PDF - Table of Contents

import re     #REGEX
import glob   #Search files
import fitz   #PyMuPDF 1.14.2

#REGEX
findEN = r"(^[a-z]{2})\s\D*?\s*([0-9]+)"
#findHR = r"hr\D*\s*([0-9]+)\D*([0-9]*)"

#Search all pdfs from this directory
pdfList = glob.glob('./*.pdf')


#Go through each pdf
for pdf in pdfList:
    doc = fitz.open(pdf)
    text = doc[0].getText("text")
    numbero = doc.pageCount

    #Spis tresci
    engTest = re.findall(findEN, text ,re.MULTILINE)
    engTest = sorted(engTest, key=lambda tup: int(tup[1]))
    for i,item in enumerate(engTest):
        if "en" in item:
            engStart = item[1]
            if(len(engTest)>i+1):
                engEnd = engTest[i+1][1]
            else:
                engEnd = doc.pageCount()
        if "hr" in item:
            hrStart = item[1]
            if(len(engTest)>i+1):
                hrEnd = engTest[i+1][1]
            else:
                hrEnd = doc.pageCount()



    #Save whole text to files
    #EN
    with open("EN", "a+", encoding="utf-8") as f:
        for i in range(int(engStart)-1, int(engEnd)-1):
            if i < numbero:
                actualPage = doc[i].getText("text")
                f.write(actualPage)
                f.truncate()
    #HR
    with open("HR", "a+", encoding="utf-8") as f:
        for i in range(int(hrStart)-1, int(hrEnd)-1):
            if i < numbero:
                actualPage = doc[i].getText("text")
                f.write(actualPage)
                f.truncate()

    doc.close()