e

M3U8/scrapers/ppv.py

@@ -1,8 +1,4 @@
-#!/usr/bin/env python3
-
 import asyncio
-import json
-import re
 from datetime import datetime, timedelta
 from functools import partial
 from pathlib import Path
@@ -40,6 +36,50 @@ MIRRORS = [
     "https://freeppv.fun",
 ]
 
+NFL_TEAMS = {
+    "Arizona Cardinals",
+    "Atlanta Falcons",
+    "Baltimore Ravens",
+    "Buffalo Bills",
+    "Carolina Panthers",
+    "Chicago Bears",
+    "Cincinnati Bengals",
+    "Cleveland Browns",
+    "Dallas Cowboys",
+    "Denver Broncos",
+    "Detroit Lions",
+    "Green Bay Packers",
+    "Houston Texans",
+    "Indianapolis Colts",
+    "Jacksonville Jaguars",
+    "Kansas City Chiefs",
+    "Las Vegas Raiders",
+    "Los Angeles Chargers",
+    "Los Angeles Rams",
+    "Miami Dolphins",
+    "Minnesota Vikings",
+    "New England Patriots",
+    "New Orleans Saints",
+    "New York Giants",
+    "New York Jets",
+    "Philadelphia Eagles",
+    "Pittsburgh Steelers",
+    "San Francisco 49ers",
+    "Seattle Seahawks",
+    "Tampa Bay Buccaneers",
+    "Tennessee Titans",
+    "Washington Redskins",
+}
+
+
+def is_nfl(event: str) -> bool:
+    try:
+        t1, t2 = event.split(" vs. ")
+
+        return t1 in NFL_TEAMS or t2 in NFL_TEAMS
+    except ValueError:
+        return False
+
 
 async def refresh_api_cache(
     client: httpx.AsyncClient, url: str
@@ -110,14 +150,12 @@ async def process_event(url: str, url_num: int) -> str | None:
 
 async def get_events(
     client: httpx.AsyncClient,
-    api_url: str,
+    base_url: str,
     cached_keys: set[str],
 ) -> list[dict[str, str]]:
 
     events: list[dict[str, str]] = []
 
-    base_url = re.match(r"(https?://.+?)/", api_url)[1]
-
     if not (
         api_data := load_cache(
             API_FILE,
@@ -126,8 +164,9 @@ async def get_events(
             per_entry=False,
         )
     ):
-        api_data = await refresh_api_cache(client, api_url)
-        API_FILE.write_text(json.dumps(api_data, indent=2), encoding="utf-8")
+        api_data = await refresh_api_cache(client, urljoin(base_url, "api/streams"))
+
+        write_cache(API_FILE, api_data)
 
     for stream_group in api_data["streams"]:
         sport = stream_group["category"]
@@ -168,8 +207,8 @@ async def get_events(
     return events
 
 
-async def main(client: httpx.AsyncClient) -> None:
-    cached_urls = load_cache(CACHE_FILE, exp=10800)
+async def scrape(client: httpx.AsyncClient) -> None:
+    cached_urls = load_cache(CACHE_FILE, exp=10_800)
     cached_count = len(cached_urls)
     urls.update(cached_urls)
 
@@ -184,7 +223,7 @@ async def main(client: httpx.AsyncClient) -> None:
 
     events = await get_events(
         client,
-        urljoin(base_url, "api/streams"),
+        base_url,
         set(cached_urls.keys()),
     )
 
@@ -200,6 +239,11 @@ async def main(client: httpx.AsyncClient) -> None:
         if url:
             sport, event = ev["sport"], ev["event"]
 
+            if sport == "American Football":
+                tvg_id = "NFL.Dummy.us" if is_nfl(event) else "NCAA.Sports.Dummy.us"
+            else:
+                tvg_id = league_info(sport)[0]
+
             key = f"[{sport}] {event} (PPV)"
 
             entry = {
@@ -207,7 +251,7 @@ async def main(client: httpx.AsyncClient) -> None:
                 "logo": ev["logo"],
                 "base": base_url,
                 "timestamp": now.timestamp(),
-                "id": league_info(sport)["id"],
+                "id": tvg_id or "Live.Event.us",
             }
 
             urls[key] = cached_urls[key] = entry