pa/response_parser.py

# response_parser.py
import requests
import json
import re
from pathlib import Path

# Cookie 信息
COOKIES = {
    'platformUser_session': 'eyJsYXN0QWNjZXNzZWQiOjE3NTkxNDc4NjYzMzJ9.2gNtuRzCQH%2BoNra1%2B1WXxcDtTmW91yYVAOLbH6Ry%2BLM',
    '_manage_session': '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%3D%3D.jBwQkblyoEP6t7OELXxUMKkoU9%2FJWWQsZPg25SZSz5o'
}

def get_api_response():
    """获取API响应"""
    session = requests.Session()
    
    # 设置Cookie
    for name, value in COOKIES.items():
        session.cookies.set(name, value, domain='prod-eu-cmp.simbalinkglobal.com')
    
    # 设置请求头
    headers = {
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
        'Accept-Encoding': 'gzip, deflate, br, zstd',
        'Accept-Language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',
        'Cache-Control': 'max-age=0',
        'Connection': 'keep-alive',
        'Host': 'prod-eu-cmp.simbalinkglobal.com',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
    }
    session.headers.update(headers)
    
    url = "https://prod-eu-cmp.simbalinkglobal.com/simcustomer?filterData=N4IgkgxhCWAmAy0DOAXEAuEAOAnFrATAMw4AM5AjKUQKw1GkFYDsANLvsWZdXURThwA2dnkIlypKrXqMCpUZwk8ZRIcyFFF47uTwVmBoQe1dJ0vtQAsNU8qm966w3d0X6WUlYqvzj-syevip8NOLBDqo4NDhEIKwgqACGKACuSBggIAC%2BQA&pageSize=50"
    
    try:
        response = session.get(url, timeout=30)
        if response.status_code == 200:
            return response.text
        else:
            print(f"请求失败: {response.status_code}")
            return None
    except Exception as e:
        print(f"API调用异常: {e}")
        return None

def parse_response(response_text):
    """解析响应内容"""
    print("=== 响应内容分析 ===")
    print(f"响应长度: {len(response_text)} 字符")
    
    # 查找ICCID模式
    iccid_pattern = r'8988239000\d{8}'
    iccids = re.findall(iccid_pattern, response_text)
    
    print(f"找到 {len(iccids)} 个ICCID:")
    for iccid in iccids:
        print(f"  - {iccid}")
    
    # 查找JSON数据
    json_patterns = [
        r'\{[^{}]*"iccid"[^{}]*\}',
        r'\[[^\[\]]*"8988239000\d{8}"[^\[\]]*\]',
        r'\{.*"data".*\}',
        r'\{.*"result".*\}'
    ]
    
    for pattern in json_patterns:
        matches = re.findall(pattern, response_text, re.DOTALL)
        if matches:
            print(f"\n找到JSON数据模式: {pattern}")
            for match in matches:
                try:
                    json_data = json.loads(match)
                    print(f"JSON数据: {json.dumps(json_data, indent=2, ensure_ascii=False)}")
                except:
                    print(f"原始数据: {match[:200]}...")
    
    # 查找表格数据
    table_patterns = [
        r'<table[^>]*>.*?</table>',
        r'<tbody[^>]*>.*?</tbody>',
        r'<tr[^>]*>.*?</tr>'
    ]
    
    for pattern in table_patterns:
        matches = re.findall(pattern, response_text, re.DOTALL | re.IGNORECASE)
        if matches:
            print(f"\n找到表格数据: {len(matches)} 个匹配")
            for i, match in enumerate(matches[:3]):  # 只显示前3个
                print(f"表格 {i+1}: {match[:200]}...")
    
    # 查找JavaScript数据
    js_patterns = [
        r'window\.__INITIAL_STATE__\s*=\s*(\{.*?\});',
        r'window\.__DATA__\s*=\s*(\{.*?\});',
        r'var\s+data\s*=\s*(\{.*?\});',
        r'const\s+data\s*=\s*(\{.*?\});'
    ]
    
    for pattern in js_patterns:
        matches = re.findall(pattern, response_text, re.DOTALL)
        if matches:
            print(f"\n找到JavaScript数据: {pattern}")
            for match in matches:
                try:
                    json_data = json.loads(match)
                    print(f"JS数据: {json.dumps(json_data, indent=2, ensure_ascii=False)}")
                except:
                    print(f"原始JS数据: {match[:200]}...")
    
    return iccids

def create_working_api():
    """创建可用的API函数"""
    print("\n=== 创建可用的API函数 ===")
    
    template = '''
# 可用的批量查询API
import requests
import json
import re
from pathlib import Path

