import urllib.request from html.parser import HTMLParser import xml.etree.ElementTree as ET from xml.dom import minidom from datetime import datetime, timedelta from zoneinfo import ZoneInfo from urllib.parse import quote # ========================================== # NASTAVENIE # ========================================== START_DATE = datetime.now().date() DAYS = 3 OUTPUT = "/opt/epg/sledovani.xml" TIMEZONE = ZoneInfo("Europe/Bratislava") TIMEZONE = ZoneInfo("Europe/Prague") CHANNELS = [ "animal_planet", "ard", "auto_motor_sport", "axn", "axnblack", "axnwhite", "baby_tv", "ballcasterz", "barrandov", "barrandovplus", "bbc", "bbc_earth", "bbc_first", "boomerang", "brno1", "btv", "cartoon_network_hd", "cinemax1", "cinemax2", "cms_tv", "cnn", "cs_film", "csrtv", "ct1", "ct1_sk", "ct1jm", "ct1jzc", "ct1sm", "ct1svc", "ct2", "ct24", "ct4sport", "ctart", "ctdecko", "dajto", "detskeradio", "Discovery", "Disney_Channel", "disney_junior", "DocuBoxHD", "dog_cat", "doma", "ducktv_cz", "duna", "dunaworld", "DVTV", "epic_drama", "espresso", "Eurosport", "Eurosport2", "fanda", "FashionboxHD", "fast_epg_comedy", "fast_epg_czsk", "fast_epg_family", "fast_epg_kids", "fast_epg_kids_sk", "fast_sledovanietv_comedy", "fast_sledovanietv_czsk", "fast_sledovanietv_family", "Fastnfunbox", "FightboxHD", "Film_Europe", "film_plus", "filmbox", "FilmboxArthouse", "FilmboxExtra", "FilmboxFamily", "FilmboxHD", "filmboxplus", "filmpro", "fireplace", "fishinghunting", "food_network", "france24", "france24_fr", "funbox_uhd", "godzone_tv", "golf", "GTTV", "haha_tv", "HBO", "hbo_comedy", "HBO2", "hgtv_ce", "history", "hn_tv", "hobby", "horor_film", "i_concerts", "ID", "ivodarenstvi", "ivysocina_stream_zs", "jihoceska_televize", "Jim_Jam", "joj", "joj_24", "joj_sport", "joj_sport2", "joj_svet", "joj_svet_cz", "jojcinema", "jojfamily", "jojplus", "Kino_CS", "kinobarrandov", "kinosvet", "kladno", "komentovana_krmeni", "krea_tv", "krusna_tv", "KVIFF_TV", "lala_tv", "levicka_tv", "locall_tv", "loop_naturetv_mumlava_waterfalls", "loop_naturetv-galerie-zvirat", "loop_naturetv-osetrovani-mladat", "love_nature", "m1", "m2", "m4", "m5", "markiza", "markiza_klasik", "markiza_krimi", "markizaint", "mezzo", "mezzo_live", "Minimax", "mnamtv", "mnau", "moldava_tv", "mtv", "nat_geo_wild", "naturetv", "NGC_HD", "nhk", "Nickelodeon", "nickjr", "nicktoons", "NoePlus", "nova", "nova_lady", "nova_sport", "nova_sport2", "novacinema", "novaint", "ocko", "ocko_blackHD", "ocko_expresHD", "ocko_express", "ocko_starHD", "ockogold", "ockoHD", "orf1", "orf2", "pan_kubinska_hora", "pan_marino_brdo", "plzen_tv", "pohoda", "Polar", "polsat", "polsatsport", "praha", "prima_krimi", "prima_krimi_sk", "prima_love_sk", "prima_max", "prima_news", "prima_show", "prima_sport", "prima_star", "primacool", "primacool_sk", "primafamily", "primalove", "primaplus", "primazoom", "pscr", "radior", "raj_tv", "rebel", "regiotv", "regiotv_hun", "retro", "rik", "rik2", "rt_jc", "rt_ustecko", "rtm_plus_liberec", "rusyn_fm", "ruzomberok", "rv_tv", "sat_crime_invest", "seejay", "senzi_tv", "severka_tv", "Seznam", "sky_news", "slagr", "slagr_premium", "slagr2", "slovacko", "slovak_sport", "slovak_sport2", "smichov", "spektrum", "spektrum_home", "sport1cz", "sport1sk", "Sport2", "stork_nest", "stork_nest_sk", "stv1", "stv1sk", "stv2", "stv24", "stv2sk", "stv4", "ta3", "telka", "tik_bohumin", "TLC", "travelhd", "travelxp", "tv_bratislava", "tv_central", "tv_doktor", "tv_liptov", "tv_lux", "tv_mistral", "tv_nitricka", "tv_nove_zamky", "tv_osem", "tv_paprika", "tv_partizanske", "tv_poprad", "tv_prerov", "tv_puls", "tv_reduta", "tv_romana", "tv_ruzinov", "tv_sen", "tv_slovensko", "tv5", "tv7", "tv9", "tvbeskyd", "TVlife", "tvnoe", "tvp1", "tvp2", "tvp3", "tvr", "uatv", "ukraina_24", "up_network", "uscenes_cat_cafe", "uscenes_coral_garden", "uscenes_hammock_beach", "uscenes_hammock_beach_hd", "ustecko_tv", "v1tv", "vega", "viasat_explore", "viasat_history", "viasat_nature", "war", "warner_tv", "wau", "zaktv", "zdf", "zoo_brno_a_vesnice", "zoo_brno_m_ledni", "zvirata_v_zoo" ] # ========================================== # HTML PARSER # ========================================== class EPGParser(HTMLParser): def __init__(self, channel_id): super().