import pdfplumber
import json
import re

filename = "/home/x79/sisvietnamvn_01/sisvietnamvn_Trang chính thức hiện tại/DaoTao/2.-CHUONG-TRINH-CAN-THIEP-MACH-MAU-THAN-KINH-NANG-CAO-BO-SUNG-FINAL.pdf"
with pdfplumber.open(filename) as pdf:
    full_text = ""
    for page in pdf.pages:
        full_text += page.extract_text() + "\n"
        
    print("Total length:", len(full_text))
    # Find all headings
    headings = re.findall(r'^(\d+)\.\s+(.*)$', full_text, re.MULTILINE)
    print("Headings found:")
    for h in headings:
        print(h)