python3 << 'EOF' import pdfplumber files = { "2021": "/tmp/workspace/attachments/73a5a688-aed8-4ec7-8764-fd4060699e66/2021.pdf", "2022": "/tmp/workspace/attachments/73a5a688-aed8-4ec7-8764-fd4060699e66/2022.pdf", "2023": "/tmp/workspace/attachments/73a5a688-aed8-4ec7-8764-fd4060699e66/2023.pdf", "2024": "/tmp/workspace/attachments/73a5a688-aed8-4ec7-8764-fd4060699e66/2024.pdf", "2025": "/tmp/workspace/attachments/73a5a688-aed8-4ec7-8764-fd4060699e66/20251.pdf", } for year, path in files.items(): print(f"\n{'='*60}") print(f"YEAR: {year}") print(f"{'='*60}") try: with pdfplumber.open(path) as pdf: print(f"Total pages: {len(pdf.pages)}") for i, page in enumerate(pdf.pages): text = page.extract_text() if text: print(f"\n--- Page {i+1} ---") print(text[:3000]) except Exception as e: print(f"Error: {e}") EOF

python3 << 'EOF' import subprocess import sys # Check what's available result = subprocess.run(['python3', '-c', 'import fitz; print("pymupdf ok")'], capture_output=True, text=True) print("pymupdf:", result.stdout.strip(), result.stderr.strip()) result2 = subprocess.run(['python3', '-c', 'from pdf2image import convert_from_path; print("pdf2image ok")'], capture_output=True, text=True) print("pdf2image:", result2.stdout.strip(), result2.stderr.strip()) result3 = subprocess.run(['python3', '-c', 'import pypdf; r = pypdf.PdfReader("/tmp/workspace/attachments/73a5a688-aed8-4ec7-8764-fd4060699e66/2021.pdf"); p = r.pages[1]; print(repr(p.extract_text()[:500]))'], capture_output=True, text=True) print("pypdf page2:", result3.stdout.strip(), result3.stderr.strip()) EOF

mkdir -p /tmp/workspace/pdf_images && python3 << 'EOF' from pdf2image import convert_from_path import os files = { "2021": "/tmp/workspace/attachments/73a5a688-aed8-4ec7-8764-fd4060699e66/2021.pdf", "2022": "/tmp/workspace/attachments/73a5a688-aed8-4ec7-8764-fd4060699e66/2022.pdf", "2023": "/tmp/workspace/attachments/73a5a688-aed8-4ec7-8764-fd4060699e66/2023.pdf", "2024": "/tmp/workspace/attachments/73a5a688-aed8-4ec7-8764-fd4060699e66/2024.pdf", "2025": "/tmp/workspace/attachments/73a5a688-aed8-4ec7-8764-fd4060699e66/20251.pdf", } # Convert ALL pages of each PDF to images (low DPI to keep small) for year, path in files.items(): print(f"Converting {year}...") pages = convert_from_path(path, dpi=120) print(f" {year}: {len(pages)} pages") for i, page in enumerate(pages): out_path = f"/tmp/workspace/pdf_images/{year}_page{i+1:02d}.png" page.save(out_path, "PNG") print(f" Saved {len(pages)} images for {year}") print("Done.") EOF