求助：使用Python脚本下载SAM排除列表的弹窗激活问题

我正在编写Python脚本从SAM网站下载最新排除列表，流程是：访问目标页面→点击初始OK弹窗→点击首个Zip下载链接→处理需要滚动到底部才能激活Accept按钮的弹窗。目前脚本能弹出最后一个窗口，但无法激活Accept按钮完成下载。

修正后的完整脚本 #

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import os
import time

def download_latest_file():
    try:
        print("Initializing Chrome WebDriver...")
        options = webdriver.ChromeOptions()
        # 设置下载目录，替换为你的实际路径
        prefs = {'download.default_directory': '/Users/m_keiffer/Downloads'}
        options.add_experimental_option('prefs', prefs)
        driver = webdriver.Chrome(options=options)

        print("Opening the webpage...")
        driver.get("https://sam.gov/data-services/Exclusions/Public%20V2?privacy=Public")

        wait = WebDriverWait(driver, 30)

        # 处理初始OK弹窗
        try:
            print("Handling initial OK pop-up...")
            # 匹配包含"OK"文本的按钮
            ok_button = wait.until(EC.element_to_be_clickable((By.XPATH, "//button[contains(text(), 'OK')]")))
            ok_button.click()
            print("OK button clicked.")
        except Exception as e:
            print(f"Error handling initial OK pop-up: {str(e)}")

        # 找到并点击首个Zip下载链接
        try:
            print("Finding download links...")
            # 定位页面中第一个Zip格式的下载链接
            exclusions_link = wait.until(EC.element_to_be_clickable((By.XPATH, "//a[contains(@href, '.zip')][1]")))
            print(f"Clicking on the download link: {exclusions_link.text}")
            exclusions_link.click()
            print("Download link clicked.")
        except Exception as e:
            print(f"Error finding or clicking download link: {str(e)}")
            driver.quit()
            return

        # 处理Accept弹窗
        try:
            print("Handling Accept pop-up...")
            # 等待弹窗加载完成，定位弹窗内的内容滚动区域
            modal_content = wait.until(EC.presence_of_element_located((By.XPATH, "//sa-security-modal//div[@class='modal-body']")))
            
            # 滚动到内容区域底部，触发Accept按钮激活逻辑
            driver.execute_script("arguments[0].scrollTop = arguments[0].scrollHeight", modal_content)
            # 等待按钮状态更新，替换sleep为显式等待更可靠
            accept_button = wait.until(EC.element_to_be_clickable((By.XPATH, "//button[contains(text(), 'Accept')]")))
            
            accept_button.click()
            print("Accept button clicked.")
        except Exception as e:
            print(f"Error handling Accept pop-up: {str(e)}")
            driver.quit()
            return

        # 等待下载完成（可根据文件大小调整时间，或通过文件状态判断）
        time.sleep(15)

        download_path = "/Users/m_keiffer/Downloads"
        files_after = os.listdir(download_path)
        print(f"Files in Downloads: {files_after}")
        new_files = [f for f in files_after if f.endswith('.zip') or f.endswith('.csv')]
        if new_files:
            # 按文件修改时间排序获取最新文件
            latest_file = max(new_files, key=lambda x: os.path.getmtime(os.path.join(download_path, x)))
            print(f"Latest downloaded file: {latest_file}")
        else:
            print("No new files found in the Downloads folder.")

        driver.quit()
    except Exception as e:
        print(f"Failed to initialize the WebDriver or other error: {str(e)}")

# 执行函数
download_latest_file()

关键修改点说明 #

1. 补全并修正XPath定位：原脚本中XPath被截断，替换为精准匹配元素的路径，确保能正确找到OK按钮、下载链接和Accept按钮。
2. 滚动正确的元素：针对弹窗内的modal-body区域滚动，而非整个弹窗容器，确保触发页面的滚动检测逻辑来激活Accept按钮。
3. 替换sleep为显式等待：使用WebDriverWait等待Accept按钮可点击，比固定sleep更可靠，避免因加载延迟导致的失败。
4. 完善最新文件判断逻辑：原脚本中max函数的key参数不完整，补充为按文件修改时间排序，精准获取最新下载的文件。

内容的提问来源于stack exchange，提问作者Michael Keiffer