"""
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('''
Contents
''')
# Create table of contents with links to all 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" - {text}\n"
else:
ret += f"
- {text}\n"
ret += f"
\n"
ret += f" - page={position.page_num}\n"
ret += f"
- depth={position.depth}\n"
ret += f"
- heading={position.heading}\n"
ret += f"
- id={position.id!r}\n"
ret += f"
- href={position.href!r}\n"
ret += f"
- rect={position.rect}\n"
ret += f"
- text={text!r}\n"
ret += f"
- open_close={position.open_close}\n"
ret += f"
\n"
ret += '
\n'
# Main content.
ret += textwrap.dedent(f'''
First section
Contents of first section.
Second section
Contents of second section.
Second section first subsection
Contents of second section first subsection.
IDTEST
Third section
Contents of third section.
NAMETEST.
''')
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)