e

M3U8/scrapers/streameast.py

@@ -1,5 +1,4 @@
 import asyncio
-from datetime import datetime, timedelta
 from functools import partial
 from pathlib import Path
 from urllib.parse import urljoin
@@ -8,24 +7,13 @@ import httpx
 from playwright.async_api import async_playwright
 from selectolax.parser import HTMLParser
 
-from .utils import (
-    TZ,
-    capture_req,
-    get_base,
-    get_logger,
-    leagues,
-    load_cache,
-    new_browser,
-    now,
-    safe_process_event,
-    write_cache,
-)
+from .utils import Cache, Time, get_logger, leagues, network
 
 log = get_logger(__name__)
 
 urls: dict[str, dict[str, str | float]] = {}
 
-CACHE_FILE = Path(__file__).parent / "caches" / "streameast.json"
+CACHE_FILE = Cache(Path(__file__).parent / "caches" / "streameast.json", exp=10_800)
 
 MIRRORS = [
     "https://streameast.ga",
@@ -48,7 +36,7 @@ MIRRORS = [
 
 async def process_event(url: str, url_num: int) -> str | None:
     async with async_playwright() as p:
-        browser, context = await new_browser(p, browser="brave")
+        browser, context = await network.browser(p, browser="brave")
 
         page = await context.new_page()
 
@@ -56,7 +44,7 @@ async def process_event(url: str, url_num: int) -> str | None:
 
         got_one = asyncio.Event()
 
-        handler = partial(capture_req, captured=captured, got_one=got_one)
+        handler = partial(network.capture_req, captured=captured, got_one=got_one)
 
         page.on("request", handler)
 
@@ -114,8 +102,10 @@ async def get_events(
     soup = HTMLParser(r.text)
     events = []
 
-    start_dt = now - timedelta(minutes=30)
-    end_dt = now + timedelta(minutes=30)
+    now = Time.now()
+
+    start_dt = now.delta(minutes=-30)
+    end_dt = now.delta(minutes=30)
 
     for section in soup.css("div.se-sport-section"):
         if not (sport := section.attributes.get("data-sport-name", "").strip()):
@@ -147,7 +137,7 @@ async def get_events(
             if cached_keys & {key}:
                 continue
 
-            event_dt = datetime.fromtimestamp(timestamp, TZ)
+            event_dt = Time.from_ts(timestamp)
 
             if time_text == "LIVE" or (start_dt <= event_dt < end_dt):
                 events.append(
@@ -155,6 +145,7 @@ async def get_events(
                         "sport": sport,
                         "event": name,
                         "link": href,
+                        "timestamp": timestamp,
                     }
                 )
 
@@ -162,15 +153,15 @@ async def get_events(
 
 
 async def scrape(client: httpx.AsyncClient) -> None:
-    cached_urls = load_cache(CACHE_FILE, exp=10_800)
+    cached_urls = CACHE_FILE.load()
     cached_count = len(cached_urls)
     urls.update(cached_urls)
 
-    log.info(f"Collected {cached_count} event(s) from cache")
+    log.info(f"Loaded {cached_count} event(s) from cache")
 
-    if not (base_url := await get_base(client, MIRRORS)):
+    if not (base_url := await network.get_base(MIRRORS)):
         log.warning("No working StreamEast mirrors")
-        write_cache(CACHE_FILE, cached_urls)
+        CACHE_FILE.write(cached_urls)
         return
 
     log.info(f'Scraping from "{base_url}"')
@@ -184,14 +175,14 @@ async def scrape(client: httpx.AsyncClient) -> None:
     log.info(f"Processing {len(events)} new URL(s)")
 
     for i, ev in enumerate(events, start=1):
-        url = await safe_process_event(
+        url = await network.safe_process(
             lambda: process_event(ev["link"], url_num=i),
             url_num=i,
             log=log,
         )
 
         if url:
-            sport, event = ev["sport"], ev["event"]
+            sport, event, ts = ev["sport"], ev["event"], ev["timestamp"]
 
             tvg_id, logo = leagues.info(sport)
 
@@ -205,8 +196,8 @@ async def scrape(client: httpx.AsyncClient) -> None:
                 "url": url,
                 "logo": logo,
                 "base": base_url,
-                "timestamp": now.timestamp(),
-                "id": tvg_id,
+                "timestamp": ts,
+                "id": tvg_id or "Live.Event.us",
             }
 
             urls[key] = cached_urls[key] = entry
@@ -216,4 +207,4 @@ async def scrape(client: httpx.AsyncClient) -> None:
     else:
         log.info("No new events found")
 
-    write_cache(CACHE_FILE, cached_urls)
+    CACHE_FILE.write(cached_urls)