e

M3U8/fetch.py

@@ -9,6 +9,7 @@ from scrapers import (
     ppv,
     roxie,
     shark,
+    sport9,
     streambtw,
     streameast,
     streamfree,
@@ -48,6 +49,7 @@ async def main() -> None:
         asyncio.create_task(ppv.scrape(network.client)),
         asyncio.create_task(roxie.scrape(network.client)),
         asyncio.create_task(shark.scrape(network.client)),
+        asyncio.create_task(sport9.scrape(network.client)),
         asyncio.create_task(streambtw.scrape(network.client)),
         asyncio.create_task(streameast.scrape(network.client)),
         asyncio.create_task(streamfree.scrape(network.client)),
@@ -64,6 +66,7 @@ async def main() -> None:
         | ppv.urls
         | roxie.urls
         | shark.urls
+        | sport9.urls
         | streambtw.urls
         | streameast.urls
         | strmd.urls

M3U8/scrapers/sport9.py

@@ -0,0 +1,132 @@
+from functools import partial
+from urllib.parse import urljoin
+
+import httpx
+from playwright.async_api import async_playwright
+from selectolax.parser import HTMLParser
+
+from .utils import Cache, Time, get_logger, leagues, network
+
+log = get_logger(__name__)
+
+urls: dict[str, dict[str, str | float]] = {}
+
+CACHE_FILE = Cache("sport9.json", exp=3_600)
+
+BASE_URL = "https://sport9.ru"
+
+
+async def get_events(
+    client: httpx.AsyncClient,
+    cached_keys: set[str],
+) -> list[dict[str, str]]:
+    try:
+        r = await client.get(BASE_URL)
+        r.raise_for_status()
+    except Exception as e:
+        log.error(f'Failed to fetch "{BASE_URL}": {e}')
+
+        return []
+
+    soup = HTMLParser(r.text)
+
+    events = []
+
+    for card in soup.css("a.match-card"):
+        live_badge = card.css_first(".live-badge")
+
+        if not live_badge or live_badge.text(strip=True) != "Live":
+            continue
+
+        if not (sport_node := card.css_first(".tournament-name")):
+            continue
+
+        team_1_node = card.css_first(".teams-container2 .team1")
+        team_2_node = card.css_first(".teams-container2 .team2")
+
+        if not (team_1_node and team_2_node):
+            continue
+
+        if not (href := card.attributes.get("href")):
+            continue
+
+        sport = sport_node.text(strip=True)
+        team_1 = team_1_node.text(strip=True)
+        team_2 = team_2_node.text(strip=True)
+
+        key = f"[{sport}] {team_1} vs {team_2} (SPRT9)"
+
+        if cached_keys & {key}:
+            continue
+
+        events.append(
+            {
+                "sport": sport,
+                "event": f"{team_1} vs {team_2}",
+                "link": urljoin(BASE_URL, href),
+            }
+        )
+
+    return events
+
+
+async def scrape(client: httpx.AsyncClient) -> None:
+    cached_urls = CACHE_FILE.load()
+    cached_count = len(cached_urls)
+    urls.update(cached_urls)
+
+    log.info(f"Loaded {cached_count} event(s) from cache")
+
+    log.info(f'Scraping from "{BASE_URL}"')
+
+    events = await get_events(client, set(cached_urls.keys()))
+
+    log.info(f"Processing {len(events)} new URL(s)")
+
+    if events:
+        now = Time.now().timestamp()
+
+        async with async_playwright() as p:
+            browser, context = await network.browser(p, browser="brave")
+
+            for i, ev in enumerate(events, start=1):
+                handler = partial(
+                    network.process_event,
+                    client=client,
+                    url=ev["link"],
+                    url_num=i,
+                    context=context,
+                    log=log,
+                )
+
+                url = await network.safe_process(
+                    handler,
+                    url_num=i,
+                    log=log,
+                )
+
+                if url:
+                    sport, event = ev["sport"], ev["event"]
+
+                    key = f"[{sport}] {event} (SPRT9)"
+
+                    tvg_id, logo = leagues.get_tvg_info(sport, event)
+
+                    entry = {
+                        "url": url,
+                        "logo": logo,
+                        "base": "https://vividmosaica.com/",
+                        "timestamp": now,
+                        "id": tvg_id or "Live.Event.us",
+                    }
+
+                    urls[key] = cached_urls[key] = entry
+
+            await browser.close()
+
+    if new_count := len(cached_urls) - cached_count:
+        log.info(f"Collected and cached {new_count} new event(s)")
+    else:
+        log.info("No new events found")
+
+    CACHE_FILE.write(cached_urls)