### 使用 Python 和 Selenium 抓取 API 返回数据 为了通过 Python 和 Selenium 获取 API 请求的响应数据，可以利用 `Network.getResponseBody` 函数来访问网络请求的内容。由于官方并未直接提供此类功能的支持[^4]，开发者通常会借助 Chrome DevTools Protocol (CDP) 来实现这一目标。 #### 实现方法 下面是一个简单的例子展示如何设置并捕获特定 URL 的 HTTP 响应： ```python from selenium import webdriver from selenium.webdriver.chrome.service import Service from selenium.webdriver.common.by import By import time def setup_driver(): options = webdriver.ChromeOptions() # 启用性能日志记录以便后续分析流量 options.add_experimental_option('perfLoggingPrefs', { 'enableNetwork': True, 'traceCategories': 'devtools.network' }) service = Service(executable_path='/path/to/chromedriver') driver = webdriver.Chrome(service=service, options=options) return driver driver = setup_driver() try: performance_log = [] def intercept_request(request_id, stage, params): nonlocal performance_log if "response" in params and request_id not in [item['requestId'] for item in performance_log]: entry = {"requestId": request_id} response_data = driver.execute_cdp_cmd( 'Network.getResponseBody', {'requestId': request_id}) entry["content"] = response_data.get("body", "") performance_log.append(entry) # 开始监听所有的网络事件 driver.execute_cdp_cmd('Network.enable', {}) driver.execute_cdp_cmd('Page.enable', {}) # 设置拦截器处理每一个完成的请求 driver.command_executor._commands["SEND_COMMAND_TO_DEVTOOLS"] = ("POST", '/session/$sessionId/chromium/send_command_and_get_result') result = driver.execute("SEND_COMMAND_TO_DEVTOOLS", dict(cmd='Network.setRequestInterception', params={'patterns': [{'urlPattern': '*'}]})) original_send = getattr(driver, "_send") def send(command, params=None): global original_send converted_params = {} if command == "Network.continueInterceptedRequest": intercept_request(params['interceptionId'], None, params) elif isinstance(params, dict): converted_params.update({k: v for k, v in params.items()}) try: resp = original_send(command, converted_params or {}) except Exception as e: pass return resp setattr(driver, "_send", send) url = "https://example.com/api/data" driver.get(url) while len(performance_log) == 0: time.sleep(1) finally: for log_entry in performance_log: print(f'Request ID: {log_entry["requestId"]}') print(f'Content:\n{log_entry["content"]}\n') driver.quit() ``` 这段代码展示了怎样配置浏览器选项以启用性能日志，并定义了一个自定义发送命令用于捕捉每次请求完成后调用 `Network.getResponseBody` 方法的结果。当页面加载完毕后，程序等待直到至少有一个有效的响应被捕获再打印出来。