Parse an Nginx access.log file into a Pandas DataFrame

parse_nginx_access_log.py

"""
Parse an Nginx access.log file into a Pandas DataFrame. Also works with gzipped files.
"""

import argparse
import pathlib

import pandas as pd


parser = argparse.ArgumentParser()
parser.add_argument("path", type=pathlib.Path, help="path to access.log file")

DATE_FORMAT = r"%d/%b/%Y:%H:%M:%S %z"


def remove_quotes(value):
    return value.strip(r'"') if value else value


def main(log_file):
    df = pd.read_csv(
        log_file,
        sep=r'\s(?=(?:[^"]*"[^"]*")*[^"]*$)(?![^\[]*\])',
        engine="python",
        usecols=[0, 3, 4, 5, 6, 7, 8],
        names=["ip", "time", "request", "status", "size", "referer", "agent"],
        parse_dates=False,
        header=None,
        converters={
            "request": remove_quotes,
            "referer": remove_quotes,
            "agent": remove_quotes,
        },
    )
    df["time"] = pd.to_datetime(df["time"], format=DATE_FORMAT, exact=False)

    # Aggregate views by day and IP
    summary = df.groupby([df["time"].dt.date, df["ip"]]).agg({"status": "count"})
    summary.sort_values(by=["time", "status"], ascending=False, inplace=True)
    print(summary.to_string())


if __name__ == "__main__":
    args = parser.parse_args()
    main(args.path)