Extract dates, locations, and summaries of events within a specified period from an ICS file and save them as a CSV file.

ical2csv.py

#!/usr/bin/env python3
from datetime import datetime
from pathlib import Path

import pandas as pd
from icalendar import Calendar


def extract_vevents(ics_file, from_yymmdd='1677-09-21', to_yymmdd='2262-04-11'):
    """Extract dates, locations, and summaries of events within a specified period
       from an ICS file and save them as a CSV file.

    Args:
        ics_file (str or Path):
        from_yymmdd (str): Beginning of the target period.
        to_yymmdd (str): Ending of the target period.
    Returns:
        pandas.DataFrame:
    References:
        https://icalendar.readthedocs.io/en/latest/index.html
        https://datatracker.ietf.org/doc/html/rfc5545.html
    """
    src_path = Path(ics_file)
    # For keyboard inputs
    from_yymmdd = '1677-09-21' if from_yymmdd == '' else from_yymmdd
    to_yymmdd = '2262-04-11' if to_yymmdd == '' else to_yymmdd
    # Convert to datetime.date
    from_date = datetime.strptime(from_yymmdd, '%Y-%m-%d').date()
    to_date = datetime.strptime(to_yymmdd, '%Y-%m-%d').date()
    # Prepare an event list.
    with src_path.open() as f:
        calendar = Calendar.from_ical(f.read())
        events = calendar.walk('VEVENT')  # <class 'list'>

    outer = []
    for event in events:
        start_dt = event.get('dtstart').dt  # Basically <datetime.datetime> but sometimes <datetime.date>
        # Align data types to <class 'datetime.date'> for comparison.
        base_date = start_dt.date() if isinstance(start_dt, datetime) else start_dt
        # Skip dates_ out of the range.
        if not from_date <= base_date <= to_date:
            continue
        # Rest of the items
        end_dt = event.get('dtend').dt
        location = event.get('LOCATION')
        summary = event.get('SUMMARY')
        outer.append([str(start_dt), str(end_dt), location, summary])  # Cast into str for sorting.
    # Construct a DataFrame
    df = pd.DataFrame(
        outer,
        columns=['dtstart', 'dtend', 'LOCATION', 'SUMMARY']).sort_values(
        by=['dtstart', 'dtend'], ignore_index=True)
    df.dtstart = df.dtstart.apply(pd.to_datetime)
    df.dtend = df.dtstart.apply(pd.to_datetime)
    # Sava as a CSV file.
    date_max, date_min = df.dtstart.iat[0].date(), df.dtstart.iat[-1].date()
    fname = f'{src_path.stem}_{date_max}_{date_min}.csv'
    fpath = Path('.').absolute() / fname
    df.to_csv(fpath, index=False)
    print(f'\033[93mSaved: {fpath}\033[0m')
    return df


if __name__ == '__main__':
    extract_vevents(
        input('ICS file? >> '),
        input('Date FROM (yyyy-mm-dd) >> '),
        input('Date TO (yyyy-mm-dd) >> ')
    )