__init__() self.channel_id = channel_id self.programmes = [] self.current_time = None self.current_title = None self.in_li = False self.in_a = False def handle_starttag(self, tag, attrs): attrs = dict(attrs) if tag == "li": self.in_li = True self.current_time = None self.current_title = None if self.in_li and tag == "span": data_time = attrs.get("data-time") if data_time: try: self.current_time = int(data_time) except ValueError: pass if self.in_li and tag == "a": href = attrs.get("href", "") if "channelEvent:" + self.channel_id + ":" in href: self.in_a = True def handle_data(self, data): if self.in_a: text = data.strip() if text: if self.current_title: self.current_title += " " + text else: self.current_title = text def handle_endtag(self, tag): if tag == "a": self.in_a = False if tag == "li": if self.current_time and self.current_title: self.programmes.append({ "start": self.current_time, "title": self.current_title }) self.in_li = False # ========================================== # XMLTV # ========================================== tv = ET.Element("tv") tv.set( "generator-info-name", "SledovaniTV" ) total_channels = 0 total_programmes = 0 # ========================================== # CHANNELS # ========================================== for channel_id in CHANNELS: print() print("==========================================") print("KANÁL:") print("ID:", channel_id) print("==========================================") # -------------------------------------- # CHANNEL # -------------------------------------- channel = ET.SubElement( tv, "channel" ) channel.set( "id", channel_id ) display_name = ET.SubElement( channel, "display-name" ) display_name.text = channel_id total_channels += 1 # -------------------------------------- # DNI # -------------------------------------- base_urls = [ "https://sledovanitv.cz/epg/default/", "https://sledovanietv.sk/epg/default/" ] for day_offset in range(DAYS): current_date = START_DATE + timedelta( days=day_offset ) date_string = current_date.strftime( "%Y-%m-%d" ) print() print("Dátum:", date_string) programmes = [] # -------------------------------------- # SKÚSENIE CZ / SK # -------------------------------------- for base_url in base_urls: url = ( base_url + date_string + "?channel=channel%3A" + quote(channel_id) ) print("URL:", url) try: req = urllib.request.Request( url, headers={ "User-Agent": "Mozilla/5.0" } ) with urllib.request.urlopen( req, timeout=30 ) as response: html = response.read().decode( "utf-8" ) except Exception as e: print("CHYBA:", e) continue parser = EPGParser( channel_id ) parser.feed(html) test_programmes = parser.programmes # ---------------------------------- # ODSTRÁNENIE DUPLÍC # ---------------------------------- unique = {} for p in test_programmes: key = ( p["start"], p["title"] ) if key not in unique: unique[key] = p test_programmes = list( unique.values() ) test_programmes.sort( key=lambda x: x["start"] ) print( "Nájdené programy:", len(test_programmes) ) # ---------------------------------- # AK SME NIEČO NAŠLI, POUŽIJEME TO # ---------------------------------- if test_programmes: programmes = test_programmes break # -------------------------------------- # PROGRAMMES # -------------------------------------- for i, program in enumerate( programmes ): start_timestamp = program[ "start" ] start_dt = datetime.fromtimestamp( start_timestamp, tz=TIMEZONE ) # Koniec programu = # začiatok ďalšieho programu if i + 1 < len(programmes): end_timestamp = programmes[ i + 1 ]["start"] end_dt = datetime.fromtimestamp( end_timestamp, tz=TIMEZONE ) else: # Posledný program dňa # zatiaľ +1 hodina end_dt = ( start_dt + timedelta(hours=1) ) start_xml = start_dt.strftime( "%Y%m%d%H%M%S %z" ) end_xml = end_dt.strftime( "%Y%m%d%H%M%S %z" ) programme = ET.SubElement( tv, "programme" ) programme.set( "start", start_xml ) programme.set( "stop", end_xml ) programme.set( "channel", channel_id ) title = ET.SubElement( programme, "title" ) title.set( "lang", "cs" ) title.text = program[ "title" ] total_programmes += 1 # ========================================== # ULOŽENIE XML # ========================================== xml_data = ET.tostring( tv, encoding="utf-8" ) pretty = minidom.parseString( xml_data ).toprettyxml( indent=" ", encoding="UTF-8" ) with open( OUTPUT, "wb" ) as f: f.write(pretty) # ========================================== # VÝSLEDOK # ========================================== print() print() print("==========================================") print(" SLEDOVANITV XMLTV – 3 DNI") print("==========================================") print("Od: ", START_DATE) print("Počet dní:", DAYS) print("Kanály: ", total_channels) print("Programy: ", total_programmes) print("Výstup: ", OUTPUT) print("==========================================") print()