#coding:utf-8
import os  
import pandas as pd  
from PyPDF2 import PdfReader  
  
# 指定要讀取的文件夾路徑  
folder_path = r'E:/臨時(shí)文件/'
  
# 獲取文件夾下的所有PDF文件  
pdf_files = [f for f in os.listdir(folder_path) if f.endswith('.pdf')]  
  
# 存儲(chǔ)PDF文件的頁碼信息  
pdf_page_info = []  
  
# 遍歷每個(gè)PDF文件  
# for file_name in pdf_files:  
#使用enumerate()函數(shù)來同時(shí)獲取循環(huán)的次數(shù)和元素值，index來寫編號(hào)
for index,file_name in enumerate(pdf_files): 
    file_path = os.path.join(folder_path, file_name)  
    with open(file_path, 'rb') as file:  
        # 創(chuàng)建PDF閱讀器對(duì)象  
        reader = PdfReader(file)  
        # 獲取PDF文件的頁數(shù)  
        # num_pages = reader.getNumPages()  
        num_pages = len(reader.pages)  
        # 將文件名稱、頁碼數(shù)量和備注添加到列表中  
        # pdf_page_info.append((os.path.splitext(file_name)[0], file_name, num_pages, ''))  
        pdf_page_info.append((index+1, file_name, num_pages, ''))  
  
# 創(chuàng)建Excel文件并輸出數(shù)據(jù)  
df = pd.DataFrame(pdf_page_info, columns=['編號(hào)', '文件名稱', '頁碼數(shù)量', '備注'])  
df.to_excel('output.xlsx', index=False)