e

M3U8/fetch.py

@@ -9,12 +9,12 @@ from scrapers import (
     ppv,
     roxie,
     shark,
-    sport9,
     streambtw,
     streameast,
     streamfree,
     strmd,
     tvpass,
+    vuen,
     watchfooty,
 )
 from scrapers.utils import get_logger, network
@@ -49,12 +49,12 @@ 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)),
         asyncio.create_task(strmd.scrape(network.client)),
         asyncio.create_task(tvpass.scrape(network.client)),
+        asyncio.create_task(vuen.scrape(network.client)),
         asyncio.create_task(watchfooty.scrape(network.client)),
     ]
 
@@ -66,12 +66,12 @@ async def main() -> None:
         | ppv.urls
         | roxie.urls
         | shark.urls
-        | sport9.urls
         | streambtw.urls
         | streameast.urls
         | strmd.urls
         | streamfree.urls
         | tvpass.urls
+        | vuen.urls
         | watchfooty.urls
     )
 

M3U8/scrapers/strmd.py

@@ -144,7 +144,7 @@ async def get_events(
         if not (ts := event["date"]):
             continue
 
-        start_ts = int(str(ts)[:-3])
+        start_ts = int(f"{ts}"[:-3])
 
         event_dt = Time.from_ts(start_ts)
 

M3U8/scrapers/vuen.py

@@ -1,3 +1,5 @@
+import json
+import re
 from functools import partial
 from urllib.parse import urljoin
 
@@ -11,50 +13,104 @@ log = get_logger(__name__)
 
 urls: dict[str, dict[str, str | float]] = {}
 
-CACHE_FILE = Cache("sport9.json", exp=3_600)
+CACHE_FILE = Cache("vuen.json", exp=3_600)
 
-BASE_URL = "https://sport9.ru"
+API_FILE = Cache("vuen-html.json", exp=28_800)
+
+BASE_URL = "https://vuen.link"
+
+
+async def refresh_api_cache(
+    client: httpx.AsyncClient,
+    url: str,
+) -> dict[str, list[dict]]:
+    now = Time.now()
+
+    log.info("Refreshing API cache")
+
+    data = {}
+
+    try:
+        r = await client.get(url)
+        r.raise_for_status()
+    except Exception as e:
+        log.error(f'Failed to fetch "{url}": {e}')
+
+        return data
+
+    soup = HTMLParser(r.text)
+
+    for script in soup.css("script"):
+        if not script:
+            continue
+
+        content = script.text(strip=True)
+
+        if not (
+            match := re.search(
+                r"window\.matches\s*=\s*JSON\.parse\(`(.*?)`\)",
+                content,
+                re.DOTALL,
+            )
+        ):
+            continue
+
+        data["matches"] = json.loads(match[1])
+
+        data["timestamp"] = now.timestamp()
+
+        break
+
+    return data
 
 
 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}')
+    if not (api_data := API_FILE.load(per_entry=False)):
+        api_data = await refresh_api_cache(client, BASE_URL)
 
-        return []
-
-    soup = HTMLParser(r.text)
+        API_FILE.write(api_data)
 
     events = []
 
-    for card in soup.css("a.match-card"):
-        live_badge = card.css_first(".live-badge")
+    now = Time.clean(Time.now())
+    start_dt = now.delta(minutes=-30)
+    end_dt = now.delta(minutes=30)
 
-        if not live_badge or live_badge.text(strip=True) != "Live":
+    for match in api_data.get("matches", []):
+        if not (ts := match.get("startTimestamp")):
             continue
 
-        if not (sport_node := card.css_first(".tournament-name")):
+        start_ts = int(f"{ts}"[:-3])
+
+        event_dt = Time.from_ts(start_ts)
+
+        if not start_dt <= event_dt <= end_dt:
             continue
 
-        team_1_node = card.css_first(".teams-container2 .team1")
-        team_2_node = card.css_first(".teams-container2 .team2")
+        event_name = match["matchstr"]
 
-        if not (team_1_node and team_2_node):
+        sport = match["league"]
+
+        channels: list[dict[str, str | list[str]]] = match.get("channels", [])
+
+        event_link = None
+
+        if not channels:
+            event_link = urljoin(BASE_URL, match["slug"])
+
+        for channel in channels:
+            event_link = (channel.get("oldLinks") or channel.get("links") or [None])[0]
+
+            if event_link:
+                break
+
+        if not event_link:
             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)"
+        key = f"[{sport}] {event_name} (VUEN)"
 
         if cached_keys & {key}:
             continue
@@ -62,8 +118,9 @@ async def get_events(
         events.append(
             {
                 "sport": sport,
-                "event": f"{team_1} vs {team_2}",
-                "link": urljoin(BASE_URL, href),
+                "event": event_name,
+                "link": event_link,
+                "timestamp": now.timestamp(),
             }
         )
 
@@ -84,10 +141,8 @@ async def scrape(client: httpx.AsyncClient) -> None:
     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")
+            browser, context = await network.browser(p)
 
             for i, ev in enumerate(events, start=1):
                 handler = partial(
@@ -105,9 +160,13 @@ async def scrape(client: httpx.AsyncClient) -> None:
                 )
 
                 if url:
-                    sport, event = ev["sport"], ev["event"]
+                    sport, event, ts = (
+                        ev["sport"],
+                        ev["event"],
+                        ev["timestamp"],
+                    )
 
-                    key = f"[{sport}] {event} (SPRT9)"
+                    key = f"[{sport}] {event} (VUEN)"
 
                     tvg_id, logo = leagues.get_tvg_info(sport, event)
 
@@ -115,7 +174,7 @@ async def scrape(client: httpx.AsyncClient) -> None:
                         "url": url,
                         "logo": logo,
                         "base": "https://vividmosaica.com/",
-                        "timestamp": now,
+                        "timestamp": ts,
                         "id": tvg_id or "Live.Event.us",
                     }
 

M3U8/scrapers/watchfooty.py

@@ -183,7 +183,7 @@ async def get_events(
         if not (ts := event.get("ts")):
             continue
 
-        start_ts = int(str(ts)[:-3])
+        start_ts = int(f"{ts}"[:-3])
 
         event_dt = Time.from_ts(start_ts)