用python实现批量计算pdf页数, 批量重命名和批量pdf转图片

1. 批量计算文件夹下面所有pdf的页数，并生成一个excel文件，把pdf文件名字和页数都写入到pdf文件。
   

代码：

import os
import openpyxl
from PyPDF2 import PdfFileReader


def extract_number(filename):
    """从文件名中提取数字"""
    start = None
    end = None
    for i, char in enumerate(filename):
        if char.isdigit() and start is None:
            start = i
        elif not char.isdigit() and start is not None and end is None:
            end = i
            break
    if start is not None:
        if end is None:
            return int(filename[start:])
        else:
            return int(filename[start:end])
    else:
        return None


folder_path = r'/Users/Materials/资料/office相关/用python实现批量计算pdf页数, 批量重命名和批量pdf转图片/python图片转pdf'
excel_path = folder_path + '/pdf_info.xlsx'
pdf_paths = [os.path.join(folder_path, file) for file in os.listdir(folder_path) if file.endswith('.pdf')]
# pdf_paths = sorted(pdf_paths, key=lambda x: extract_number(os.path.basename(x)))  # 按文件名中数字的大小排序
page_counts = []
pdf_names = []
for pdf_path in pdf_paths:
    pdf_name = os.path.splitext(os.path.basename(pdf_path))[0]  # 获取 PDF 文件名，并去掉文件格式后缀
    pdf_names.append(pdf_name)  # 将 PDF 文件名添加到列表中
    with open(pdf_path, 'rb') as f:
        pdf = PdfFileReader(f)
        page_count = pdf.getNumPages()
        page_counts.append(page_count)
workbook = openpyxl.Workbook()
worksheet = workbook.active
worksheet.title = '页面计算'
worksheet['A1'] = 'PDF名字'  # 将列标题改为 'PDF Name'
worksheet['B1'] = '新文件名字'
worksheet['C1'] = '页数'

for i in range(len(pdf_paths)):
    worksheet.cell(row=i + 2, column=1, value=pdf_names[i])  # 将 PDF 文件名添加到表格中
    worksheet.cell(row=i + 2, column=3, value=page_counts[i])
workbook.save(excel_path)

2. 根据excel中新文件名字，进行批量重命名
   

代码：

import os
import pandas as pd


# 读取Excel文件
df = pd.read_excel('pdf_info.xlsx')
pdf_dict = {}
# 遍历每一行
for i, row in df.iterrows():
    # 获取PDF文件名和编号
    pdf_name = row['PDF名字']
    num = row['新文件名字']
    # 添加到字典中
    pdf_dict[str(pdf_name)+'.pdf'] = str(num)
# 遍历当前文件夹下所有pdf文件，重命名文件
for file in os.listdir('.'):
    if file.endswith('.pdf') and file in pdf_dict:
        # 获取文件对应的编号
        num = pdf_dict[file]
        # 重命名文件
        os.rename(os.path.join('.', file), os.path.join('.', str(num) + '.pdf'))

3. 批量把pdf文件转化成图片，并创建对应的文件夹，图片的命名规则是8位数，前面有0填充。
   
   
   

代码：

# 批量把pdf文件转化成jpg
# Python 3.7.13
# PyPDF2 2.12.1

import os
from pdf2image import convert_from_path
from PyPDF2 import PdfFileReader
from PIL import Image

# 设置图片最大的像素
Image.MAX_IMAGE_PIXELS = 2300000000

# 必须采用绝对路径，不然会报错
folder_path = r'/Users/Materials/资料/office相关/用python实现批量计算pdf页数, 批量重命名和批量pdf转图片/python图片转pdf'

for filename in os.listdir(folder_path):
    if filename.endswith(".pdf"):
        pdf_path = os.path.join(folder_path, filename)

        input_pdf = PdfFileReader(open(pdf_path, "rb"))

        # 获得文件的最大页数
        max_pages = input_pdf.numPages

        # 对每一个pdf文件创建一个文件夹
        new_folder_path = os.path.join(folder_path, f"{filename[:-4]}")
        os.mkdir(new_folder_path)
        current_page = 0
        # 每10页导出的一次，防止报内存限制
        for page in range(1, max_pages + 1, 10):
            images = convert_from_path(pdf_path, dpi=200, first_page=page, last_page=min(page + 10 - 1, max_pages))
            # save each image in the new directory
            for i, image in enumerate(images):
                # 对图片进行命名，编号的顺序8位数，其余用0填充，e.g. 00000001。
                current_page = str(i + page).zfill(8)
                image.save(os.path.join(new_folder_path, str(current_page) + ".jpg"), "JPEG")
        print("file_name:" + filename + ", max_pages:" + str(max_pages) + ", all_pages:" + current_page)