mirror of
https://github.com/anthropics/skills
synced 2026-07-05 11:36:53 +00:00
9422aa6c64
docx: Add commenting and track-changes support. Reorganize OOXML tooling into a shared office/ module. pptx: Streamline SKILL.md, add slide-editing and pptxgenjs guides, bundle html2pptx as a tgz. Reorganize OOXML tooling into a shared office/ module. xlsx: Move recalc script into scripts/ and expand it. Add shared office/ module for OOXML pack/unpack/validate. pdf: Improve form-filling workflow with new form-structure extraction script and updated field-info extraction.
34 lines
1008 B
Python
34 lines
1008 B
Python
import os
|
|
import sys
|
|
|
|
from pdf2image import convert_from_path
|
|
|
|
|
|
|
|
|
|
def convert(pdf_path, output_dir, max_dim=1000):
|
|
images = convert_from_path(pdf_path, dpi=200)
|
|
|
|
for i, image in enumerate(images):
|
|
width, height = image.size
|
|
if width > max_dim or height > max_dim:
|
|
scale_factor = min(max_dim / width, max_dim / height)
|
|
new_width = int(width * scale_factor)
|
|
new_height = int(height * scale_factor)
|
|
image = image.resize((new_width, new_height))
|
|
|
|
image_path = os.path.join(output_dir, f"page_{i+1}.png")
|
|
image.save(image_path)
|
|
print(f"Saved page {i+1} as {image_path} (size: {image.size})")
|
|
|
|
print(f"Converted {len(images)} pages to PNG images")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
if len(sys.argv) != 3:
|
|
print("Usage: convert_pdf_to_images.py [input pdf] [output directory]")
|
|
sys.exit(1)
|
|
pdf_path = sys.argv[1]
|
|
output_directory = sys.argv[2]
|
|
convert(pdf_path, output_directory)
|