PR3_Steinberger/SL2/s2_a3.py

82 lines
2.3 KiB
Python
Raw Normal View History

import re
import json
import string
text_file = open(r"Personen.txt", "r")
data = text_file.readlines()
2023-01-12 12:50:06 +01:00
arr = [None] * len(data)
counter = 1
text_file.close()
for line in data:
2023-01-12 12:50:06 +01:00
try:
data_array = re.split(",", line)
name = data_array[0]
name_array = re.split("\s",name)
adresse1 = data_array[1]
adresse2 = data_array[2]
geburtsdatum = data_array[3]
telefon = data_array[4]
telefon = telefon.replace("\n", "")
2023-01-12 12:50:06 +01:00
titel = re.search("^.*\.$",name_array[0])
2023-01-12 12:50:06 +01:00
if titel != None:
titel = titel.string
if len(name_array) == 4:
vorname = name_array[1]
zweitname = name_array[2]
nachname = name_array[3]
else:
vorname = name_array[1]
nachname = name_array[2]
zweitname = None
else:
2023-01-12 12:50:06 +01:00
if len(name_array) == 3:
vorname = name_array[0]
zweitname = name_array[1]
nachname = name_array[2]
else:
vorname = name_array[0]
nachname = name_array[1]
zweitname = None
2023-01-12 12:50:06 +01:00
# adresse_array = re.split("\s", adresse)
plz = re.findall("\d{5}", adresse2)
hausnummer = re.findall(r"\b\d{1,4}\b", adresse1)
strasse_chars = re.findall("\D",adresse1)
strasse = ''.join(strasse_chars)
strasse = strasse.replace("\"", "")
ort_chars = re.findall("\D",adresse2)
ort = ''.join(ort_chars)
ort = ort.replace("\"", "")
2023-01-12 12:50:06 +01:00
geburtsdatum = re.findall("[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9]", line)
# telefon = re.findall("\d{6,20}", line)
2023-01-12 12:50:06 +01:00
person = {
"Index" : counter,
"Titel" : titel,
"Vorname" : vorname,
"Zweitname" : zweitname,
"Nachname" : nachname,
"Geburtsdatum" : geburtsdatum,
"Strasse" : strasse,
"Hausnummer" : hausnummer,
"PLZ" : plz,
"Wohnort" : ort,
"Rufnummer" : telefon
}
arr[counter - 1] = person
counter = counter + 1
except:
continue
with open(r"PersonenNeu.json", "w") as f:
json.dump(arr,f, indent=1, ensure_ascii=False)
2023-01-10 13:29:30 +01:00
f.close()