health log

edit scraping method for webcast.py

M3U8/base.m3u8

@@ -58,7 +58,7 @@ http://41.205.93.154/BRAVO/index.m3u8
 https://buzzrota-web.amagi.tv/playlist.m3u8
 
 #EXTINF:-1 tvg-chno="20" tvg-id="CSPAN.us2" tvg-name="C-SPAN" tvg-logo="http://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s10161_dark_360w_270h.png" group-title="TV",C-SPAN
-http://mytvstream.net:8080/live/30550113/30550113/136589.m3u8
+http://mytvstream.net:8080/live/bn80NG/909467/136589.m3u8
 
 #EXTINF:-1 tvg-chno="21" tvg-id="Cartoon.Network.HD.us2" tvg-name="Cartoon Network" tvg-logo="http://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s12131_dark_360w_270h.png" group-title="TV",Cartoon Network
 http://23.237.104.106:8080/USA_CARTOON_NETWORK/index.m3u8
@@ -127,7 +127,7 @@ http://hardcoremedia.xyz/live/rabdsbmz/3731346838/129866.ts
 http://hardcoremedia.xyz/live/rabdsbmz/3731346838/129867.ts
 
 #EXTINF:-1 tvg-chno="43" tvg-id="Disney.Channel.HD.us2" tvg-name="Disney" tvg-logo="http://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s10171_dark_360w_270h.png" group-title="TV",Disney Channel
-http://104.255.88.155/disney/index.m3u8
+http://hardcoremedia.xyz/live/rabdsbmz/3731346838/257087.ts
 
 #EXTINF:-1 tvg-chno="44" tvg-id="Disney.XD.HD.us2" tvg-name="Disney XD" tvg-logo="http://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s18279_dark_360w_270h.png" group-title="TV",Disney XD
 http://hardcoremedia.xyz/live/rabdsbmz/3731346838/130092.ts
@@ -148,40 +148,40 @@ http://23.237.104.106:8080/USA_ESPNU/index.m3u8
 http://snowbank.houseinventer.com/6501/index.m3u8?token=M1lDdWljYkdyZGFhZzVxeGc2Mkt5OGJicWNxd2xheDkzWWVieEt5b3lZVERxNEduaVp1UnBxU2VlWmF0ZnRlRGxaMm1zNStDbnJOOXFZMlhtcStybmc9PQ==
 
 #EXTINF:-1 tvg-chno="50" tvg-id="FanDuel.Sports.Network.Detroit.24/7.HDTV.us" tvg-name="FDSN Detroit" tvg-logo="https://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s54286_dark_360w_270h.png" group-title="TV",FDSN Detroit
-http://mytvstream.net:8080/live/30550113/30550113/20930.m3u8
+http://mytvstream.net:8080/live/bn80NG/909467/20930.m3u8
 
 #EXTINF:-1 tvg-chno="51" tvg-id="FanDuel.Sports.Network.Florida.HDTV.(Out.of.Market).us" tvg-name="FDSN Florida" tvg-logo="https://i.gyazo.com/fad701fbaaafe161b13b23ed9b50179b.png" group-title="TV",FDSN Florida
-http://mytvstream.net:8080/live/30550113/30550113/46794.m3u8
+http://mytvstream.net:8080/live/bn80NG/909467/46794.m3u8
 
 #EXTINF:-1 tvg-chno="52" tvg-id="FanDuel.Sports.Network.Midwest.24/7.HDTV.us" tvg-name="FDSN Midwest" tvg-logo="http://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s11058_dark_360w_270h.png" group-title="TV",FDSN Midwest
-http://mytvstream.net:8080/live/30550113/30550113/66795.m3u8
+http://mytvstream.net:8080/live/bn80NG/909467/66795.m3u8
 
 #EXTINF:-1 tvg-chno="53" tvg-id="FanDuel.Sports.Network.North.HDTV.us" tvg-name="FDSN North" tvg-logo="https://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s10977_dark_360w_270h.png" group-title="TV",FDSN North
-http://mytvstream.net:8080/live/30550113/30550113/58827.m3u8
+http://mytvstream.net:8080/live/bn80NG/909467/58827.m3u8
 
 #EXTINF:-1 tvg-chno="54" tvg-id="FanDuel.Sports.Network.Ohio.(Cleveland).HDTV.us" tvg-name="FDSN Ohio" tvg-logo="http://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s49691_dark_360w_270h.png" group-title="TV",FDSN Ohio
-http://mytvstream.net:8080/live/30550113/30550113/17752.m3u8
+http://mytvstream.net:8080/live/bn80NG/909467/17752.m3u8
 
 #EXTINF:-1 tvg-chno="55" tvg-id="FanDuel.Sports.Network.Oklahoma.24/7.HDTV.(Tulsa).us" tvg-name="FDSN Oklahoma" tvg-logo="https://i.gyazo.com/80ad6fd142cd67f06eef58d9ce5aa72b.png" group-title="TV",FDSN Oklahoma
-http://mytvstream.net:8080/live/30550113/30550113/20934.m3u8
+http://mytvstream.net:8080/live/bn80NG/909467/20934.m3u8
 
 #EXTINF:-1 tvg-chno="56" tvg-id="FanDuel.Sports.Network.SoCal.HDTV.us" tvg-name="FDSN SoCal" tvg-logo="http://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s16743_dark_360w_270h.png" group-title="TV",FDSN SoCal
-http://mytvstream.net:8080/live/30550113/30550113/221151.m3u8
+http://mytvstream.net:8080/live/bn80NG/909467/221151.m3u8
 
