pdf-to-image-preview

PDF to Image Skill

Task Objective

• This Skill is used to: convert each page of a PDF file into an independent image file
• Capabilities include: PDF file parsing, image format conversion (PNG/JPG), adjustable resolution output
• Trigger conditions: scenarios where the user needs to convert PDF to images, extract PDF pages, convert PDF content to images, etc.

Prerequisites

• Dependency description: the dependency packages and versions required by the scripts

  pymupdf>=1.23.0
  

Operation Steps

• Standard process:
  1. Prepare the PDF file
     • Confirm the PDF file path (use ./ to indicate the current working directory)
     • For example:./document.pdf

1. Execute the conversion

   • Call the script to convert each page of the PDF file into an image
   • Command example:

     python scripts/convert_pdf_to_images.py \
       --input ./document.pdf \
       --output-dir ./images
     

   • Optional parameters:
     • --image-format: image format, supports png or jpg, default is png
     • --dpi: image resolution (DPI), default is 200
     • --zip: generate a ZIP archive
     • --zip-output: ZIP archive output path (default: images.zip)

2. View the output

   • Image files are saved in the specified output directory
   • File naming format:page_001.png、page_002.png...
   • You can choose whether to generate a ZIP archive

Resource Index

• Required script: see scripts/convert_pdf_to_images.py(Purpose and parameters: PDF to image script)

Notes

• The input PDF file must exist and be readable
• The output directory must have write permission
• PDF page limit: currently supports PDF files within 100 pages; for more than 100 pages, please split before converting
• Converting large PDF files may take a long time, please wait patiently

Troubleshooting

• Script not found error: make sure to execute in the Skill directory, or use the relative path scripts/xxx.py
• Python version issue: make sure to use Python 3.6 or higher
• Missing dependencies: execute pip install pymupdf>=1.23.0 to install dependencies
• Page count exceeded error: the PDF file exceeds 100 pages, please use a PDF tool to split it into multiple smaller files

Usage Examples

Example 1: Basic conversion (PNG format)

python scripts/convert_pdf_to_images.py \
  --input ./report.pdf \
  --output-dir ./images

Example 2: Use JPG format

python scripts/convert_pdf_to_images.py \
  --input ./document.pdf \
  --output-dir ./images \
  --image-format jpg

Example 3: High-resolution output

python scripts/convert_pdf_to_images.py \
  --input ./document.pdf \
  --output-dir ./images \
  --dpi 300

Example 4: Generate a ZIP archive

python scripts/convert_pdf_to_images.py \
  --input ./document.pdf \
  --output-dir ./images \
  --zip \
  --zip-output ./images.zip

Example 5: Full configuration

python scripts/convert_pdf_to_images.py \
  --input ./report.pdf \
  --output-dir ./images \
  --image-format jpg \
  --dpi 200 \
  --zip