e

M3U8/scrape/livetvsx.py

@@ -97,67 +97,6 @@ async def fetch_xml_stream(url: str, ssl_ctx: ssl.SSLContext) -> io.BytesIO:
         return io.BytesIO(b"")
 
 
-async def parse_feed(
-    url: str,
-    ssl_ctx: ssl.SSLContext,
-    cached_keys: set[str],
-) -> list[dict[str, str]]:
-
-    events: list[dict[str, str]] = []
-    pub_date_format = "%a, %d %b %Y %H:%M:%S %z"
-    now = datetime.now(TZ)
-
-    window_start, window_end = now - timedelta(hours=3), now + timedelta(hours=1)
-
-    buffer = await fetch_xml_stream(url, ssl_ctx)
-
-    for _, elem in ET.iterparse(buffer, events=("end",)):
-        if elem.tag == "item":
-            title = elem.findtext("title")
-            desc = elem.findtext("description")
-            pub_date = elem.findtext("pubDate")
-            link = elem.findtext("link")
-
-            try:
-                dt = datetime.strptime(pub_date, pub_date_format)
-                dt = dt.astimezone(TZ)
-            except Exception:
-                elem.clear()
-                continue
-
-            if window_start <= dt <= window_end:
-                sport, event = (
-                    (
-                        desc.split(".")[0].strip(),
-                        " ".join(p.strip() for p in desc.split(".")[1:]),
-                    )
-                    if desc
-                    else ("", "")
-                )
-
-                key = f"[{sport}: {event}] {title}"
-
-                if key in cached_keys:
-                    elem.clear()
-                    continue
-
-                if exist_sprts & {sport, event}:
-                    continue
-
-                events.append(
-                    {
-                        "sport": sport,
-                        "event": event,
-                        "title": title,
-                        "link": link,
-                    }
-                )
-
-            elem.clear()
-
-    return events
-
-
 async def process_event(url: str, url_num: int) -> str | None:
     async with async_playwright() as p:
         browser = await p.firefox.launch(headless=True)
@@ -176,10 +115,8 @@ 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()
 
         popup = None
@@ -284,6 +221,67 @@ async def process_event(url: str, url_num: int) -> str | None:
         await browser.close()
 
 
+async def get_events(
+    url: str,
+    ssl_ctx: ssl.SSLContext,
+    cached_keys: set[str],
+) -> list[dict[str, str]]:
+
+    events: list[dict[str, str]] = []
+    pub_date_format = "%a, %d %b %Y %H:%M:%S %z"
+    now = datetime.now(TZ)
+
+    window_start, window_end = now - timedelta(hours=3), now + timedelta(hours=1)
+
+    buffer = await fetch_xml_stream(url, ssl_ctx)
+
+    for _, elem in ET.iterparse(buffer, events=("end",)):
+        if elem.tag == "item":
+            title = elem.findtext("title")
+            desc = elem.findtext("description")
+            pub_date = elem.findtext("pubDate")
+            link = elem.findtext("link")
+
+            try:
+                dt = datetime.strptime(pub_date, pub_date_format)
+                dt = dt.astimezone(TZ)
+            except Exception:
+                elem.clear()
+                continue
+
+            if window_start <= dt <= window_end:
+                sport, event = (
+                    (
+                        desc.split(".")[0].strip(),
+                        " ".join(p.strip() for p in desc.split(".")[1:]),
+                    )
+                    if desc
+                    else ("", "")
+                )
+
+                key = f"[{sport}: {event}] {title}"
+
+                if key in cached_keys:
+                    elem.clear()
+                    continue
+
+                if exist_sprts & {sport, event}:
+                    continue
+
+                events.append(
+                    {
+                        "sport": sport,
+                        "event": event,
+                        "title": title,
+                        "link": link,
+                    }
+                )
+
+            elem.clear()
+
+    return events
+
+
 async def main(client: httpx.AsyncClient) -> None:
     log.info(f'Scraping from "{BASE_URL}"')
 
@@ -292,13 +290,13 @@ async def main(client: httpx.AsyncClient) -> None:
     cached_urls = load_cache()
     cached_count = len(cached_urls)
 
-    events = await parse_feed(BASE_URL, cert, set(cached_urls.keys()))
+    events = await get_events(BASE_URL, cert, set(cached_urls.keys()))
 
     log.info(f"Processing {len(events)} URLs")
 
     now_ts = datetime.now(TZ).timestamp()
 
-    for num, ev in enumerate(events, start=1):
+    for i, ev in enumerate(events, start=1):
         sport = ev["sport"]
         event = ev["event"]
         title = ev["title"]
@@ -307,8 +305,8 @@ async def main(client: httpx.AsyncClient) -> None:
         key = f"[{sport}: {event}] {title}"
 
         url = await safe_process_event(
-            lambda: process_event(link, url_num=num),
-            url_num=num,
+            lambda: process_event(link, url_num=i),
+            url_num=i,
             log=log,
         )
 
@@ -330,4 +328,4 @@ 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)")