import fitz
import sys

doc = fitz.open(r'C:\git\spark-lesson\reference\sources\ufn-2000-paper.pdf')
output = []
for i in range(len(doc)):
    text = doc[i].get_text()
    if text.strip():
        output.append(f'=== PAGE {i+1} ===')
        output.append(text)
full = '\n'.join(output)
with open(r'C:\git\spark-lesson\reference\sources\ufn-2000-paper.txt', 'w', encoding='utf-8') as f:
    f.write(full)
print(f'Extracted {len(full)} chars from {len(doc)} pages')