diff --git a/M3U8/scrapers/ovogoal.py b/M3U8/scrapers/ovogoal.py index 71b2e3ea..fae771b1 100644 --- a/M3U8/scrapers/ovogoal.py +++ b/M3U8/scrapers/ovogoal.py @@ -11,9 +11,7 @@ urls: dict[str, dict[str, str | float]] = {} TAG = "OVOGOAL" -CACHE_FILE = Cache(TAG, exp=10_800) - -HTML_CACHE = Cache(f"{TAG}-html", exp=19_800) +CACHE_FILE = Cache(TAG, exp=19_800) BASE_URL = "https://ovogoal.plus" @@ -48,27 +46,22 @@ async def process_event(url: str, url_num: int) -> tuple[str | None, str | None] return match[3], iframe_src -async def refresh_html_cache() -> dict[str, dict[str, str | float]]: - log.info("Refreshing HTML cache") - - now = Time.clean(Time.now()) - - events = {} +async def get_events(cached_keys: list[str]) -> list[dict[str, str]]: + events = [] if not (html_data := await network.request(BASE_URL, log=log)): return events soup = HTMLParser(html_data.content) + sport = "Live Event" + for card in soup.css(".stream-row"): if (not (watch_btn_elem := card.css_first(".watch-btn"))) or ( not (onclick := watch_btn_elem.attributes.get("onclick")) ): continue - if not (event_time_elem := card.css_first(".stream-time")): - continue - if not (event_name_elem := card.css_first(".stream-info")): continue @@ -76,50 +69,20 @@ async def refresh_html_cache() -> dict[str, dict[str, str | float]]: event_name = event_name_elem.text(strip=True) - event_time = event_time_elem.text(strip=True) + if f"[{sport}] {event_name} ({TAG})" in cached_keys: + continue - event_dt = Time.from_str(f"{now.date()} {event_time}", timezone="CET") - - sport = "Live Event" - - key = f"[{sport}] {event_name} ({TAG})" - - events[key] = { - "sport": sport, - "event": event_name, - "link": href, - "event_ts": event_dt.timestamp(), - "timestamp": now.timestamp(), - } + events.append( + { + "sport": sport, + "event": event_name, + "link": href, + } + ) return events -async def get_events(cached_keys: list[str]) -> list[dict[str, str]]: - now = Time.clean(Time.now()) - - if not (events := HTML_CACHE.load()): - events = await refresh_html_cache() - - HTML_CACHE.write(events) - - live = [] - - start_ts = now.delta(minutes=-30).timestamp() - end_ts = now.delta(minutes=30).timestamp() - - for k, v in events.items(): - if k in cached_keys: - continue - - if not start_ts <= v["event_ts"] <= end_ts: - continue - - live.append(v) - - return live - - async def scrape() -> None: cached_urls = CACHE_FILE.load() @@ -138,6 +101,8 @@ async def scrape() -> None: if events: log.info(f"Processing {len(events)} new URL(s)") + now = Time.clean(Time.now()) + for i, ev in enumerate(events, start=1): handler = partial( process_event, @@ -152,11 +117,7 @@ async def scrape() -> None: log=log, ) - sport, event, ts = ( - ev["sport"], - ev["event"], - ev["event_ts"], - ) + sport, event = ev["sport"], ev["event"] key = f"[{sport}] {event} ({TAG})" @@ -166,7 +127,7 @@ async def scrape() -> None: "url": url, "logo": logo, "base": iframe, - "timestamp": ts, + "timestamp": now.timestamp(), "id": tvg_id or "Live.Event.us", "link": link, } diff --git a/M3U8/scrapers/pawa.py b/M3U8/scrapers/pawa.py index d81b4b6b..47fbb601 100644 --- a/M3U8/scrapers/pawa.py +++ b/M3U8/scrapers/pawa.py @@ -61,6 +61,8 @@ async def get_events(cached_keys: list[str]) -> list[dict[str, str]]: feed = feedparser.parse(html_data.content) + sport = "Live Event" + for entry in feed.entries: if not (link := entry.get("link")): continue @@ -68,8 +70,6 @@ async def get_events(cached_keys: list[str]) -> list[dict[str, str]]: if not (title := entry.get("title")): continue - sport = "Live Event" - title = title.replace(" v ", " vs ") if f"[{sport}] {title} ({TAG})" in cached_keys: