Messenger_1Million_Stats/scripts/find_gromots.py

from datetime import datetime
from million.analyze.wordFinder import findWords
from million.parse.fb_exports import FacebookExportParser


DATA_PATH = './data/'

parser = FacebookExportParser()

export = parser.parse(DATA_PATH)

gros_mots = ['merde', 'sexe', 'pute', 'putain', 'bite', 'nichon', 'con(ne)?', 'baiser?']
msg_gros_mots = findWords(export.messages, gros_mots)

msg_gros_mots_grp = {}

for msg in msg_gros_mots:
    if msg.sender_name not in msg_gros_mots_grp: msg_gros_mots_grp[msg.sender_name] = []
    msg_gros_mots_grp[msg.sender_name].append(msg)

for name in msg_gros_mots_grp:
    print(name)

    for msg in msg_gros_mots_grp[name]:
        time = datetime.fromtimestamp(msg.timestamp_ms / 1000)
        time_str = time.strftime("%d/%m/%Y %H:%M:%S")
        print(f"\t{time_str} : {msg.content}")