Python自动化下载文件后处理的IndexError：深度解析与解决方案

import os
import time
from selenium import webdriver
from selenium.webdriver.common.by import By

# 假设 driver 已经初始化并导航到相关页面
# driver = webdriver.Chrome()

def download_wait():
    """
    等待下载完成，通过检查临时下载文件是否存在来判断。
    """
    seconds = 0
    dl_wait = True
    while dl_wait and seconds < 100:
        time.sleep(1)
        dl_wait = False  # 假设下载已完成
        for fname in os.listdir(r"C:\Users\Testuser\Downloads"):
            # 如果发现 .crdownload 或 .tmp 文件，则表示下载仍在进行
            if fname.endswith('.crdownload') or fname.endswith('.tmp'):
                dl_wait = True
                break # 发现一个临时文件即可，无需检查所有
        seconds += 1
    return seconds

Years = ["2010", "2011"]
for year in Years:
    try:
        # 查找并点击下载链接
        report = driver.find_elements(By.XPATH, f"//span[@class='btn_archived download'][.//a[contains(@href,{year})]]")
        if len(report) != 0:
            report[0].click() # 点击下载
            download_wait() # 等待下载完成

            # 列出下载目录中的文件并进行过滤
            files = os.listdir(r"C:\Users\Testuser\Downloads")
            filtered_files = [file for file in files if file.lower().endswith(('.pdf', '.htm'))]
            print(f"Year: {year}, All files: {files}, Filtered files: {filtered_files}")

            # 尝试访问过滤后的第一个文件，此处可能发生 IndexError
            filename = filtered_files[0]
            # 后续文件处理逻辑...

    except Exception as e:
        print(f"An error occurred for year {year}: {e}")

Year: 2009, All files: ['NYSE_XOM_2009.pdf'], Filtered files: ['NYSE_XOM_2009.pdf']
Year: 2010, All files: ['NYSE_XOM_2010.pdf.crdownload'], Filtered files: []

>>> "foo.pdf".endswith((".pdf", ".htm"))
True
>>> "foo.pdf.crdownload".endswith((".pdf", ".htm"))
False
>>> "foo.pdf.crdownload".endswith((".pdf", ".htm", ".crdownload"))
True
>>> "foo.pdf.crdownload".endswith((".pdf", ".htm", ".pdf.crdownload"))
True

            # 列出下载目录中的文件并进行过滤
            files = os.listdir(r"C:\Users\Testuser\Downloads")
            filtered_files = [file for file in files if file.lower().endswith(('.pdf', '.htm'))]
            print(f"Year: {year}, All files: {files}, Filtered files: {filtered_files}")

            if len(filtered_files) > 0:
                filename = filtered_files[0]
                print(f"Processing file: {filename}")
                # 后续文件处理逻辑...
            else:
                print(f"Warning: No completed .pdf or .htm file found for year {year} after download attempt.")
                # 可以选择跳过、重试下载或记录错误

            # 示例：如果需要将 .crdownload 文件也包含在列表中进行识别或日志记录
            # 注意：通常不建议直接处理 .crdownload 文件的内容
            filtered_files = [file for file in files if file.lower().endswith(('.pdf', '.htm', '.crdownload'))]
            print(f"Year: {year}, All files: {files}, Filtered files: {filtered_files}")

            if len(filtered_files) > 0:
                filename = filtered_files[0]
                if filename.lower().endswith('.crdownload'):
                    print(f"Identified an incomplete download: {filename}. Skipping content processing.")
                    # 可以将其移动到错误目录或记录下来
                else:
                    print(f"Processing completed file: {filename}")
                    # 后续文件处理逻辑...
            else:
                print(f"Warning: No relevant file found for year {year} after download attempt.")