import_from_pdf.py

"""
Extract images and text from a PDF into assets/imported/<pdf_basename>/
Requires: pip install PyPDF2 pillow pdfminer.six
Usage: python import_from_pdf.py /path/to/file.pdf
"""
import sys
from pathlib import Path
import os

try:
    from PyPDF2 import PdfReader
except Exception:
    PdfReader = None


def extract_text(pdf_path, out_dir):
    if PdfReader is None:
        raise RuntimeError('PyPDF2 not installed. pip install PyPDF2')
    reader = PdfReader(str(pdf_path))
    texts = []
    for i,page in enumerate(reader.pages):
        try:
            txt = page.extract_text() or ''
            texts.append(f"--- PAGE {i+1} ---\n"+txt)
        except Exception as e:
            texts.append(f"--- PAGE {i+1} ---\nERROR: {e}")
    out = out_dir / 'extracted_text.txt'
    out.write_text('\n\n'.join(texts), encoding='utf-8')
    print('Wrote', out)


def main():
    if len(sys.argv)<2:
        print('Usage: python import_from_pdf.py /path/to/file.pdf')
        return
    pdf = Path(sys.argv[1])
    if not pdf.exists():
        print('PDF not found:', pdf)
        return
    base = pdf.stem.replace(' ', '_')
    out_dir = Path(__file__).parent / 'imported' / base
    out_dir.mkdir(parents=True, exist_ok=True)
    try:
        extract_text(pdf, out_dir)
    except Exception as e:
        print('Text extraction failed:', e)
    print('Done. Review files in', out_dir)

if __name__=='__main__':
    main()