Python批量实现PDF转换为图片(JPG/PNG)

pip install PyMuPDF 
pip install pdf2image 
pip install pypiwin32

for i in os.listdir(path):
    file_name,file_suffix = i.split(".") 
    if file_suffix == "doc":
        word = Dispatch('Word.Application')
        doc = word.Documents.Open(path+f"{i}")
        # 将 Word 文档转换为 docx 格式文件
        doc.SaveAs(path+f"{file_name}.docx",FileFormat=12)
        print(i,"转换完成")
        doc.Close()
        word.Quit()
        sleep(3)        

# 将 Word 文档转换为 docx 格式文件
        doc.SaveAs(path+f"{file_name}.docx",FileFormat=17)

for filename in os.listdir(path):
    if filename.endswith(".pdf"):
        # 获取当前 PDF 文件的总页数
        doc = fitz.open(path + filename)
        total_pages = doc.page_count
        doc.close()
        
        print(f"正在转换 {filename}，共 {total_pages} 页...")
        for i, page in enumerate(convert_from_path(path + filename, grayscale=False), start=1):
            # 构造文件名
            output_filename = os.path.splitext(filename)[0] + "_" + str(i) + ".png"
            # 保存图片
            page.save(path_images + output_filename, "png")
            # 输出转换进度
            print(f"已完成第 {i}/{total_pages} 页的转换")

# -*- coding: utf-8 -*-
"""
Created on Wed May 31 17:10:27 2023

@author: ypzhao
"""

import os
import fitz
from pdf2image import convert_from_path
from time import sleep
from win32com.client import Dispatch

# 定义PDF文件路径和输出区间路径
# 待转换pdf文件路径
path = "C:/Users/ypzhao/Desktop/pdf/"
# doc/docx转换后的路径
path_convert = "C:/Users/ypzhao/Desktop/pdf/"
# 转换后的图片路径
path_images = "C:/Users/ypzhao/Desktop/images/"
print("-----doc开始转换为docx-----")

for i in os.listdir(path):
    file_name,file_suffix = i.split(".") 
    if file_suffix == "doc":
        word = Dispatch('Word.Application')
        doc = word.Documents.Open(path+f"{i}")
        doc.SaveAs(path+f"{file_name}.docx",FileFormat=12)
        print(i,"转换完成")
        doc.Close()
        word.Quit()
        sleep(3)

print("-----开始转换为pdf-----")
for i in os.listdir(path):
    file_name,file_suffix = i.split(".") 
    if file_suffix == "docx":
        word = Dispatch('Word.Application')
        doc = word.Documents.Open(path+f"{i}")
        doc.SaveAs(path_convert+f"{file_name}.pdf",FileFormat=17)
        print(i,"...转换完成")
        doc.Close()
        word.Quit()
        sleep(3)
    else:
        pass


# 循环遍历PDF文件，并转换为图片
for filename in os.listdir(path):
    if filename.endswith(".pdf"):
        # 获取当前 PDF 文件的总页数
        doc = fitz.open(path + filename)
        total_pages = doc.page_count
        doc.close()
        
        print(f"正在转换 {filename}，共 {total_pages} 页...")
        #按照原图输出pdf文件为word
        #若想黑白输出pdf为图片格式，修改grayscale=False为grayscale=True
        for i, page in enumerate(convert_from_path(path + filename, grayscale=False), start=1):
            # 构造文件名
            output_filename = os.path.splitext(filename)[0] + "_" + str(i) + ".png"
            # 保存图片
            page.save(path_images + output_filename, "png")
            # 输出转换进度
            print(f"已完成第 {i}/{total_pages} 页的转换")

print("-----已完成所有转换-----")