e

M3U8/scrapers/roxie.py

@@ -1,10 +1,10 @@
 import asyncio
+import re
 from functools import partial
 from pathlib import Path
 from urllib.parse import urljoin
 
 import httpx
-from playwright.async_api import async_playwright
 from selectolax.parser import HTMLParser
 
 from .utils import Cache, Time, get_logger, leagues, network
@@ -25,6 +25,31 @@ CACHE_FILE = Cache(Path(__file__).parent / "caches" / "roxie.json", exp=10_800)
 HTML_CACHE = Cache(Path(__file__).parent / "caches" / "roxie_html.json", exp=28_800)
 
 
+async def process_event(
+    client: httpx.AsyncClient,
+    url: str,
+    url_num: int,
+) -> str | None:
+
+    try:
+        r = await client.get(url)
+        r.raise_for_status()
+    except Exception as e:
+        log.error(f'URL {url_num}) Failed to fetch "{url}": {e}')
+        return
+
+    valid_m3u8 = re.compile(
+        r"showPlayer\(['\"]clappr['\"],\s*['\"]([^'\"]+?\.m3u8(?:\?[^'\"]*)?)['\"]\)",
+        re.IGNORECASE,
+    )
+
+    if match := valid_m3u8.search(r.text):
+        log.info(f"URL {url_num}) Captured M3U8")
+        return match[1]
+
+    log.info(f"URL {url_num}) No M3U8 found")
+
+
 async def refresh_html_cache(
     client: httpx.AsyncClient,
     url: str,
@@ -135,43 +160,36 @@ async def scrape(client: httpx.AsyncClient) -> None:
     log.info(f"Processing {len(events)} new URL(s)")
 
     if events:
-        async with async_playwright() as p:
+        for i, ev in enumerate(events, start=1):
-            browser, context = await network.browser(p)
+            handler = partial(
+                process_event,
+                client=client,
+                url=ev["link"],
+                url_num=i,
+            )
 
-            for i, ev in enumerate(events, start=1):
+            url = await network.safe_process(
-                handler = partial(
+                handler,
-                    network.process_event,
+                url_num=i,
-                    url=ev["link"],
+                log=log,
-                    url_num=i,
+            )
-                    context=context,
-                    timeout=15,
-                    log=log,
-                )
 
-                url = await network.safe_process(
+            if url:
-                    handler,
+                sport, event, ts = ev["sport"], ev["event"], ev["event_ts"]
-                    url_num=i,
-                    log=log,
-                )
 
-                if url:
+                tvg_id, logo = leagues.info(sport)
-                    sport, event, ts = ev["sport"], ev["event"], ev["event_ts"]
 
-                    tvg_id, logo = leagues.info(sport)
+                key = f"[{sport}] {event} (ROXIE)"
 
-                    key = f"[{sport}] {event} (ROXIE)"
+                entry = {
+                    "url": url,
+                    "logo": logo,
+                    "base": "",
+                    "timestamp": ts,
+                    "id": tvg_id or "Live.Event.us",
+                }
 
-                    entry = {
+                urls[key] = cached_urls[key] = entry
-                        "url": url,
-                        "logo": logo,
-                        "base": "",
-                        "timestamp": ts,
-                        "id": tvg_id or "Live.Event.us",
-                    }
-
-                    urls[key] = cached_urls[key] = entry
-
-            await browser.close()
 
     if new_count := len(cached_urls) - cached_count:
         log.info(f"Collected and cached {new_count} new event(s)")

M3U8/scrapers/streameast.py

@@ -124,10 +124,7 @@ async def scrape(client: httpx.AsyncClient) -> None:
 
     if events:
         async with async_playwright() as p:
-            try:
+            browser, context = await network.browser(p, browser="brave")
-                browser, context = await network.browser(p, browser="brave")
-            except Exception:
-                browser, context = await network.browser(p)
 
             for i, ev in enumerate(events, start=1):
                 handler = partial(

M3U8/scrapers/strmd.py

@@ -150,7 +150,7 @@ async def scrape(client: httpx.AsyncClient) -> None:
 
     if events:
         async with async_playwright() as p:
-            browser, context = await network.browser(p, "brave")
+            browser, context = await network.browser(p, browser="brave")
 
             for i, ev in enumerate(events, start=1):
                 handler = partial(