PDF合并，PDF拆分，PDF转换

PDF合并，PDF拆分，PDF转换

由于工作需要处理PDF文件，在网上找了一些工具、但还是不太方便、有的甚至需要充钱才能处理。于是多方整理终于可以自己解决了。
python首先导入需要的库如下：

import os
import datetime
import PyPDF2
from PyPDF2 import PdfMerger
from pdf2docx import Converter
import fitz
from PIL import Image

1、PDF合并

def pdf_merger():
    pdf_path = 'D:\\工程材料\\'
    outfile = 'pdf合并文件_'
    pdf_merger_ = PdfMerger()
    for root, dirs, files in os.walk(pdf_path):
        for f in files:
            f_ = os.path.join(root, f)
            print(f_)
            pdf_merger_.append(f_)
    pdf_name = 'D:\\advance\\' + outfile + '.pdf'
    pdf_merger_.write(pdf_name)

2、PDF拆分

def pdf_split():
    pdf_name1 = 'D:\\查勘.pdf'
    outfile = 'pdf拆分文件_'
    pdf_reader = PyPDF2.PdfReader(pdf_name1)
    pdf_nums = len(pdf_reader.pages)
    for num in range(0, pdf_nums):
        print(num)
        pdf_writer = PyPDF2.PdfWriter()
        page_obj = pdf_reader.pages[num]
        pdf_writer.add_page(page_obj)
        pdf_name2 = 'D:\\advance\\' + outfile + str(num) + '.pdf'
        pdf_writer.write(pdf_name2)

3、PDF转换成word文件

def pdf_to_docx():
    pdf_name = 'D:\\设计费.pdf'
    outfile = 'pdf转换为word文件_'
    cv = Converter(pdf_name)
    docx_name = 'D:\\advance\\' + outfile  + '.docx'
    # cv.convert(docx_name, start=0, end=None)
    cv.convert(docx_name, start=0, end=2)
    # cv.convert(docx_name, pages=[0, 2, 5])
    cv.close()

4、PDF转换为图片

def pdf_to_jpe():
    pdf_name1 = 'D:\\查勘.pdf'
    doc = fitz.open(pdf_name1)
    outfile = 'pdf转换为jpe_'
    pdf_reader = PyPDF2.PdfReader(pdf_name1)
    pdf_nums = len(pdf_reader.pages)
    for num in range(0, pdf_nums):
        print(num)
        page = doc.load_page(num)
        pix = page.get_pixmap(matrix=fitz.Matrix(2, 2), alpha=False)  
        # Matrix(2, 2)清晰度可以接受，越大越清晰
        pdf_name2 = 'D:\\advance\\' + outfile + str(num) + '.png'
        pix.save(pdf_name2)

5、多个图片单独转换为多个PDF

def jpe_to_pdf_single():
    jpe_path = 'D:\\图片\\'
    outfile = 'jpe转换为pdf文件_'
    for root, dirs, files in os.walk(jpe_path):
        for f in files:
            f_ = os.path.join(root, f)
            print(f_)
            pdf_name = 'D:\\advance\\' + outfile + str(f) + '.pdf'
            img_file = Image.open(f_)
            img_file.save(pdf_name, 'pdf', save_all=True)

6、多个图片合并转换为一个PDF（）

def jpe_to_pdf_all():
    jpe_path = 'D:\\图片\\'
    outfile = 'jpe转换为pdf文件'
    pdf_name = 'D:\\advance\\' + outfile + '.pdf'
    image_list = []
    file_list = []
    for root, dirs, files in os.walk(jpe_path):
        for f in files:
            f_ = os.path.join(root, f)
            print(f_)
            file_list.append(f_)

    for i in file_list:
        if file_list.index(i) == 0:
            pdf_first = Image.open(i)  
            # 传入的第一张图片,封面
        else:
            img_file = Image.open(i)
            image_list.append(img_file)
            pdf_first.save(pdf_name, 'pdf', save_all=True, append_images=image_list)