Typora导出的PDF目录标题自动加编号

Typora导出的PDF目录标题自动加编号

在Typora主题文件夹增加如下文件后，标题便自动加上了编号：

https://gitcode.net/as604049322/blog_data/-/blob/master/base.user.css

例如：

但是导出的PDF中，目录却没有编号：

这是我使用Python处理该文件，使其具有编号，完整代码如下：

1# 博客地址：https://blog.csdn.net/as604049322
2__author__ = '小小明-代码实体'
3__date__ = '2023/8/31'
4
5from PyPDF2 import PdfReader, PdfWriter
6
7
8def get_pdf_Bookmark(filename):
9    "作者CSDN：https://blog.csdn.net/as604049322"
10    if isinstance(filename, str):
11        pdf_reader = PdfReader(filename)
12    else:
13        pdf_reader = filename
14    pagecount = len(pdf_reader.pages)
15    # 用保存每个标题id所对应的页码
16    idnum2pagenum = {}
17    for i in range(pagecount):
18        page = pdf_reader.pages[i]
19        idnum2pagenum[page.indirect_ref.idnum] = i
20    # 保存每个标题对应的标签数据，包括层级，标题和页码索引（页码-1）
21    bookmark = []
22
23    def get_pdf_Bookmark_inter(outlines, tab=0):
24        for outline in outlines:
25            if isinstance(outline, list):
26                get_pdf_Bookmark_inter(outline, tab + 1)
27            else:
28                bookmark.append(
29                    (tab, outline['/Title'], idnum2pagenum[outline.page.idnum]))
30
31    get_pdf_Bookmark_inter(pdf_reader.outline)
32    return bookmark
33
34
35def pdf_write_bookmark(bookmark, pdf_file, compress=True):
36    pdf_reader = PdfReader(pdf_file)
37    num_pages = len(pdf_reader.pages)
38    pdf_writer = PdfWriter()
39    for page in pdf_reader.pages:
40        if compress:
41            page.compress_content_streams()
42        pdf_writer.add_page(page)
43    # pdf_reader.
44    last_cache = [None] * (max(bookmark, key=lambda x: x[0])[0] + 1)
45    for tab, title, pagenum in bookmark:
46        if pagenum >= num_pages:
47            continue
48        parent = last_cache[tab - 1] if tab > 0 else None
49        indirect_id = pdf_writer.add_outline_item(title, pagenum, parent=parent)
50        last_cache[tab] = indirect_id
51    pdf_writer.page_mode = "/UseOutlines"
52    with open(pdf_file, "wb") as out:
53        pdf_writer.write(out)
54    print("已成功将书签写入到", pdf_file)
55
56
57if __name__ == '__main__':
58    file = r"C:\Users\sj\Desktop\集团管理层培训.pdf"
59    bookmark = get_pdf_Bookmark(file)
60    num_cache = [0] * 7
61    last_tab = 0
62    new_bookmark = []
63    for tab, title, pagenum in bookmark:
64        if tab > last_tab:
65            num_cache[tab] = 1
66        else:
67            num_cache[tab] += 1
68        new_title = title
69        if not title[0].isdigit():
70            new_title = ".".join(map(str, num_cache[:tab + 1])) + " " + title
71        # print(tab, new_title, pagenum)
72        new_bookmark.append((tab, new_title, pagenum))
73        last_tab = tab
74    pdf_write_bookmark(new_bookmark, file)

处理后的PDF目录就有编号了：

小伙伴们，快快用实践一下吧！如果在学习过程中，有遇到任何问题，欢迎加我好友，我拉你进Python学习交流群共同探讨学习。