Files
Aislo/resources/tester/scratch/inspect_pdf_table_structure.py
T

14 lines
471 B
Python

import sys, os, re, json
import fitz
sys.stdout.reconfigure(encoding='utf-8')
pdf_path = "resources/knowledge/original/원가계산/건설공사_표준품셈/2026년_건설공사_표준품셈.pdf"
doc = fitz.open(pdf_path)
# Look closely at 1-2-2 in 제1장 (PDF page 60-61, printed pages 4-5)
print("=== PDF Page 60 (Printed page 4) Tables ===")
print(doc[59].get_text()[:1200])
print("\n=== PDF Page 61 (Printed page 5) Tables ===")
print(doc[60].get_text()[:1200])