Whatsapp group chat to excel/csv. Run python whatsapp_extract.py <filename>.txt

whatsapp_extract.py

#Export required chat as text without media
#This supports group chats to tabular format where you have all contacts of people in the group
#todo: add regex for numbers as authors
import pandas as pd
import os
import numpy as np
import re
import sys


def starts_with_date(s):
    pattern = r"^([0-9]+\/[0-9]+\/[0-9]+, [0-9]+:[0-9]+)"
    return True if re.match(pattern, s) else False


def starts_with_author(s):
    pattern = r"^([\w]+):|([\w]+[\s]+[\w]+):"
    return True if re.match(pattern, s) else False


def date_time(s):
    s_split = s.split(", ")
    date, time = s_split[0], s_split[1]
    return date, time


def get_data(line):
    line_split = line.split(" - ")
    date, time = date_time(line_split[0])
    message = " ".join(line_split[1:])

    if starts_with_author(message):
        message_split = message.split(": ")
        author = message_split[0]
        message = " ".join(message_split[1:])
    else:
        author = None
    return date, time, author, message


def extract(file_name):
    buffer = []
    data = []
    date, time, author = None, None, None
    with open(file_name, encoding="utf-8") as f:
        f.readline()
        while True:
            line = f.readline()
            if not line:
                break
            line = line.strip()
            if starts_with_date(line):
                if len(buffer) > 0:
                    data.append([date, time, author, " ".join(buffer)])
                buffer.clear()
                date, time, author, message = get_data(line)
                buffer.append(message)
            else:
                buffer.append(line)
    df = pd.DataFrame(data, columns=["Date", "Time", "Author", "Message"])
    return df


if __name__ == "__main__":
    file_name = sys.argv[1]
    fname = file_name.split(".")[0]
    df = extract(file_name)
    # output_file = f"{fname}_extract.csv"
    # df.to_csv(output_file, index=False, encoding="utf-8")
    output_file = f"{fname}_extract.xls"
    df.to_excel(output_file, index=False)