#!/usr/bin/env python3
import os
import sys
import argparse
import urllib.request

def install_and_import(package):
    import importlib
    try:
        importlib.import_module(package)
    except ImportError:
        import subprocess
        print(f"[{package}] is not installed. Installing dynamically...", file=sys.stderr)
        subprocess.check_call([sys.executable, "-m", "pip", "install", "--quiet", package])
    finally:
        globals()[package] = importlib.import_module(package)

# Ensure pypdf is installed and imported
install_and_import('pypdf')

def download_file(url, dest_path):
    print(f"Downloading PDF from {url}...", file=sys.stderr)
    headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36'}
    req = urllib.request.Request(url, headers=headers)
    with urllib.request.urlopen(req) as response:
        with open(dest_path, 'wb') as out_file:
            out_file.write(response.read())

def extract_text_from_pdf(pdf_path):
    print(f"Parsing text from {pdf_path}...", file=sys.stderr)
    reader = pypdf.PdfReader(pdf_path)
    text_content = []
    
    # Extract metadata if available
    meta = reader.metadata
    if meta:
        text_content.append("---")
        text_content.append(f"title: {meta.title or 'Unknown'}")
        text_content.append(f"author: {meta.author or 'Unknown'}")
        text_content.append(f"subject: {meta.subject or 'Unknown'}")
        text_content.append("---")
        text_content.append("")

    for page_num, page in enumerate(reader.pages):
        page_text = page.extract_text()
        if page_text:
            text_content.append(f"## Page {page_num + 1}")
            text_content.append(page_text)
            text_content.append("")
            
    return "\n".join(text_content)

def main():
    parser = argparse.ArgumentParser(description="Download and parse PDF files to clean text.")
    parser.add_argument("--url", help="URL of the PDF file to download and parse.")
    parser.add_argument("--file", help="Path to local PDF file to parse.")
    parser.add_argument("--output", required=True, help="Output path to save the extracted text (Markdown format).")
    
    args = parser.parse_args()
    
    # Create output directory if it doesn't exist
    out_dir = os.path.dirname(args.output)
    if out_dir and not os.path.exists(out_dir):
        os.makedirs(out_dir, exist_ok=True)
        
    pdf_temp_path = "scratch/temp_download.pdf"
    os.makedirs("scratch", exist_ok=True)
    
    try:
        if args.url:
            download_file(args.url, pdf_temp_path)
            target_pdf = pdf_temp_path
        elif args.file:
            target_pdf = args.file
        else:
            print("Error: You must provide either --url or --file", file=sys.stderr)
            sys.exit(1)
            
        extracted_text = extract_text_from_pdf(target_pdf)
        
        with open(args.output, "w", encoding="utf-8") as f:
            f.write(extracted_text)
            
        print(f"Successfully extracted text to: {args.output}", file=sys.stderr)
        
        # Clean up temp file
        if os.path.exists(pdf_temp_path) and args.url:
            os.remove(pdf_temp_path)
            
    except Exception as e:
        print(f"Error occurred during parsing: {str(e)}", file=sys.stderr)
        sys.exit(1)

if __name__ == "__main__":
    main()