M3U8/fetch.py

@@ -25,6 +25,7 @@ from scrapers import (
     totalsportek3,
     tvapp,
     volokit,
+    watchfooty,
     webcast,
 )
 from scrapers.utils import get_logger, network
@@ -68,9 +69,9 @@ async def main() -> None:
                 asyncio.create_task(roxie.scrape(hdl_brwsr)),
                 asyncio.create_task(sportzone.scrape(xtrnl_brwsr)),
                 asyncio.create_task(streamcenter.scrape(hdl_brwsr)),
-                asyncio.create_task(streamhub.scrape(xtrnl_brwsr)),
+                # asyncio.create_task(streamhub.scrape(xtrnl_brwsr)),
                 asyncio.create_task(streamsgate.scrape(xtrnl_brwsr)),
-                # asyncio.create_task(timstreams.scrape(xtrnl_brwsr)),
+                asyncio.create_task(timstreams.scrape(xtrnl_brwsr)),
             ]
 
             httpx_tasks = [
@@ -90,6 +91,7 @@ async def main() -> None:
             await asyncio.gather(*(pw_tasks + httpx_tasks))
 
             # others
+            # await watchfooty.scrape(xtrnl_brwsr)
             await livetvsx.scrape(xtrnl_brwsr)
 
         finally:
@@ -120,6 +122,7 @@ async def main() -> None:
         | totalsportek3.urls
         | tvapp.urls
         | volokit.urls
+        | watchfooty.urls
         | webcast.urls
     )
 

M3U8/scrapers/watchfooty.py

@@ -0,0 +1,296 @@
+import asyncio
+import re
+from functools import partial
+from itertools import chain
+from typing import Any
+from urllib.parse import urljoin
+
+from playwright.async_api import Browser, Page, Response, TimeoutError
+
+from .utils import Cache, Time, get_logger, leagues, network
+
+log = get_logger(__name__)
+
+urls: dict[str, dict[str, str | float]] = {}
+
+TAG = "WATCHFTY"
+
+CACHE_FILE = Cache(TAG, exp=10_800)
+
+API_FILE = Cache(f"{TAG}-api", exp=19_800)
+
+BASE_DOMAIN = "watchfooty.pw"
+
+API_URL, BASE_URL = f"https://api.{BASE_DOMAIN}", f"https://www.{BASE_DOMAIN}"
+
+VALID_SPORTS = [
+    # "american-football",
+    "baseball",
+    "basketball",
+    "fighting",
+    "football",
+    "golf",
+    "hockey",
+    "racing",
+    "tennis",
+    "volleyball",
+]
+
+
+async def refresh_api_cache(now: Time) -> list[dict[str, Any]]:
+    tasks = [
+        network.request(
+            urljoin(API_URL, "api/v1/matches/all"),
+            log=log,
+            params={"date": d.date()},
+        )
+        for d in [now, now.delta(days=1)]
+    ]
+
+    results = await asyncio.gather(*tasks)
+
+    if not (data := [*chain.from_iterable(r.json() for r in results if r)]):
+        return [{"timestamp": now.timestamp()}]
+
+    for ev in data:
+        ev["ts"] = ev.pop("timestamp")
+
+    data[-1]["timestamp"] = now.timestamp()
+
+    return data
+
+
+def sift_xhr(resp: Response, match_id: int) -> bool:
+    resp_url = resp.url
+
+    return (
+        f"/en/stream/{match_id}/" in resp_url
+        and "_rsc=" not in resp_url
+        and resp.status == 200
+    )
+
+
+async def process_event(
+    url: str,
+    match_id: int,
+    url_num: int,
+    page: Page,
+) -> tuple[str | None, str | None]:
+
+    nones = None, None
+
+    captured: list[str] = []
+
+    got_one = asyncio.Event()
+
+    handler = partial(
+        network.capture_req,
+        captured=captured,
+        got_one=got_one,
+    )
+
+    strm_handler = partial(sift_xhr, match_id=match_id)
+
+    page.on("request", handler)
+
+    try:
+        try:
+            async with page.expect_response(strm_handler, timeout=3_250) as strm_resp:
+                resp = await page.goto(
+                    url,
+                    wait_until="domcontentloaded",
+                    timeout=6_000,
+                )
+
+                if not resp or resp.status != 200:
+                    log.warning(
+                        f"URL {url_num}) Status Code: {resp.status if resp else 'None'}"
+                    )
+
+                    return nones
+
+                response = await strm_resp.value
+
+                stream_url = response.url
+        except TimeoutError:
+            log.warning(f"URL {url_num}) No available stream links.")
+
+            return nones
+
+        embed = re.sub(
+            pattern=r"^.*\/stream",
+            repl="https://pikachusports.top/embed",
+            string=stream_url,
+        )
+
+        await page.goto(
+            embed,
+            wait_until="domcontentloaded",
+            timeout=5_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 nones
+
+        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], embed
+
+        log.warning(f"URL {url_num}) No M3U8 captured after waiting.")
+
+        return nones
+
+    except Exception as e:
+        log.warning(f"URL {url_num}) {e}")
+
+        return nones
+
+    finally:
+        page.remove_listener("request", handler)
+
+
+async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
+    now = Time.clean(Time.now())
+
+    if not (api_data := API_FILE.load(per_entry=False, index=-1)):
+        log.info("Refreshing API cache")
+
+        api_data = await refresh_api_cache(now)
+
+        API_FILE.write(api_data)
+
+    events = []
+
+    pattern = re.compile(r"\-+|\(")
+
+    start_dt = now.delta(minutes=-30)
+    end_dt = now.delta(minutes=5)
+
+    for event in api_data:
+        match_id = event.get("matchId")
+
+        name = event.get("title")
+
+        league = event.get("league")
+
+        if not (match_id and name and league):
+            continue
+
+        if event["sport"] not in VALID_SPORTS:
+            continue
+
+        sport = pattern.split(league, 1)[0].strip()
+
+        if f"[{sport}] {name} ({TAG})" in cached_keys:
+            continue
+
+        if not (date := event.get("date")):
+            continue
+
+        event_dt = Time.from_str(date, timezone="UTC")
+
+        if not start_dt <= event_dt <= end_dt:
+            continue
+
+        logo = urljoin(API_URL, poster) if (poster := event.get("poster")) else None
+
+        events.append(
+            {
+                "sport": sport,
+                "event": name,
+                "link": urljoin(BASE_URL, f"stream/{match_id}"),
+                "match-id": match_id,
+                "logo": logo,
+                "timestamp": event_dt.timestamp(),
+            }
+        )
+
+    return events
+
+
+async def scrape(browser: Browser) -> None:
+    cached_urls = CACHE_FILE.load()
+
+    valid_urls = {k: v for k, v in cached_urls.items() if v["url"]}
+
+    valid_count = cached_count = len(valid_urls)
+
+    urls.update(valid_urls)
+
+    log.info(f"Loaded {cached_count} event(s) from cache")
+
+    log.info(f'Scraping from "{BASE_URL}"')
+
+    if events := await get_events(cached_urls.keys()):
+        log.info(f"Processing {len(events)} new URL(s)")
+
+        async with network.event_context(browser, stealth=False) as context:
+            for i, ev in enumerate(events, start=1):
+                async with network.event_page(context) as page:
+                    handler = partial(
+                        process_event,
+                        url=(link := ev["link"]),
+                        match_id=ev["match-id"],
+                        url_num=i,
+                        page=page,
+                    )
+
+                    url, iframe = await network.safe_process(
+                        handler,
+                        url_num=i,
+                        semaphore=network.PW_S,
+                        log=log,
+                        timeout=20,
+                    )
+
+                    sport, event, logo, ts = (
+                        ev["sport"],
+                        ev["event"],
+                        ev["logo"],
+                        ev["timestamp"],
+                    )
+
+                    key = f"[{sport}] {event} ({TAG})"
+
+                    tvg_id, pic = leagues.get_tvg_info(sport, event)
+
+                    entry = {
+                        "url": url,
+                        "logo": logo or pic,
+                        "base": iframe,
+                        "timestamp": ts,
+                        "id": tvg_id or "Live.Event.us",
+                        "link": link,
+                    }
+
+                    cached_urls[key] = entry
+
+                    if url:
+                        valid_count += 1
+
+                        entry["url"] = url.split("&t")[0]
+
+                        urls[key] = entry
+
+        log.info(f"Collected and cached {valid_count - cached_count} new event(s)")
+
+    else:
+        log.info("No new events found")
+
+    CACHE_FILE.write(cached_urls)

