import pdfplumber

all_text = []

with pdfplumber.open(r'C:\Users\a931627\Documents\stadtwerke-saas-analysis\leads\raw\unterfranken.pdf') as pdf:
    for i, page in enumerate(pdf.pages):
        w = page.width
        h = page.height
        # Split into left and right columns
        left = page.crop((0, 0, w/2, h))
        right = page.crop((w/2, 0, w, h))
        left_text = left.extract_text(x_tolerance=2, y_tolerance=2) or ""
        right_text = right.extract_text(x_tolerance=2, y_tolerance=2) or ""
        all_text.append(f"=== PAGE {i+1} LEFT ===\n{left_text}")
        all_text.append(f"=== PAGE {i+1} RIGHT ===\n{right_text}")

full = "\n".join(all_text)

# Write to file for easier reading
with open(r'C:\Users\a931627\Documents\stadtwerke-saas-analysis\leads\unterfranken_pdf_raw.txt', 'w', encoding='utf-8') as f:
    f.write(full)

print(f"Written {len(full)} chars")
print(full[:3000])