PyMuPDF
PyMuPDF copied to clipboard
pymupdf
ValueError: not enough values to unpack (expected 3, got 2) is thrown when call insert_pdf
Description of the bug
Want to split a pdf file into multiple pdf by 5 pages per file. When insert_pdf is called, a ValueError is thrown.
example.pdf
How to reproduce the bug
from io import BytesIO
from pathlib import Path
import fitz
def _clean_up(file_path):
doc = fitz.open(file_path)
tmp = BytesIO()
tmp.write(doc.write(garbage=4, deflate=True))
doc = fitz.Document('pdf', tmp.getvalue())
tmp.close()
return doc
def split_pdf_by_page(file_path, pages_per_split, result_dir, num_splits=None, paging_prefix=""):
# Not split
if not pages_per_split:
return [shutil.copy(file_path, result_dir/f"{paging_prefix}_0.pdf")]
# Clean pdf
source_doc = _clean_up(file_path)
# Calculate the number of pages per split file and the number of split files
page_range = pages_per_split - 1
split_range = range(0, source_doc.page_count, pages_per_split)
num_splits = num_splits or len(split_range)
# Create a list to hold the paths of the split files
split_paths = []
# Loop through each split range and create a new PDF file
for i, start in enumerate(split_range):
output_doc = fitz.open()
# Determine the ending page for this split file
to_page = start + page_range if i < num_splits - 1 else -1
output_doc.insert_pdf(source_doc, from_page=start, to_page=to_page)
# Save the output document to a file and add the path to the list of split files
path = result_dir/f"{paging_prefix}_{i}.pdf"
output_doc.save(path, garbage=2)
split_paths.append(path)
# If this is the last split file, exit the loop
if to_page == -1:
break
return split_paths
if __name__ == "__main__":
file_path = Path("./example.pdf")
pages_per_file = 5
result_dir = Path("./result")
result_dir.mkdir()
split_pdf_by_page(file_path, pages_per_file, result_dir, paging_prefix="src")
PyMuPDF version
1.24.9
Operating system
Linux
Python version
3.8
This error does not happen in method .insert_pdf itself, but occurs when resolving names for deciphering LINK_NAMED hyperlinks.
You can avoid this by excluding link in source pages altogether when copying pages: .insert_pdf(source, links=False).
Will excluding links affect the result PDF's content?
No, pages will look the same, but any hyperlinks will no longer respond when clicking on the respective area.
