iptv/EPG/fetch.py

#!/usr/bin/env python3
import asyncio
import gzip
import json
from pathlib import Path
from xml.etree import ElementTree as ET

import httpx

tvg_ids_file = Path(__file__).parent / "TVG-IDs.json"
epg_file = Path(__file__).parent / "TV.xml"
epg_urls = [
    "https://epgshare01.online/epgshare01/epg_ripper_CA1.xml.gz",
    "https://epgshare01.online/epgshare01/epg_ripper_DUMMY_CHANNELS.xml.gz",
    "https://epgshare01.online/epgshare01/epg_ripper_ES1.xml.gz",
    "https://epgshare01.online/epgshare01/epg_ripper_FANDUEL1.xml.gz",
    "https://epgshare01.online/epgshare01/epg_ripper_MY1.xml.gz",
    "https://epgshare01.online/epgshare01/epg_ripper_PLEX1.xml.gz",
    "https://epgshare01.online/epgshare01/epg_ripper_PT1.xml.gz",
    "https://epgshare01.online/epgshare01/epg_ripper_UK1.xml.gz",
    "https://epgshare01.online/epgshare01/epg_ripper_US1.xml.gz",
    "https://epgshare01.online/epgshare01/epg_ripper_US2.xml.gz",
    "https://epgshare01.online/epgshare01/epg_ripper_US_LOCALS2.xml.gz",
    "https://epgshare01.online/epgshare01/epg_ripper_US_SPORTS1.xml.gz",
]

client = httpx.AsyncClient(
    timeout=5,
    follow_redirects=True,
    headers={
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/134.0.0.0 Safari/537.36 Edg/134.0.0.0"
    },
)

live_img = "https://i.gyazo.com/978f2eb4a199ca5b56b447aded0cb9e3.png"

dummies = {
    "Basketball.Dummy.us": live_img,
    "Live.Event.us": live_img,
    "MLB.Baseball.Dummy.us": None,
    "MLS.Soccer.Dummy.us": None,
    "NBA.Basketball.Dummy.us": None,
    "NFL.Dummy.us": None,
    "NHL.Hockey.Dummy.us": None,
    "PPV.EVENTS.Dummy.us": live_img,
    "Premier.League.Dummy.us": None,
    "Racing.Dummy.us": None,
    "Soccer.Dummy.us": live_img,
    "Sports.Dummy.us": live_img,
    "Tennis.Dummy.us": None,
    "UEFA.Champions.League.Dummy.us": None,
    "UFC.Fight.Pass.Dummy.us": live_img,
    "WNBA.dummy.us": None,
}


async def fetch_xml(url: str) -> ET.Element:
    try:
        r = await client.get(url)
        r.raise_for_status()
    except Exception as e:
        raise SystemExit(f'Failed to fetch "{url}"\n{e}') from e

    try:
        decompressed_data = gzip.decompress(r.content)

        return ET.fromstring(decompressed_data)

    except Exception as e:
        raise SystemExit(f'Failed to decompress and parse XML from "{url}"\n{e}') from e


async def main() -> None:
    tvg_ids: dict[str, str] = json.loads(tvg_ids_file.read_text(encoding="utf-8"))

    tvg_ids |= dummies

    root = ET.Element("tv")

    tasks = [fetch_xml(url) for url in epg_urls]
    results = await asyncio.gather(*tasks)

    for epg_data in results:
        if epg_data is None:
            continue

        for channel in epg_data.findall("channel"):
            if (channel_id := channel.get("id")) in tvg_ids:
                for icon_tag in channel.findall("icon"):
                    if logo := tvg_ids.get(channel_id):
                        icon_tag.set("src", logo)

                if (url_tag := channel.find("url")) is not None:
                    channel.remove(url_tag)

                root.append(channel)

        for program in epg_data.findall("programme"):
            tvg_id = program.get("channel")

            if tvg_id in tvg_ids:
                if (title_text := program.find("title").text) in [
                    "NHL Hockey",
                    "Live: NFL Football",
                ] and (subtitle := program.find("sub-title")) is not None:

                    program.find("title").text = f"{title_text} {subtitle.text}"

                root.append(program)

    tree = ET.ElementTree(root)

    tree.write(epg_file, encoding="utf-8", xml_declaration=True)

    print(f"EPG saved to {epg_file.name}")


if __name__ == "__main__":
    asyncio.run(main())