# Cookie 信息
COOKIES = {
    'platformUser_session': 'eyJsYXN0QWNjZXNzZWQiOjE3NTkxNDc4NjYzMzJ9.2gNtuRzCQH%2BoNra1%2B1WXxcDtTmW91yYVAOLbH6Ry%2BLM',
    '_manage_session': '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%3D%3D.jBwQkblyoEP6t7OELXxUMKkoU9%2FJWWQsZPg25SZSz5o'
}

def read_query_items(path):
    """读取查询项目文件"""
    p = Path(path)
    if not p.exists():
        raise FileNotFoundError(f"{path} not found.")
    
    encodings = ['utf-8', 'gbk', 'utf-8-sig', 'cp1252']
    for encoding in encodings:
        try:
            lines = [l.strip() for l in p.read_text(encoding=encoding).splitlines() if l.strip()]
            if lines:
                return lines
        except Exception:
            continue
    
    raise Exception("无法读取文件")

def query_iccids_batch(iccid_list, page_size=50):
    """批量查询ICCID"""
    session = requests.Session()
    
    # 设置Cookie
    for name, value in COOKIES.items():
        session.cookies.set(name, value, domain='prod-eu-cmp.simbalinkglobal.com')
    
    # 设置请求头
    headers = {
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
        'Accept-Encoding': 'gzip, deflate, br, zstd',
        'Accept-Language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',
        'Cache-Control': 'max-age=0',
        'Connection': 'keep-alive',
        'Host': 'prod-eu-cmp.simbalinkglobal.com',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
    }
    session.headers.update(headers)
    
    # 使用您提供的filterData（需要根据实际ICCID列表调整）
    filter_data = "N4IgkgxhCWAmAy0DOAXEAuEAOAnFrATAMw4AM5AjKUQKw1GkFYDsANLvsWZdXURThwA2dnkIlypKrXqMCpUZwk8ZRIcyFFF47uTwVmBoQe1dJ0vtQAsNU8qm966w3d0X6WUlYqvzj-syevip8NOLBDqo4NDhEIKwgqACGKACuSBggIAC%2BQA"
    url = f"https://prod-eu-cmp.simbalinkglobal.com/simcustomer?filterData={filter_data}&pageSize={page_size}"
    
    try:
        response = session.get(url, timeout=30)
        if response.status_code == 200:
            return response.text
        else:
            print(f"请求失败: {response.status_code}")
            return None
    except Exception as e:
        print(f"API调用异常: {e}")
        return None

def extract_iccids_from_response(response_text):
    """从响应中提取ICCID"""
    iccid_pattern = r'8988239000\\d{8}'
    iccids = re.findall(iccid_pattern, response_text)
    return iccids

def main():
    """主函数"""
    # 读取查询项
    query_items = read_query_items('text.txt')
    print(f"读取到 {len(query_items)} 个查询项")
    
    # 分批处理
    batch_size = 50
    batches = [query_items[i:i+batch_size] for i in range(0, len(query_items), batch_size)]
    
    all_results = []
    for i, batch in enumerate(batches, 1):
        print(f"\\n处理批次 {i}/{len(batches)}: {len(batch)} 个ICCID")
        
        # 查询批次
        response = query_iccids_batch(batch)
        if response:
            # 提取结果
            found_iccids = extract_iccids_from_response(response)
            print(f"找到 {len(found_iccids)} 个ICCID结果")
            all_results.extend(found_iccids)
        
        # 批次间等待
        if i < len(batches):
            time.sleep(2)
    
    print(f"\\n总共找到 {len(all_results)} 个ICCID结果")
    
    # 保存结果
    with open('api_results.txt', 'w', encoding='utf-8') as f:
        for iccid in all_results:
            f.write(f"{iccid}\\n")
    
    print("结果已保存到 api_results.txt")

if __name__ == "__main__":
    import time
    main()
'''
    
    with open('working_api.py', 'w', encoding='utf-8') as f:
        f.write(template)
    
    print("可用的API函数已保存到 working_api.py")

def main():
    print("=== 响应解析工具 ===")
    
    # 获取API响应
    response_text = get_api_response()
    if not response_text:
        print("无法获取API响应")
        return
    
    # 解析响应
    iccids = parse_response(response_text)
    
    # 创建可用的API
    create_working_api()
    
    print("\n=== 解析完成 ===")
    print("建议:")
    print("1. 查看找到的ICCID列表")
    print("2. 使用 working_api.py 进行批量查询")
    print("3. 需要进一步分析filterData的生成规则")

if __name__ == "__main__":
    main()