import fitz
import sys

doc = fitz.open(r'C:\git\spark-lesson\reference\sources\cenrs-book.pdf')
print(f'Pages: {len(doc)}')
for i in range(min(len(doc), 10)):
    text = doc[i].get_text()
    if text.strip():
        print(f'=== PAGE {i+1} ===')
        print(text[:3000])
        print('...')