e

M3U8/scrapers/pixel.py

@@ -1,8 +1,9 @@
+import json
 import re
 
-import httpx
+from playwright.async_api import async_playwright
 
-from .utils import Cache, Time, get_logger, leagues
+from .utils import Cache, Time, get_logger, leagues, network
 
 log = get_logger(__name__)
 
@@ -16,36 +17,45 @@ BASE_URL = "https://pixelsport.tv/backend/livetv/events"
 
 
 async def refresh_api_cache(
-    client: httpx.AsyncClient,
     url: str,
     ts: float,
 ) -> dict[str, list[dict, str, str]]:
     log.info("Refreshing API cache")
 
-    try:
-        r = await client.get(url)
-        r.raise_for_status()
-    except Exception as e:
-        log.error(f'Failed to fetch "{url}": {e}')
+    async with async_playwright() as p:
+        try:
+            browser, context = await network.browser(p)
 
-        return {}
+            page = await context.new_page()
 
-    data = r.json()
+            await page.goto(
+                url,
+                wait_until="domcontentloaded",
+                timeout=10_000,
+            )
+
+            raw_json = await page.locator("pre").inner_text()
+
+        except Exception as e:
+            log.error(f'Failed to fetch "{url}": {e}')
+
+            return {}
+
+        finally:
+            await browser.close()
+
+    data = json.loads(raw_json)
 
     data["timestamp"] = ts
 
     return data
 
 
-async def get_events(
-    client: httpx.AsyncClient,
-    cached_keys: set[str],
-) -> dict[str, str | float]:
+async def get_events(cached_keys: set[str]) -> dict[str, str | float]:
     now = Time.clean(Time.now())
 
     if not (api_data := API_FILE.load(per_entry=False)):
         api_data = await refresh_api_cache(
-            client,
             BASE_URL,
             now.timestamp(),
         )
@@ -100,7 +110,7 @@ async def get_events(
     return events
 
 
-async def scrape(client: httpx.AsyncClient) -> None:
+async def scrape() -> None:
     cached_urls = CACHE_FILE.load()
     cached_count = len(cached_urls)
     urls.update(cached_urls)
@@ -109,7 +119,7 @@ async def scrape(client: httpx.AsyncClient) -> None:
 
     log.info(f'Scraping from "{BASE_URL}"')
 
-    events = await get_events(client, set(cached_urls.keys()))
+    events = await get_events(set(cached_urls.keys()))
 
     if events:
         for d in (urls, cached_urls):