iptv/M3U8/scrape/tvpass.py
2025-09-04 19:53:27 -04:00

72 lines
2.2 KiB
Python

import json
import re
from pathlib import Path
import httpx
from .utils import LOGOS, get_logger, now
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"
def load_cache() -> dict[str, str]:
try:
data = json.loads(CACHE_FILE.read_text(encoding="utf-8"))
return {} if now.hour <= 12 else data
except (FileNotFoundError, json.JSONDecodeError):
return {}
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 main(client: httpx.AsyncClient) -> None:
if cached := load_cache():
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_id = tvg_id_match[1] if tvg_id_match else None
tvg_name = tvg_name_match[1] if tvg_name_match else None
sport = group_title_match[1].upper().strip() if group_title_match else None
if tvg_id == "":
url = data[i + 1]
if tvg_name:
tvg_name = "(".join(tvg_name.split("(")[:-1]).strip()
if url.endswith("/hd"):
urls[f"[{sport}] {tvg_name}"] = {
"url": f"http://origin.thetvapp.to/hls/{url.split('/')[-2]}/mono.m3u8",
"logo": LOGOS.get(
sport,
"https://i.gyazo.com/ec27417a9644ae517196494afa72d2b9.png",
),
}
CACHE_FILE.write_text(json.dumps(urls, indent=2), encoding="utf-8")
log.info(f"Cached {len(urls)} event(s)")