.get('user', {})
            account_id = user_info.get('name', '') or user_info.get('username', '')
            
            if not account_id:
                print("    [!] 无法获取账号昵称，跳过保存")
                return
            
            # 标记为已处理
            self.processed_cookies.add(cookie_fingerprint)
            
            # 准备保存的数据
            account_data = {
                'cookies': cookies,
                'capture_time': datetime.now().strftime('%Y-%m-%d %H:%M:%S'),
                'capture_domain': 'baijiahao.baidu.com',
                'nick': user_info.get('name', ''),
                'username': user_info.get('username', ''),
                'app_id': str(user_info.get('shoubai_c_appid', '')),
                'user_id': user_info.get('userid', 0),
                'level': user_info.get('status_cn', ''),
                'domain': user_info.get('domain', ''),
                'wishes': user_info.get('wishes', ''),
                'media_type': user_info.get('media_type', ''),
            }
            
            # 保存到字典
            self.captured_cookies[account_id] = account_data
            
            # 保存到文件
            self.save_cookies()
            
            print(f"\n    [OK] 账号信息已保存")
            print(f"    账号ID: {account_id}")
            print(f"    昵称: {account_data['nick']}")
            print(f"    用户名: {account_data['username']}")
            print(f"    App ID: {account_data['app_id']}")
            print(f"    等级: {account_data['level']}")
            print(f"    领域: {account_data['domain']}")
        else:
            print("    [!] 获取账号信息失败，Cookie未保存")
            print("    原因：可能是Cookie已失效或网络问题")
            print("    建议：")
            print("      1. 确认已在小火花客户端中成功登录账号")
            print("      2. 刷新页面或重新切换账号")
            print("      3. 检查网络连接是否正常")
        
        print("-"*70 + "\n")


# 创建捕获器实例
addons = [BaijiahaoCapture()]