iptv/M3U8/scrapers/tvpass.py

import re
from pathlib import Path

import httpx

from .utils import get_logger, leagues, load_cache, now, write_cache

log = get_logger(__name__)

urls: dict[str, dict[str, str]] = {}

BASE_URL = "https://tvpass.org/playlist/m3u"

CACHE_FILE = Path(__file__).parent / "caches" / "tvpass.json"


async def fetch_m3u8(client: httpx.AsyncClient) -> list[str]:
    try:
        r = await client.get(BASE_URL)
        r.raise_for_status()
    except Exception as e:
        log.error(f'Failed to fetch "{BASE_URL}"\n{e}')
        return []

    return r.text.splitlines()


async def scrape(client: httpx.AsyncClient) -> None:
    if cached := load_cache(CACHE_FILE, exp=86_400, nearest_hr=True):
        urls.update(cached)
        log.info(f"Collected {len(urls)} event(s) from cache")
        return

    log.info(f'Scraping from "{BASE_URL}"')

    for i, line in enumerate(data := await fetch_m3u8(client)):
        if line.startswith("#EXTINF"):
            tvg_id_match = re.search(r'tvg-id="([^"]*)"', line)
            tvg_name_match = re.search(r'tvg-name="([^"]*)"', line)
            group_title_match = re.search(r'group-title="([^"]*)"', line)

            tvg = tvg_id_match[1] if tvg_id_match else None

            if not tvg and (url := data[i + 1]).endswith("/hd"):
                if tvg_name := tvg_name_match[1]:
                    sport = group_title_match[1].upper().strip()

                    event = "(".join(tvg_name.split("(")[:-1]).strip()

                    key = f"[{sport}] {event} (TVP)"

                    channel = url.split("/")[-2]

                    tvg_id, logo = leagues.info(sport)

                    entry = {
                        "url": f"http://origin.thetvapp.to/hls/{channel}/mono.m3u8",
                        "logo": logo,
                        "id": tvg_id,
                        "base": "https://tvpass.org",
                        "timestamp": now.timestamp(),
                    }

                    urls[key] = entry

    write_cache(CACHE_FILE, urls)

    log.info(f"Cached {len(urls)} event(s)")