PyMuPDF/docs/samples/story-write-stabilized.py at ffac9697a7b80f209da7f666e7dd72241389c982 · pymupdf/PyMuPDF · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
"""
Demo script for PyMuPDF's `pymupdf.Story.write_stabilized()`.

`pymupdf.Story.write_stabilized()` is similar to `pymupdf.Story.write()`,
except instead of taking a fixed html document, it does iterative layout
of dynamically-generated html content (provided by a callback) to a
`pymupdf.DocumentWriter`.

For example this allows one to add a dynamically-generated table of contents
section while ensuring that page numbers are patched up until stable.
"""

import textwrap

import pymupdf


def rectfn(rect_num, filled):
    '''
    We return one rect per page.
    '''
    rect = pymupdf.Rect(10, 20, 290, 380)
    mediabox = pymupdf.Rect(0, 0, 300, 400)
    #print(f'rectfn(): rect_num={rect_num} filled={filled}')
    return mediabox, rect, None


def contentfn(positions):
    '''
    Returns html content, with a table of contents derived from `positions`.
    '''
    ret = ''
    ret += textwrap.dedent('''
            <!DOCTYPE html>
            <body>
            <h2>Contents</h2>
            <ul>
            ''')

    # Create table of contents with links to all <h1..6> sections in the
    # document.
    for position in positions:
        if position.heading and (position.open_close & 1):
            text = position.text if position.text else ''
            if position.id:
                ret += f"    <li><a href=\"#{position.id}\">{text}</a>\n"
            else:
                ret += f"    <li>{text}\n"
            ret += "        <ul>\n"
            ret += f"        <li>page={position.page_num}\n"
            ret += f"        <li>depth={position.depth}\n"
            ret += f"        <li>heading={position.heading}\n"
            ret += f"        <li>id={position.id!r}\n"
            ret += f"        <li>href={position.href!r}\n"
            ret += f"        <li>rect={position.rect}\n"
            ret += f"        <li>text={text!r}\n"
            ret += f"        <li>open_close={position.open_close}\n"
            ret += "        </ul>\n"

    ret += '</ul>\n'

    # Main content.
    ret += textwrap.dedent('''

            <h1>First section</h1>
            <p>Contents of first section.

            <h1>Second section</h1>
            <p>Contents of second section.
            <h2>Second section first subsection</h2>

            <p>Contents of second section first subsection.

            <h1>Third section</h1>
            <p>Contents of third section.

            </body>
            ''')
    ret = ret.strip()
    with open(__file__.replace('.py', '.html'), 'w') as f:
        f.write(ret)
    return ret;


out_path = __file__.replace('.py', '.pdf')
writer = pymupdf.DocumentWriter(out_path)
pymupdf.Story.write_stabilized(writer, contentfn, rectfn)
writer.close()