Parse Whatsapp chats

parse.py

import re
import sys
import glob
import pandas as pd
import matplotlib.pyplot as plt

regex = """(?P<datetime>\d{1,2}\/\d{1,2}\/\d{1,4}, \d{1,2}:\d{1,2}( (?i)[ap]m)*) - (?P<name>.*(?::\s*\w+)*|[\w\s]+?)(?:\s+(?P<action>joined|left|was removed|changed the (?:subject to "\w+"|group's icon))|:\s(?P<message>(?:.+|\n(?!\d{1,2}\/\d{1,2}\/\d{1,4}, \d{1,2}:\d{1,2}( (?i)[ap]m)*))+))"""

files = sys.argv[1:]

for fname in files:
    with open(fname) as f:
        text = f.read()
    matches = re.findall(regex, text)
    messages = []
    for match in matches:
        messages.append(match[::2])

    df = pd.DataFrame(messages, columns=['datetime', 'name', 'message'])
    df.datetime = pd.to_datetime(df.datetime, dayfirst=True)
    df.set_index('datetime', inplace=True)
    lengths = df.message.str.len()
    monthly = lengths.groupby(pd.Grouper(freq='M')).count() #.sum()
    #monthly = lengths.groupby(pd.Grouper(freq='D')).count().rolling('30d', min_periods=1).sum()
    #plt.figure()
    #ax = monthly.plot(title=fname[19:-4])
    ax = monthly.plot()

ax.legend([fname[19:-4] for fname in files])
#plt.ylabel("bytes/month")
plt.ylabel("messages/month")
plt.show()