musortv.py

#!/usr/bin/env python3

import argparse
import json
from datetime import datetime

import bs4
import pytz
import requests
import tzlocal


def parse_page(url):
    musorok = []

    r = requests.get(
        url,
        headers={
            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.96 Safari/537.36',
        },
    )

    soup = bs4.BeautifulSoup(r.text, 'lxml')

    for entry in soup.select('.multicolumndayprogarea .smartpe_progentry'):
        musor = {}

        start_raw = entry.select('.smartpe_time')[0]['content']
        start_utc = datetime.strptime(start_raw, '%Y-%m-%dGMT%H:%M:%S')
        start_local = start_utc.replace(tzinfo=pytz.utc).astimezone(tzlocal.get_localzone())
        start_fmt = start_local.strftime('%Y-%m-%d %H:%M')
        musor['start'] = start_fmt

        name = entry.select('a')[0].get_text()
        musor['name'] = name

        desc = entry.select('.smartpe_progshortdesc')[0].get_text()
        if desc.isdigit():
            try:
                desc = next(entry.select('.smartpe_progentrylong')[0].stripped_strings)
            except StopIteration:
                desc = ''
        musor['desc'] = desc

        premier = entry.select('[class^="smartpe_recommendation_premier"]')
        musor['premier'] = bool(premier)

        musorok.append(musor)

    for (i, musor) in enumerate(musorok):
        if i < len(musorok) - 1:
            musor['end'] = musorok[i + 1]['start']
        else:
            musor['end'] = ''

    musorok = [x for x in musorok if x['start'].split()[0] == musorok[0]['start'].split()[0]]

    return musorok


if __name__ == '__main__':
    parser = argparse.ArgumentParser(prog='musortv')
    parser.add_argument(
        '-r', '--raw',
        action='store_true',
        help='print raw JSON data',
    )
    parser.add_argument(
        'urls',
        nargs='+',
        metavar='URL',
        help='musor.tv URL',
    )
    args = parser.parse_args()

    for url in args.urls:
        data = parse_page(url)

        if args.raw:
            print(json.dumps(data, indent=2))
        else:
            for musor in data:
                premier = '(PREMIER)' if musor['premier'] else ''
                end = musor['end'].split()[1] if musor['end'] else ''
                print(f'[{musor["start"]} - {end:>5}] {musor["name"]} [{musor["desc"]}] {premier}')