rio2016.py

import bs4
import calendar
import requests
import time


def get_list(url, time):
    r = requests.get(url)

    soup = bs4.BeautifulSoup(r.text, "html.parser")
    streams = []
    for it in soup.select('span[data-redir]'):
        if int(it["data-broadcast-end"]) >= time:
            info_dict = {
                'url': it["data-redir"],
                'title': it.findChild("span", {"class": "title"}),
                'time': it.findChild("span", {"class": "time"}),
                "category": it.findChild("span", {"class": "category"})
            }
            streams.append(info_dict)
    return streams


def main():
    cur_time = calendar.timegm(time.gmtime()) * 1000

    url1 = "http://www.api.v3.tvp.pl/shared/listing.php?portal_name=rio2016.tvp.pl&portal_id=19369963&parent_id=24035157&type=directory_standard&copy=false&direct=true&order=position%2C1&count=-1&epg_start=" + str(cur_time) + "&epg_end=" + str(cur_time) + "&template=epg%2Fdisciplines-listing.html"
    url2 = "http://www.api.v3.tvp.pl/shared/listing.php?portal_name=rio2016.tvp.pl&portal_id=19369963&parent_id=25851771&type=virtual_channel&copy=false&direct=true&order=position%2C1&count=-1&epg_start=" + str(cur_time) + "&epg_end=" + str(cur_time) + "&template=epg%2Fchannels-listing.html"

    streams = get_list(url1, cur_time)
    streams += get_list(url2, cur_time)

    streams = [dict(p) for p in set(tuple(i.items()) for i in streams)]
    streams = sorted(streams, key=lambda k: k['title'].text)

    for s in streams:
        if s["category"]:
            print ("%s: %s (%s)\n%s\n" % (s["title"].text, s["category"].text, s["time"].text, s["url"]))
        else:
            print ("%s (%s)\n%s\n" % (s["title"].text, s["time"].text, s["url"]))

if __name__ == "__main__":
    main()