This commit is contained in:
doms9 2025-10-01 11:57:49 -04:00
parent 7103b0f1c4
commit 00000d9937
17 changed files with 597 additions and 524 deletions

View file

@ -5,7 +5,7 @@ from urllib.parse import urljoin
import httpx
from selectolax.parser import HTMLParser
from .utils import get_logger, leagues, load_cache, now, safe_process_event, write_cache
from .utils import Cache, Time, get_logger, leagues, network
log = get_logger(__name__)
@ -13,7 +13,7 @@ urls: dict[str, dict[str, str]] = {}
BASE_URL = "https://streambtw.com/"
CACHE_FILE = Path(__file__).parent / "caches" / "streambtw.json"
CACHE_FILE = Cache(Path(__file__).parent / "caches" / "streambtw.json", exp=86_400)
async def process_event(
@ -45,7 +45,7 @@ async def get_events(client: httpx.AsyncClient) -> list[dict[str, str]]:
r = await client.get(BASE_URL)
r.raise_for_status()
except Exception as e:
log.error(f'Failed to fetch "{BASE_URL}"\n{e}')
log.error(f'Failed to fetch "{BASE_URL}": {e}')
return []
@ -60,22 +60,24 @@ async def get_events(client: httpx.AsyncClient) -> list[dict[str, str]]:
link = card.css_first("a.btn.btn-primary")
if href := link.attrs.get("href"):
events.append(
{
"sport": sport,
"event": name,
"link": urljoin(BASE_URL, href),
}
)
if not (href := link.attrs.get("href")):
continue
events.append(
{
"sport": sport,
"event": name,
"link": urljoin(BASE_URL, href),
}
)
return events
async def scrape(client: httpx.AsyncClient) -> None:
if cached := load_cache(CACHE_FILE, exp=86_400, nearest_hr=True):
if cached := CACHE_FILE.load():
urls.update(cached)
log.info(f"Collected {len(urls)} event(s) from cache")
log.info(f"Loaded {len(urls)} event(s) from cache")
return
log.info(f'Scraping from "{BASE_URL}"')
@ -85,10 +87,11 @@ async def scrape(client: httpx.AsyncClient) -> None:
log.info(f"Processing {len(events)} new URL(s)")
for i, ev in enumerate(events, start=1):
url = await safe_process_event(
url = await network.safe_process(
lambda: process_event(client, url=ev["link"], url_num=i),
url_num=i,
log=log,
timeout=10,
)
if url:
@ -102,12 +105,12 @@ async def scrape(client: httpx.AsyncClient) -> None:
"url": url,
"logo": logo,
"base": BASE_URL,
"timestamp": now.timestamp(),
"id": tvg_id,
"timestamp": Time.now().timestamp(),
"id": tvg_id or "Live.Event.us",
}
urls[key] = entry
log.info(f"Collected {len(urls)} event(s)")
write_cache(CACHE_FILE, urls)
CACHE_FILE.write(urls)