PyMuPDF 1.24.4 中文文档（四）（5）

import pymupdf
import json
my_json =  """
[
 {
 "name" :           "Five-storied Pagoda",
 "temple" :         "Rurikō-ji",
 "founded" :        "middle Muromachi period, 1442",
 "region" :         "Yamaguchi, Yamaguchi",
 "position" :       "34.190181,131.472917"
 },
 {
 "name" :           "Founder's Hall",
 "temple" :         "Eihō-ji",
 "founded" :        "early Muromachi period",
 "region" :         "Tajimi, Gifu",
 "position" :       "35.346144,137.129189"
 },
 {
 "name" :           "Fudōdō",
 "temple" :         "Kongōbu-ji",
 "founded" :        "early Kamakura period",
 "region" :         "Kōya, Wakayama",
 "position" :       "34.213103,135.580397"
 },
 {
 "name" :           "Goeidō",
 "temple" :         "Nishi Honganji",
 "founded" :        "Edo period, 1636",
 "region" :         "Kyoto",
 "position" :       "34.991394,135.751689"
 },
 {
 "name" :           "Golden Hall",
 "temple" :         "Murō-ji",
 "founded" :        "early Heian period",
 "region" :         "Uda, Nara",
 "position" :       "34.536586819357986,136.0395548452301"
 },
 {
 "name" :           "Golden Hall",
 "temple" :         "Fudō-in",
 "founded" :        "late Muromachi period, 1540",
 "region" :         "Hiroshima",
 "position" :       "34.427014,132.471117"
 },
 {
 "name" :           "Golden Hall",
 "temple" :         "Ninna-ji",
 "founded" :        "Momoyama period, 1613",
 "region" :         "Kyoto",
 "position" :       "35.031078,135.713811"
 },
 {
 "name" :           "Golden Hall",
 "temple" :         "Mii-dera",
 "founded" :        "Momoyama period, 1599",
 "region" :         "Ōtsu, Shiga",
 "position" :       "35.013403,135.852861"
 },
 {
 "name" :           "Golden Hall",
 "temple" :         "Tōshōdai-ji",
 "founded" :        "Nara period, 8th century",
 "region" :         "Nara, Nara",
 "position" :       "34.675619,135.784842"
 },
 {
 "name" :           "Golden Hall",
 "temple" :         "Tō-ji",
 "founded" :        "Momoyama period, 1603",
 "region" :         "Kyoto",
 "position" :       "34.980367,135.747686"
 },
 {
 "name" :           "Golden Hall",
 "temple" :         "Tōdai-ji",
 "founded" :        "middle Edo period, 1705",
 "region" :         "Nara, Nara",
 "position" :       "34.688992,135.839822"
 },
 {
 "name" :           "Golden Hall",
 "temple" :         "Hōryū-ji",
 "founded" :        "Asuka period, by 693",
 "region" :         "Ikaruga, Nara",
 "position" :       "34.614317,135.734458"
 },
 {
 "name" :           "Golden Hall",
 "temple" :         "Daigo-ji",
 "founded" :        "late Heian period",
 "region" :         "Kyoto",
 "position" :       "34.951481,135.821747"
 },
 {
 "name" :           "Keigū-in Main Hall",
 "temple" :         "Kōryū-ji",
 "founded" :        "early Kamakura period, before 1251",
 "region" :         "Kyoto",
 "position" :       "35.015028,135.705425"
 },
 {
 "name" :           "Konpon-chūdō",
 "temple" :         "Enryaku-ji",
 "founded" :        "early Edo period, 1640",
 "region" :         "Ōtsu, Shiga",
 "position" :       "35.070456,135.840942"
 },
 {
 "name" :           "Korō",
 "temple" :         "Tōshōdai-ji",
 "founded" :        "early Kamakura period, 1240",
 "region" :         "Nara, Nara",
 "position" :       "34.675847,135.785069"
 },
 {
 "name" :           "Kōfūzō",
 "temple" :         "Hōryū-ji",
 "founded" :        "early Heian period",
 "region" :         "Ikaruga, Nara",
 "position" :       "34.614439,135.735428"
 },
 {
 "name" :           "Large Lecture Hall",
 "temple" :         "Hōryū-ji",
 "founded" :        "middle Heian period, 990",
 "region" :         "Ikaruga, Nara",
 "position" :       "34.614783,135.734175"
 },
 {
 "name" :           "Lecture Hall",
 "temple" :         "Zuiryū-ji",
 "founded" :        "early Edo period, 1655",
 "region" :         "Takaoka, Toyama",
 "position" :       "36.735689,137.010019"
 },
 {
 "name" :           "Lecture Hall",
 "temple" :         "Tōshōdai-ji",
 "founded" :        "Nara period, 763",
 "region" :         "Nara, Nara",
 "position" :       "34.675933,135.784842"
 },
 {
 "name" :           "Lotus Flower Gate",
 "temple" :         "Tō-ji",
 "founded" :        "early Kamakura period",
 "region" :         "Kyoto",
 "position" :       "34.980678,135.746314"
 },
 {
 "name" :           "Main Hall",
 "temple" :         "Akishinodera",
 "founded" :        "early Kamakura period",
 "region" :         "Nara, Nara",
 "position" :       "34.703769,135.776189"
 }
]
"""
# the result is a Python dictionary:
my_dict = json.loads(my_json)
MEDIABOX = pymupdf.paper_rect("letter")  # output page format: Letter
WHERE = MEDIABOX + (36, 36, -36, -36)
writer = pymupdf.DocumentWriter("json-example.pdf")  # create the writer
story = pymupdf.Story()
body = story.body
for i, entry in enumerate(my_dict):
    for attribute, value in entry.items():
        para = body.add_paragraph()
        if attribute == "position":
            para.set_fontsize(10)
            para.add_link(f"www.google.com/maps/@{value},14z")
        else:
            para.add_span()
            para.set_color("#990000")
            para.set_fontsize(14)
            para.set_bold()
            para.add_text(f"{attribute} ")
            para.add_span()
            para.set_fontsize(18)
            para.add_text(f"{value}")
    body.add_horizontal_line()
# This while condition will check a value from the Story `place` method
# for whether all content for the story has been written (0), otherwise
# more content is waiting to be written (1)
more = 1
while more:
    device = writer.begin_page(MEDIABOX)  # make new page
    more, _ = story.place(WHERE)
    story.draw(device)
    writer.end_page()  # finish page
writer.close()  # close output file
del story 

