e

M3U8/scrapers/strmfree.py

@@ -0,0 +1,206 @@
+import asyncio
+from functools import partial
+from pathlib import Path
+from urllib.parse import urljoin
+
+import httpx
+from playwright.async_api import BrowserContext, async_playwright
+
+from .utils import Cache, Time, get_logger, leagues, network
+
+log = get_logger(__name__)
+
+urls: dict[str, dict[str, str | float]] = {}
+
+API_FILE = Cache(Path(__file__).parent / "caches" / "strmfree_api.json", exp=86_400)
+
+CACHE_FILE = Cache(Path(__file__).parent / "caches" / "strmfree.json", exp=10_800)
+
+BASE_URL = "https://streamfree.to"
+
+
+async def refresh_api_cache(
+    client: httpx.AsyncClient,
+    url: str,
+) -> dict[str, dict[str, list]]:
+    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}')
+        return {}
+
+    data = r.json()
+
+    data["timestamp"] = Time.now().timestamp()
+
+    return data
+
+
+async def process_event(
+    url: str,
+    url_num: int,
+    context: BrowserContext,
+) -> 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 asyncio.wait_for(wait_task, timeout=6)
+        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[-1]
+
+        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,
+    url: str,
+    cached_keys: set[str],
+) -> list[dict[str, str]]:
+
+    if not (api_data := API_FILE.load(per_entry=False)):
+        api_data = await refresh_api_cache(
+            client,
+            urljoin(url, "streams"),
+        )
+
+        API_FILE.write(api_data)
+
+    events: list[dict[str, str]] = []
+
+    now = Time.clean(Time.now())
+    start_dt = now.delta(minutes=-30)
+    end_dt = now.delta(minutes=30)
+
+    for category, streams in api_data["streams"].items():
+        if not streams:
+            continue
+
+        for stream in streams:
+            event_dt = Time.from_ts(stream["match_timestamp"])
+
+            if not start_dt <= event_dt <= end_dt:
+                continue
+
+            sport, name = stream["league"], stream["name"]
+
+            key = f"[{sport}] {name} (STRMFR)"
+
+            if cached_keys & {key}:
+                continue
+
+            stream_url = stream["stream_key"]
+
+            stream_logo = stream["thumbnail_url"]
+
+            events.append(
+                {
+                    "sport": sport,
+                    "event": name,
+                    "link": urljoin(url, f"player/{category}/{stream_url}"),
+                    "logo": urljoin(url, stream_logo),
+                    "timestamp": event_dt.timestamp(),
+                }
+            )
+
+    return events
+
+
+async def scrape(client: httpx.AsyncClient) -> None:
+    cached_urls = CACHE_FILE.load()
+    cached_count = len(cached_urls)
+    urls.update(cached_urls)
+
+    log.info(f"Loaded {cached_count} event(s) from cache")
+
+    log.info(f'Scraping from "{BASE_URL}"')
+
+    events = await get_events(
+        client,
+        BASE_URL,
+        set(cached_urls.keys()),
+    )
+
+    log.info(f"Processing {len(events)} new URL(s)")
+
+    async with async_playwright() as p:
+        browser, context = await network.browser(p)
+
+        for i, ev in enumerate(events, start=1):
+            handler = partial(process_event, url=ev["link"], url_num=i, context=context)
+
+            url = await network.safe_process(handler, url_num=i, log=log)
+
+            if url:
+                sport, event, logo, ts = (
+                    ev["sport"],
+                    ev["event"],
+                    ev["logo"],
+                    ev["timestamp"],
+                )
+
+                key = f"[{sport}] {event} (STRMFR)"
+
+                tvg_id, pic = leagues.get_tvg_info(sport, event)
+
+                entry = {
+                    "url": url,
+                    "logo": logo or pic,
+                    "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)")
+    else:
+        log.info("No new events found")
+
+    CACHE_FILE.write(cached_urls)