Convert PDF documents to structured JSON (using PyMuPDF)

pdf2json_pymupdf.py

#!/usr/bin/env python3
"""
pdf2json - Convert PDF documents to structured JSON
Usage: pdf2json input.pdf [output.json]
"""

import sys
import os
import json
import argparse
import fitz # PyMuPDF

def extract_pdf_to_json(pdf_path, include_images=False):
    """Extract PDF content to structured JSON format."""
    doc = fitz.open(pdf_path)
    result = {
        "metadata": {
            "title": doc.metadata.get("title", ""),
            "author": doc.metadata.get("author", ""),
            "creator": doc.metadata.get("creator", ""),
            "producer": doc.metadata.get("producer", ""),
            "subject": doc.metadata.get("subject", ""),
            "keywords": doc.metadata.get("keywords", ""),
            "pageCount": doc.page_count
        },
        "pages": []
    }

    for page_num, page in enumerate(doc):
        page_data = {
            "page_number": page_num + 1,
            "sections": []
        }
        
        # Extract text blocks
        blocks = page.get_text("dict")["blocks"]
        
        for block in blocks:
            # Process text blocks
            if block["type"] == 0:  # Text block
                block_text = ""
                is_bold = False
                font_size = 0
                
                # Extract text and font information
                for line in block["lines"]:
                    for span in line["spans"]:
                        block_text += span["text"] + " "
                        # Check for bold text (flags & 16)
                        if span.get("flags", 0) & 16:
                            is_bold = True
                        # Track largest font size
                        font_size = max(font_size, span.get("size", 0))
                
                block_text = block_text.strip()
                if not block_text:
                    continue
                
                # Determine text type based on font attributes
                text_type = "paragraph"
                if font_size > 14 or (font_size > 11 and is_bold):
                    text_type = "heading"
                elif font_size < 9:
                    text_type = "footnote"
                
                page_data["sections"].append({
                    "type": text_type,
                    "content": block_text,
                    "bbox": block["bbox"]  # [x0, y0, x1, y1]
                })
                
        # Handle images if requested
        if include_images:
            image_list = page.get_images(full=True)
            if image_list:
                page_data["images"] = []
                for img_index, img_info in enumerate(image_list):
                    xref = img_info[0]
                    base_image = doc.extract_image(xref)
                    if base_image:
                        # Just track image metadata (not binary data)
                        page_data["images"].append({
                            "index": img_index,
                            "format": base_image["ext"],
                            "width": base_image["width"],
                            "height": base_image["height"]
                        })
        
        result["pages"].append(page_data)
    
    doc.close()
    return result

def main():
    parser = argparse.ArgumentParser(description="Convert PDF to structured JSON")
    parser.add_argument("input_pdf", help="Input PDF file path")
    parser.add_argument("output_json", nargs="?", help="Output JSON file path (defaults to input filename with .json extension)")
    parser.add_argument("-p", "--pretty", action="store_true", help="Pretty print JSON output")
    parser.add_argument("-i", "--images", action="store_true", help="Include image metadata")
    args = parser.parse_args()
    
    # Validate input file
    if not os.path.isfile(args.input_pdf):
        print(f"Error: Input file '{args.input_pdf}' does not exist", file=sys.stderr)
        sys.exit(1)
    
    # Set default output filename if not provided
    output_path = args.output_json
    if not output_path:
        base_name = os.path.splitext(args.input_pdf)[0]
        output_path = f"{base_name}.json"
    
    try:
        json_data = extract_pdf_to_json(args.input_pdf, include_images=args.images)
        
        # Write output
        with open(output_path, "w", encoding="utf-8") as f:
            if args.pretty:
                json.dump(json_data, f, indent=2, ensure_ascii=False)
            else:
                json.dump(json_data, f, ensure_ascii=False)
        
        print(f"Converted '{args.input_pdf}' to '{output_path}'")
    
    except Exception as e:
        print(f"Error converting PDF: {e}", file=sys.stderr)
        sys.exit(1)

if __name__ == "__main__":
    main()