readme.md

@@ -1,17 +1,13 @@
-## Base Log @ 2026-03-15 09:00 UTC
+## Base Log @ 2026-03-14 08:59 UTC
 
-### ✅ Working Streams: 153<br>❌ Dead Streams: 8
+### ✅ Working Streams: 157<br>❌ Dead Streams: 4
 
 | Channel | Error (Code) | Link |
 | ------- | ------------ | ---- |
 | Altitude Sports | HTTP Error (403) | `http://mytvstream.net:8080/live/30550113/30550113/79545.m3u8` |
-| CBS Sports Network | HTTP Error (403) | `http://snowbank.houseinventer.com/7007/index.m3u8?token=c0lTeGc1M0gydFNjcloydGZhbTFsY1RYMkphdG5OcXdxNHpMeGFYWW5ZRERxNEduaVp1UnBxU2VlWmF0ZnRlRGxaMm1zNStDbnJOOXFZMlhtcStybmc9PQ==` |
+| FDSN Southeast | HTTP Error (000) | `http://mytvstream.net:8080/live/30550113/30550113/2213.m3u8` |
-| ESPN | HTTP Error (403) | `http://snowbank.houseinventer.com/6500/index.m3u8?token=M1lDdWljYkdyZGFhZzVxeGc2Mkt5OGJicWNxd2xheDkzWWVieEt5b3lZVERxNEduaVp1UnBxU2VlWmF0ZnRlRGxaMm1zNStDbnJOOXFZMlhtcStybmc9PQ==` |
-| ESPN2 | HTTP Error (403) | `http://snowbank.houseinventer.com/6501/index.m3u8?token=M1lDdWljYkdyZGFhZzVxeGc2Mkt5OGJicWNxd2xheDkzWWVieEt5b3lZVERxNEduaVp1UnBxU2VlWmF0ZnRlRGxaMm1zNStDbnJOOXFZMlhtcStybmc9PQ==` |
-| Game Show Network | HTTP Error (403) | `http://mytvstream.net:8080/live/30550113/30550113/120633.m3u8` |
-| Hallmark Family | HTTP Error (403) | `http://mytvstream.net:8080/live/30550113/30550113/9307.m3u8` |
-| NBC Sports California | HTTP Error (403) | `http://mytvstream.net:8080/live/30550113/30550113/20940.m3u8` |
 | NHL Network | HTTP Error (000) | `http://mytvstream.net:8080/live/30550113/30550113/20179.m3u8` |
+| Spectrum SportsNet LA Dodgers | HTTP Error (403) | `http://mytvstream.net:8080/live/30550113/30550113/31636.m3u8` |
 ---
 #### Base Channels URL
 ```