152 lines
3.5 KiB
Python
152 lines
3.5 KiB
Python
import xml.etree.ElementTree as ET
|
|
from unidecode import unidecode #### ! ! ! pip install Unidecode ! ! ! !
|
|
|
|
#processes sms messages from locally exported xml table from "sms backup & restore" app on android
|
|
|
|
# important settings !
|
|
soubor = 'sms-20241116201536.xml'
|
|
time_after = 1731312702226
|
|
zaznam_file = "relevant_sms_test1.txt"
|
|
#
|
|
|
|
kandidati = {"prima" : 0,
|
|
"sekunda" : 0,
|
|
"tercie" : 0,
|
|
"kvarta" : 0,
|
|
"kvinta" : 0,
|
|
"sexta" : 0,
|
|
"septima" : 0,
|
|
"oktava" : 0,
|
|
"1a" : 0,
|
|
"2a" : 0,
|
|
"3a" : 0,
|
|
"4a" : 0}
|
|
|
|
kandidati = {"bogus" : 0,
|
|
"sigma" : 0,
|
|
"ahoj" : 0}
|
|
# important settings !
|
|
|
|
###
|
|
###
|
|
|
|
class Sms_hlas():
|
|
def __init__(self, author, content, kandidati):
|
|
self.author = author
|
|
self.content = content
|
|
self.kandidati = kandidati
|
|
|
|
###
|
|
###
|
|
|
|
def zpracuj_sms(): #podle data
|
|
tree = ET.parse(soubor)
|
|
root = tree.getroot()
|
|
|
|
hlasy = [] # = relevant sms
|
|
sms_count = 0
|
|
relevant = 0
|
|
|
|
for child in root:
|
|
sms_count += 1
|
|
date = int(child.get('date'))
|
|
content = unidecode(child.get('body')).lower()
|
|
author = child.get('address')
|
|
|
|
if date >= time_after:
|
|
relevant += 1
|
|
hlasy.append(Sms_hlas(author, content, [])) #obsah listu
|
|
else:
|
|
continue
|
|
|
|
return(hlasy, sms_count, relevant)
|
|
|
|
zpracovane = zpracuj_sms()
|
|
sms_count = zpracovane[1]
|
|
relevant = zpracovane[2]
|
|
hlasy = zpracovane[0]
|
|
|
|
###
|
|
###
|
|
|
|
def najdi_kandidaty(hlasy, kandidati):
|
|
|
|
for h in hlasy:
|
|
for k in kandidati:
|
|
if k in h.content:
|
|
h.kandidati.append(k)
|
|
else:
|
|
continue
|
|
|
|
return(hlasy)
|
|
|
|
zpracovane_hlasy = najdi_kandidaty(hlasy, kandidati)
|
|
|
|
###
|
|
###
|
|
|
|
def spocitej_kandidaty(zprac_hlasy, kandidati):
|
|
neplatne_hlasy = []
|
|
platne_hlasy = []
|
|
prazdne_hlasy = []
|
|
|
|
for h in zprac_hlasy:
|
|
if len(h.kandidati) > 1:
|
|
neplatne_hlasy.append(h)
|
|
elif len(h.kandidati) == 1:
|
|
for k in kandidati:
|
|
if k in h.kandidati:
|
|
kandidati[k] += 1
|
|
platne_hlasy.append(h)
|
|
else:
|
|
continue
|
|
else:
|
|
prazdne_hlasy.append(h)
|
|
|
|
return(kandidati, neplatne_hlasy, platne_hlasy, prazdne_hlasy)
|
|
|
|
|
|
spocitane = spocitej_kandidaty(zpracovane_hlasy, kandidati)
|
|
|
|
kandidati = spocitane[0]
|
|
neplatne_hlasy = spocitane[1]
|
|
platne_hlasy = spocitane[2]
|
|
prazdne_hlasy = spocitane[3]
|
|
|
|
###
|
|
###
|
|
|
|
def zapis_do_zaznamu(zaznam, nazev, list):
|
|
|
|
zaznam.write(f"\n\n\n{nazev} - {len(list)}\n")
|
|
for i in list:
|
|
zaznam.write(f"Autor: {i.author} ----- Kandidati: {i.kandidati} ----- Content: {i.content}\n")
|
|
|
|
def prite(zaznam, msg):
|
|
zaznam.write(f"{msg}\n")
|
|
print(msg)
|
|
|
|
###
|
|
###
|
|
|
|
file = open(zaznam_file, 'a')
|
|
zapis_do_zaznamu(file, "ZAZNAMENANE HLASY", zpracovane_hlasy)
|
|
zapis_do_zaznamu(file, "PLATNE HLASY", platne_hlasy)
|
|
zapis_do_zaznamu(file, "NEPLTANE HLASY", neplatne_hlasy)
|
|
zapis_do_zaznamu(file, "PRAZDNE HLASY", prazdne_hlasy)
|
|
|
|
|
|
prite(file, "\n\n- - - - - - - - - - - - - - - - - - -")
|
|
|
|
|
|
prite(file, f"sms:{sms_count} relevant(in time):{relevant}-{len(hlasy)}")
|
|
prite(file, f"platne:{len(platne_hlasy)} neplatne:{len(neplatne_hlasy)} prazdne:{len(prazdne_hlasy)}\n")
|
|
|
|
prite(file, "VYSLEDKY")
|
|
sorted_items = sorted(kandidati.items(), key=lambda kv: (kv[1], kv[0]))
|
|
for k in sorted_items:
|
|
prite(file, f"{k[0]} -> {k[1]}")
|
|
|
|
|
|
prite(file, "- - - - - - - - - - - - - - - - - - - ")
|