python 根据PDF 目录生成PDF书签

Python 代码 PDF 生成书签代码 ，使用PyPDF4 库。

txt_path 目录文件

pdf_path pdf 文件 换成自己的地址

txt 文件 格式

第 1 章-LAMP 网站构建-1
1.1-Web 概述-1
1.1.1-Web 应用的优势-2
1.1.2-Web 2.0-时代的互联网-3

章节-标题-目录中的页码

import PyPDF4

txt_path = '/Users/lcd/Desktop/lcd/python/pdfbookmark/pdf/test.txt'
pdf_path = '/Users/lcd/Desktop/lcd/python/pdfbookmark/pdf/php2.pdf'
ini_page = 26 # pdf 正式开始的页码


# 目录 可以复制pdf文档中的目录结构到txt. 调整成文档中的结构。
def get_mu_lu(page):
    sy = ''
    with open(txt_path, 'r') as f:
        txt_lines = f.readlines()
        for line in txt_lines:
            line_split = line.split('-')
            line_title = line_split[1]
            line_num = line_split[-1].replace('\n', '')
            line_level = line_split[0]
            line_level_split = line_level.split('.')
            if str(page) == str(line_num):
                if len(line_level_split) > 1:
                    sy = line_level+line_title
                    if len(line_level_split) > 2:
                        sy = line_level+line_title
                        break
                    else:
                        break

    return sy


def read_pdf():
    # 打开pdf 文件
    pdf_file = open(pdf_path, 'rb')
    pdf_reader = PyPDF4.PdfFileReader(pdf_file)
    pdf_page_num = pdf_reader.getNumPages()
    # 创建 pdfwriter 对象
    pdf_writer = PyPDF4.PdfFileWriter()
    for page_num in range(pdf_page_num):
        page = pdf_reader.getPage(page_num)
        pdf_writer.addPage(page)
        if page_num > ini_page:
            mulu = get_mu_lu(page_num - ini_page)
            if mulu:
                pdf_writer.addBookmark(mulu, page_num)
                print(mulu)
    output_file = open('example_with_bookmarks.pdf', 'wb')
    pdf_writer.write(output_file)

    pdf_file.close()
    output_file.close()


read_pdf()

希望可以帮到您