"""
Demo script for PyMuPDF's `Story.write()` method.
This is a way of laying out a story into a PDF document, that avoids the need
to write a loop that calls `story.place()` and `story.draw()`.
Instead just a single function call is required, albeit with a `rectfn()`
callback that returns the rectangles into which the story is placed.
"""
import html
import pymupdf
# Create html containing multiple copies of our own source code.
#
with open(__file__) as f:
    text = f.read()
text = html.escape(text)
html = f'''
<!DOCTYPE html>
<body>
<h1>Contents of {__file__}</h1>
<h2>Normal</h2>
<pre>
{text}
</pre>
<h2>Strong</h2>
<strong>
<pre>
{text}
</pre>
</strong>
<h2>Em</h2>
<em>
<pre>
{text}
</pre>
</em>
</body>
'''
def rectfn(rect_num, filled):
  '''
 We return four rectangles per page in this order:
 1 3
 2 4
 '''
    page_w = 800
    page_h = 600
    margin = 50
    rect_w = (page_w - 3*margin) / 2
    rect_h = (page_h - 3*margin) / 2
    if rect_num % 4 == 0:
        # New page.
        mediabox = pymupdf.Rect(0, 0, page_w, page_h)
    else:
        mediabox = None
    # Return one of four rects in turn.
    rect_x = margin + (rect_w+margin) * ((rect_num // 2) % 2)
    rect_y = margin + (rect_h+margin) * (rect_num % 2)
    rect = pymupdf.Rect(rect_x, rect_y, rect_x + rect_w, rect_y + rect_h)
    #print(f'rectfn(): rect_num={rect_num} filled={filled}. Returning: rect={rect}')
    return mediabox, rect, None
story = pymupdf.Story(html, em=8)
out_path = __file__.replace('.py', '.pdf')
writer = pymupdf.DocumentWriter(out_path)
story.write(writer, rectfn)
writer.close() 

"""
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 += f"        <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 += f"        </ul>\n"
    ret += '</ul>\n'
    # Main content.
    ret += textwrap.dedent(f'''
 <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() 

