PR3_Steinberger/SL2/s2_a3.py

import re
import json

file = open(r"Personen.txt", 'r')
lines = file.readlines()
del lines[0] #delete line "Name,Adresse,GebDatum,Telefon"

personsData = [None] * len(lines)

file.close()

index = 0 #set index equals line

for line in lines:
    lineData = re.split(",", line) #splits whole line into name, adresse, birthday, number
    nameData = re.split("\s", lineData[0]) #splits name area
    
    #pre inzialiizing data 
    title = None #could be null
    vname = ""
    secName = None #could be null
    name = ""
    bday = ""
    street = ""
    streetNumber = 0 #integer-format
    postal = 0 #integer-format
    city = ""
    phone = ""
    
    #Name-Extract
    if(re.fullmatch(".*\.$", nameData[0]) and len(nameData) > 2): #Ausnahmebehandlung für "Klaus-D. Baum" Zeile 290 bzw. Personen . im Vornamen | . = beliebiger char \.$ = Ende auf Punkt
        title = nameData[0]
        if(len(nameData) == 4): #Check für Zweitnamen
            vname = nameData[1]
            secName = nameData[2]
            name = nameData[3]
        else:
            vname = nameData[1]
            name = nameData[2]
    else:
        if(len(nameData) == 3): #Check für Zweitnamen
            vname = nameData[0]
            secName = nameData[1]
            name = nameData[2]
        else:
            vname = nameData[0]
            name = nameData[1]
    
    #Adresse-Extract
    street = re.search('[^\"\s\d]+', lineData[1]).group(0) # ^ = ignoriert Leerzeichen " und Zahlen
    streetNumber = re.search('(?<=\D)\d+', lineData[1]).group(0) #beginnt bei ersten Zahl
    postal = re.search('\d{5}', lineData[2]).group(0) #extrahiert die ersten fünf Zahlen
    city = re.search('[^\"\s\d]+', lineData[2]).group(0) #ignoriert " Leerzeichen und Zahlen
    
    #Birthday
    bdayData = re.split("-", lineData[3]) #split birthday data
    bday = bdayData[2]+"."+bdayData[1]+"."+bdayData[0] #compose data in right order
    
    #Telefon
    phone = re.search('[^\n]+', lineData[4]).group(0) #just extract \n and keep format
    
    #json format einteilung
    person = {
        'Index' : index,
        'Titel' : title,
        'Vorname' : vname,
        'Zweitname' : secName,
        'Nachname' : name,
        'Geburtstag' : bday,
        'Strasse' : street,
        'Hausnummer' : streetNumber,
        'PLZ' : postal,
        'Wohnort' : city,
        'Telefonnummer' : phone}
    personsData[index] = person

    index += 1

with open(r'PersonenNeu.json', 'w') as f:
    json.dump(personsData, f, indent=1, ensure_ascii=False)
    
f.close()