e

M3U8/scrapers/strmd.py

@@ -1,3 +1,4 @@
+import asyncio
 import re
 from functools import partial
 from pathlib import Path
@@ -5,7 +6,7 @@ from typing import Any
 from urllib.parse import urljoin
 
 import httpx
-from playwright.async_api import async_playwright
+from playwright.async_api import BrowserContext, async_playwright
 
 from .utils import Cache, Time, get_logger, leagues, network
 
@@ -49,6 +50,69 @@ async def refresh_api_cache(
     return data
 
 
+async def process_event(
+    url: str,
+    url_num: int,
+    context: BrowserContext,
+    timeout: int | float = 10,
+) -> str | None:
+
+    page = await context.new_page()
+
+    captured: list[str] = []
+
+    got_one = asyncio.Event()
+
+    handler = partial(
+        network.capture_req,
+        captured=captured,
+        got_one=got_one,
+    )
+
+    page.on("request", handler)
+
+    try:
+        await page.goto(
+            url,
+            wait_until="domcontentloaded",
+            timeout=15_000,
+        )
+
+        wait_task = asyncio.create_task(got_one.wait())
+
+        try:
+            await page.click(".jw-icon-display")
+
+            await asyncio.wait_for(wait_task, timeout=timeout)
+        except asyncio.TimeoutError:
+            log.warning(f"URL {url_num}) Timed out waiting for M3U8.")
+            return
+
+        finally:
+            if not wait_task.done():
+                wait_task.cancel()
+
+                try:
+                    await wait_task
+                except asyncio.CancelledError:
+                    pass
+
+        if captured:
+            log.info(f"URL {url_num}) Captured M3U8")
+            return captured[0]
+
+        log.warning(f"URL {url_num}) No M3U8 captured after waiting.")
+        return
+
+    except Exception as e:
+        log.warning(f"URL {url_num}) Exception while processing: {e}")
+        return
+
+    finally:
+        page.remove_listener("request", handler)
+        await page.close()
+
+
 async def get_events(
     client: httpx.AsyncClient,
     base_url: str,
@@ -154,11 +218,10 @@ async def scrape(client: httpx.AsyncClient) -> None:
 
             for i, ev in enumerate(events, start=1):
                 handler = partial(
-                    network.process_event,
+                    process_event,
                     url=ev["link"],
                     url_num=i,
                     context=context,
-                    log=log,
                 )
 
                 url = await network.safe_process(