update M3U8

M3U8/scrapers/pixel.py

@@ -49,10 +49,7 @@ async def get_events() -> dict[str, dict[str, str | float]]:
 
     events = {}
 
-    pattern = re.compile(
-        r"https?://[^\s'\"]+?\.m3u8(?:\?[^\s'\"]*)?",
-        re.IGNORECASE,
-    )
+    pattern = re.compile(r"https?://[^\s'\"]+?\.m3u8(?:\?[^\s'\"]*)?", re.IGNORECASE)
 
     for event in api_data.get("events", []):
         event_dt = Time.from_str(event["date"], timezone="UTC")

M3U8/scrapers/ppv.py

@@ -41,13 +41,7 @@ async def get_events(
     cached_keys: set[str],
 ) -> list[dict[str, str]]:
     if not (api_data := API_FILE.load(per_entry=False)):
-        api_data = await refresh_api_cache(
-            client,
-            urljoin(
-                BASE_URL,
-                "api/streams",
-            ),
-        )
+        api_data = await refresh_api_cache(client, urljoin(BASE_URL, "api/streams"))
 
         API_FILE.write(api_data)
 

M3U8/scrapers/roxie.py

@@ -18,7 +18,7 @@ HTML_CACHE = Cache("roxie-html.json", exp=19_800)
 
 BASE_URL = "https://roxiestreams.live"
 
-valid_sports = {
+SPORT_ENDPOINTS = {
     "fighting": "Fighting",
     "mlb": "MLB",
     "motorsports": "Racing",
@@ -90,7 +90,7 @@ async def refresh_html_cache(
 
         event_dt = Time.from_str(data_start, timezone="PST")
 
-        event_sport = valid_sports[sport]
+        event_sport = SPORT_ENDPOINTS[sport]
 
         key = f"[{event_sport}] {event} ({TAG})"
 
@@ -156,7 +156,7 @@ async def scrape(client: httpx.AsyncClient) -> None:
 
     log.info(f'Scraping from "{BASE_URL}"')
 
-    sport_urls = {sport: urljoin(BASE_URL, sport) for sport in valid_sports}
+    sport_urls = {sport: urljoin(BASE_URL, sport) for sport in SPORT_ENDPOINTS}
 
     events = await get_events(
         client,

M3U8/scrapers/sport9.py

@@ -71,17 +71,17 @@ async def get_events(
             team_1_node = card.css_first(".team1 .team-name")
             team_2_node = card.css_first(".team2 .team-name")
 
-            if team_1_node and not team_2_node:
-                event = team_1_node.text(strip=True)
-
-            elif team_2_node and not team_1_node:
-                event = team_2_node.text(strip=True)
-
-            elif team_1_node and team_2_node:
-                event = (
+            if team_1_node and team_2_node:
+                event = event = (
                     f"{team_1_node.text(strip=True)} vs {team_2_node.text(strip=True)}"
                 )
 
+            elif team_1_node:
+                event = team_1_node.text(strip=True)
+
+            elif team_2_node:
+                event = team_2_node.text(strip=True)
+
             else:
                 continue
 

M3U8/scrapers/streambtw.py

@@ -19,6 +19,12 @@ BASE_URL = "https://streambtw.com"
 TAG = "STRMBTW"
 
 
+def fix_league(s: str) -> str:
+    pattern = re.compile(r"^\w*-\w*", re.IGNORECASE)
+
+    return " ".join(s.split("-")) if pattern.search(s) else s
+
+
 async def process_event(
     client: httpx.AsyncClient,
     url: str,
@@ -62,13 +68,13 @@ async def get_events(client: httpx.AsyncClient) -> list[dict[str, str]]:
         if not (href := link.attrs.get("href")):
             continue
 
-        sport = card.css_first("h5.card-title").text(strip=True)
+        league = card.css_first("h5.card-title").text(strip=True)
 
         name = card.css_first("p.card-text").text(strip=True)
 
         events.append(
             {
-                "sport": sport,
+                "sport": fix_league(league),
                 "event": name,
                 "link": urljoin(BASE_URL, href),
             }

M3U8/scrapers/streamfree.py

@@ -35,19 +35,21 @@ async def get_events(client: httpx.AsyncClient) -> dict[str, dict[str, str | flo
 
     events = {}
 
-    for _, streams in api_data.get("streams", {}).items():
+    for streams in api_data.get("streams", {}).values():
         if not streams:
             continue
 
         for stream in streams:
             sport, name = stream["league"], stream["name"]
 
+            stream_key = stream["stream_key"]
+
             key = f"[{sport}] {name} ({TAG})"
 
             tvg_id, logo = leagues.get_tvg_info(sport, name)
 
             events[key] = {
-                "url": urljoin(BASE_URL, f"live/{stream['stream_key']}720p/index.m3u8"),
+                "url": urljoin(BASE_URL, f"live/{stream_key}720p/index.m3u8"),
                 "logo": logo,
                 "base": BASE_URL,
                 "timestamp": Time.now().timestamp(),

M3U8/scrapers/strmd.py

@@ -128,8 +128,7 @@ async def get_events(
 
     if not (api_data := API_FILE.load(per_entry=False, index=-1)):
         api_data = await refresh_api_cache(
-            client,
-            urljoin(url, "api/matches/all-today"),
+            client, urljoin(url, "api/matches/all-today")
         )
 
         API_FILE.write(api_data)
@@ -172,8 +171,8 @@ async def get_events(
         if not sources:
             continue
 
-        skip_sources = {"admin", "alpha", "bravo"}
-        valid_sources = [d for d in sources if d.get("source") not in skip_sources]
+        skip_types = {"admin", "alpha", "bravo"}
+        valid_sources = [d for d in sources if d.get("source") not in skip_types]
 
         if not valid_sources:
             continue

M3U8/scrapers/watchfooty.py

@@ -59,10 +59,7 @@ async def refresh_api_cache(
     log.info("Refreshing API cache")
 
     tasks = [
-        get_api_data(
-            client,
-            urljoin(url, f"api/v1/matches/{sport}"),
-        )
+        get_api_data(client, urljoin(url, f"api/v1/matches/{sport}"))
         for sport in SPORT_ENDPOINTS
     ]