DMM ミストトレインガールズ〜霧の世界の車窓から〜 X 抓包求助

import os
import json
import re

def extract_bundle_urls():
    # 配置参数
    search_str = "catalog_ex_hd"
    target_key = "m_InternalIds"
    bundle_suffix = ".bundle"
    url_prefix_base = "https://native-assets3.mist-train-girls.com/production-assets/SavedAssets/Exe/Adult/{version}/adult_spine_stills_assets_spine/"
    output_file = "output.txt"
    
    # 存储所有提取的URL
    all_urls = []
    
    # 获取当前目录下所有包含指定字符串的JSON文件
    for filename in os.listdir('.'):
        if (search_str in filename) and filename.endswith('.json'):
            print(f"处理文件: {filename}")
            
            # 提取版本号（匹配catalog_ex_hd_后的字符串，直到.json前）
            version_match = re.search(f'{search_str}_(.*)\.json', filename)
            if not version_match:
                print(f"警告: {filename} 文件名格式不符合要求，无法提取版本号，已跳过")
                continue
            version = version_match.group(1)
            url_prefix = url_prefix_base.format(version=version)
            
            try:
                # 读取JSON文件
                with open(filename, 'r', encoding='utf-8') as f:
                    data = json.load(f)
                
                # 检查是否包含目标键
                if target_key in data and isinstance(data[target_key], list):
                    # 提取包含.bundle的字符串
                    for item in data[target_key]:
                        if bundle_suffix in item:
                            # 去除'/'前包括'/'的字符
                            if '/' in item:
                                bundle_name = item.split('/')[-1]
                                # 生成完整URL
                                full_url = url_prefix + bundle_name
                                all_urls.append(full_url)
            
            except json.JSONDecodeError:
                print(f"警告: {filename} 不是有效的JSON文件，已跳过")
            except Exception as e:
                print(f"处理 {filename} 时出错: {str(e)}")
    
    # 将结果写入输出文件
    with open(output_file, 'w', encoding='utf-8') as f:
        for url in all_urls:
            f.write(url + '\n')
    
    print(f"处理完成，共提取 {len(all_urls)} 个URL，已保存到 {output_file}")

if __name__ == "__main__":
    extract_bundle_urls()