"""
Demo script for PyMuPDF's `pymupdf.Story.write_stabilized_with_links()`.
`pymupdf.Story.write_stabilized_links()` is similar to
`pymupdf.Story.write_stabilized()` except that it creates a PDF `pymupdf.Document`
that contains PDF links generated from all internal links in the original html.
"""
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 += f"        <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 += f"        </ul>\n"
    ret += '</ul>\n'
    # Main content.
    ret += textwrap.dedent(f'''
 <h1>First section</h1>
 <p>Contents of first section.
 <ul>
 <li>External <a href="https://artifex.com/">link to https://artifex.com/</a>.
 <li><a href="#idtest">Link to IDTEST</a>.
 <li><a href="#nametest">Link to NAMETEST</a>.
 </ul>
 <h1>Second section</h1>
 <p>Contents of second section.
 <h2>Second section first subsection</h2>
 <p>Contents of second section first subsection.
 <p id="idtest">IDTEST
 <h1>Third section</h1>
 <p>Contents of third section.
 <p><a name="nametest">NAMETEST</a>.
 </body>
 ''')
    ret = ret.strip()
    with open(__file__.replace('.py', '.html'), 'w') as f:
        f.write(ret)
    return ret;
out_path = __file__.replace('.py', '.pdf')
document = pymupdf.Story.write_stabilized_with_links(contentfn, rectfn)
document.save(out_path) 

"""
Demo script for PyMuPDF's `Story.write()` method.
This is a way of laying out a story into a PDF document, that avoids the need
to write a loop that calls `story.place()` and `story.draw()`.
Instead just a single function call is required, albeit with a `rectfn()`
callback that returns the rectangles into which the story is placed.
"""
import html
import pymupdf
# Create html containing multiple copies of our own source code.
#
with open(__file__) as f:
    text = f.read()
text = html.escape(text)
html = f'''
<!DOCTYPE html>
<body>
<h1>Contents of {__file__}</h1>
<h2>Normal</h2>
<pre>
{text}
</pre>
<h2>Strong</h2>
<strong>
<pre>
{text}
</pre>
</strong>
<h2>Em</h2>
<em>
<pre>
{text}
</pre>
</em>
</body>
'''
def rectfn(rect_num, filled):
  '''
 We return four rectangles per page in this order:
 1 3
 2 4
 '''
    page_w = 800
    page_h = 600
    margin = 50
    rect_w = (page_w - 3*margin) / 2
    rect_h = (page_h - 3*margin) / 2
    if rect_num % 4 == 0:
        # New page.
        mediabox = pymupdf.Rect(0, 0, page_w, page_h)
    else:
        mediabox = None
    # Return one of four rects in turn.
    rect_x = margin + (rect_w+margin) * ((rect_num // 2) % 2)
    rect_y = margin + (rect_h+margin) * (rect_num % 2)
    rect = pymupdf.Rect(rect_x, rect_y, rect_x + rect_w, rect_y + rect_h)
    #print(f'rectfn(): rect_num={rect_num} filled={filled}. Returning: rect={rect}')
    return mediabox, rect, None
story = pymupdf.Story(html, em=8)
out_path = __file__.replace('.py', '.pdf')
writer = pymupdf.DocumentWriter(out_path)
story.write(writer, rectfn)
writer.close() 

"""
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 += f"        <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 += f"        </ul>\n"
    ret += '</ul>\n'
    # Main content.
    ret += textwrap.dedent(f'''
 <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() 

"""
Demo script for PyMuPDF's `pymupdf.Story.write_stabilized_with_links()`.
`pymupdf.Story.write_stabilized_links()` is similar to
`pymupdf.Story.write_stabilized()` except that it creates a PDF `pymupdf.Document`
that contains PDF links generated from all internal links in the original html.
"""
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 += f"        <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 += f"        </ul>\n"
    ret += '</ul>\n'
    # Main content.
    ret += textwrap.dedent(f'''
 <h1>First section</h1>
 <p>Contents of first section.
 <ul>
 <li>External <a href="https://artifex.com/">link to https://artifex.com/</a>.
 <li><a href="#idtest">Link to IDTEST</a>.
 <li><a href="#nametest">Link to NAMETEST</a>.
 </ul>
 <h1>Second section</h1>
 <p>Contents of second section.
 <h2>Second section first subsection</h2>
 <p>Contents of second section first subsection.
 <p id="idtest">IDTEST
 <h1>Third section</h1>
 <p>Contents of third section.
 <p><a name="nametest">NAMETEST</a>.
 </body>
 ''')
    ret = ret.strip()
    with open(__file__.replace('.py', '.html'), 'w') as f:
        f.write(ret)
    return ret;
out_path = __file__.replace('.py', '.pdf')
document = pymupdf.Story.write_stabilized_with_links(contentfn, rectfn)
document.save(out_path)