e

M3U8/scrape/ppv.py

@@ -71,7 +71,6 @@ async def process_event(url: str, url_num: int) -> str | None:
                 ".m3u8" in req.url
                 and "amazonaws" not in req.url
                 and "knitcdn" not in req.url
-                and not captured
             ):
                 captured.append(req.url)
                 got_one.set()
@@ -119,12 +118,15 @@ async def process_event(url: str, url_num: int) -> str | None:
 async def get_events(
     client: httpx.AsyncClient,
     api_url: str,
-    cached_keys: list[str],
+    cached_keys: set[str],
 ) -> dict[str, dict[str, str | str]]:
-    events = []
+
+    events: list[dict[str, str]] = []
 
     base_url = re.match(r"(https?://.+?)/", api_url)[1]
 
+    now = datetime.now(TZ)
+
     if not (api_data := load_api_cache()):
         api_data = await refresh_api_cache(client, api_url)
         API_FILE.write_text(json.dumps(api_data, indent=2), encoding="utf-8")
@@ -156,7 +158,7 @@ async def get_events(
 
             end_dt = datetime.fromtimestamp(end_ts, tz=TZ)
 
-            if not start_dt <= datetime.now(TZ) < end_dt:
+            if not start_dt <= now < end_dt:
                 continue
 
             events.append(
@@ -189,10 +191,10 @@ async def main(client: httpx.AsyncClient) -> None:
 
     log.info(f"Processing {len(events)} URLs")
 
-    for num, ev in enumerate(events, start=1):
+    for i, ev in enumerate(events, start=1):
         url = await safe_process_event(
-            lambda: process_event(ev["link"], url_num=num),
-            url_num=num,
+            lambda: process_event(ev["link"], url_num=i),
+            url_num=i,
             log=log,
         )
 
@@ -212,7 +214,7 @@ async def main(client: httpx.AsyncClient) -> None:
 
     log.info(f"Cached {cached_count} event(s)")
 
-    log.info(f"Collected {new_count} event(s)")
+    log.info(f"Collected {new_count} new event(s)")
 
 
 # works if no cloudflare bot detection