Python script to scrape details from netflix usage log.

netflix-log.py

import pandas as pd
import urllib
from bs4 import BeautifulSoup
import argparse


def _parse():
    parser = argparse.ArgumentParser()
    parser.add_argument('-html', type=str, help='path to html file')
    parser.add_argument('-f', '--filename', type=str, help='name to save the output')
    return parser.parse_args()


def _generate(path: str, outfile: str):
    path = 'file:///' + path
    file = urllib.request.urlopen(path)
    soup = BeautifulSoup(file.read(), 'html.parser')
    ul = soup.find('ul', attrs={'class': 'structural retable'})
    lis = ul.findAll('li')
    data = []
    for li in lis:
        device = li.find('h3').text
        divs = li.findAll('div', attrs={'class': 'activityAccess'})
        for div in divs:
            location_ip = div.find('div').text.split(' - ')
            last_used = div.find('div', attrs={'class': 'activityDate'}).text.split(',')
            date = last_used[0].split(':')[1]
            time = last_used[1]
            location = location_ip[0]
            ip = location_ip[1]
            i = {}
            i['device'] = device
            i['ip'] = ip
            i['location'] = location
            i['date'] = date
            i['time'] = time
            data.append(i)
    df = pd.DataFrame(data)
    df.to_csv(outfile, index=False)


def main():
    args = _parse()
    out_filename = args.filename
    html_path = args.html
    print(out_filename)
    _generate(path=html_path, outfile=out_filename)


if __name__ == '__main__':
    main()