e

M3U8/scrape/utils/config.py

@@ -1,11 +1,14 @@
 import asyncio
+import json
 import logging
+import re
 from datetime import datetime
 from pathlib import Path
 from typing import Any
 
 import httpx
 import pytz
+from playwright.async_api import Request
 
 TZ = pytz.timezone("America/New_York")
 
@@ -65,6 +68,24 @@ def get_logger(name: str | None = None) -> logging.Logger:
     return logger
 
 
+def load_ts_cache(
+    file: Path,
+    cache_exp: int | float,
+) -> dict[str, dict[str, str | float]]:
+    try:
+        data: dict[str, dict[str, str | float]] = json.loads(
+            file.read_text(encoding="utf-8")
+        )
+
+        return {
+            k: v
+            for k, v in data.items()
+            if now.timestamp() - v.get("timestamp", 0) < cache_exp
+        }
+    except (FileNotFoundError, json.JSONDecodeError):
+        return {}
+
+
 async def safe_process_event(
     fn,
     url_num: int,
@@ -107,3 +128,15 @@ async def get_base(client: httpx.AsyncClient, mirrors: list[str]) -> str:
     results = await asyncio.gather(*tasks)
 
     return [url for url, ok in zip(mirrors, results) if ok][0]
+
+
+def capture_req(
+    req: Request,
+    captured: list[str],
+    got_one: asyncio.Event,
+) -> None:
+    valid_m3u8 = re.compile(r"^(?!.*(amazonaws|knitcdn)).*\.m3u8")
+
+    if valid_m3u8.search(req.url):
+        captured.append(req.url)
+        got_one.set()