 #EXTINF:-1 tvg-chno="57" tvg-id="FanDuel.Sports.Network.Southeast.HDTV.(Mont./Birm./Dothan/Mobile.AL).us" tvg-name="FDSN Southeast" tvg-logo="http://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s20789_dark_360w_270h.png" group-title="TV",FDSN Southeast
-http://mytvstream.net:8080/live/30550113/30550113/2213.m3u8
+http://mytvstream.net:8080/live/bn80NG/909467/2213.m3u8
 
 #EXTINF:-1 tvg-chno="58" tvg-id="FanDuel.Sports.Network.Southwest.HDTV.24/7.(Main).us" tvg-name="FDSN Southwest" tvg-logo="https://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s59629_dark_360w_270h.png" group-title="TV",FDSN Southwest
-http://mytvstream.net:8080/live/30550113/30550113/21843.m3u8
+http://mytvstream.net:8080/live/bn80NG/909467/21843.m3u8
 
 #EXTINF:-1 tvg-chno="59" tvg-id="FanDuel.Sports.Network.Sun.South.24/7.HDTV.(South.Marlins,.Rays,.Heat).us" tvg-name="FDSN Sun" tvg-logo="http://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s61084_dark_360w_270h.png" group-title="TV",FDSN Sun
-http://mytvstream.net:8080/live/30550113/30550113/104917.m3u8
+http://mytvstream.net:8080/live/bn80NG/909467/104917.m3u8
 
 #EXTINF:-1 tvg-chno="60" tvg-id="FanDuel.Sports.Network.West.HDTV.us" tvg-name="FDSN West" tvg-logo="https://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s59627_dark_360w_270h.png" group-title="TV",FDSN West
-http://mytvstream.net:8080/live/30550113/30550113/20932.m3u8
+http://mytvstream.net:8080/live/bn80NG/909467/20932.m3u8
 
 #EXTINF:-1 tvg-chno="61" tvg-id="FanDuel.Sports.Network.Wisconsin.24/7.HDTV.us" tvg-name="FDSN Wisconsin" tvg-logo="http://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s16348_dark_360w_270h.png" group-title="TV",FDSN Wisconsin
-http://mytvstream.net:8080/live/30550113/30550113/78599.m3u8
+http://mytvstream.net:8080/live/bn80NG/909467/78599.m3u8
 
 #EXTINF:-1 tvg-chno="62" tvg-id="plex.tv.FIFA+.plex" tvg-name="FIFA+ TV" tvg-logo="http://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s136235_dark_360w_270h.png" group-title="TV",FIFA+ TV
 https://jmp2.uk/stvp-IN270000230
@@ -253,7 +253,7 @@ http://23.237.104.106:8080/USA_HBO2/index.m3u8
 http://hardcoremedia.xyz/live/rabdsbmz/3731346838/129990.ts
 
 #EXTINF:-1 tvg-chno="85" tvg-id="HBO.Drama.us2" tvg-name="HBO Family" tvg-logo="http://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s34879_dark_360w_270h.png" group-title="TV",HBO Family
-http://mytvstream.net:8080/live/30550113/30550113/17772.m3u8
+http://mytvstream.net:8080/live/bn80NG/909467/17772.m3u8
 
 #EXTINF:-1 tvg-chno="86" tvg-id="HBO.Zone.HD.us2" tvg-name="HBO Zone" tvg-logo="https://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s18431_dark_360w_270h.png" group-title="TV",HBO Zone
 http://hardcoremedia.xyz/live/rabdsbmz/3731346838/129995.ts
@@ -307,10 +307,10 @@ http://212.102.60.231/NBA_TV/index.m3u8
 http://stream.cammonitorplus.net/1842/index.m3u8?token=MnE3ZWg1YkgxdFdWZlo2c2hLMkltWnJhcFo1OHhxcXVyb2pKazZXaWxZRERxNEduaVp1UnBxU2VlWmF0ZnRlRGxaMm1zNStDbnJOOXFZMlhtcStybmc9PQ==
 
 #EXTINF:-1 tvg-chno="103" tvg-id="NBC.Sports.Bay.Area.HD.us2" tvg-name="NBC Sports Bay Area" tvg-logo="http://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s63138_dark_360w_270h.png" group-title="TV",NBC Sports Bay Area
-http://mytvstream.net:8080/live/30550113/30550113/9900.m3u8
+http://mytvstream.net:8080/live/bn80NG/909467/9900.m3u8
 
 #EXTINF:-1 tvg-chno="104" tvg-id="NBC.Sports.Boston.HD.us2" tvg-name="NBC Sports Boston" tvg-logo="http://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s49198_dark_360w_270h.png" group-title="TV",NBC Sports Boston
-http://mytvstream.net:8080/live/30550113/30550113/20939.m3u8
+http://mytvstream.net:8080/live/bn80NG/909467/20939.m3u8
 
 #EXTINF:-1 tvg-chno="105" tvg-id="NBC.Sports.California.SAT.us2" tvg-name="NBC Sports California" tvg-logo="http://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s45540_dark_360w_270h.png" group-title="TV",NBC Sports California
 http://hardcoremedia.xyz/live/rabdsbmz/3731346838/136474.ts
@@ -334,7 +334,7 @@ https://stream.decentdoubts.net/6128524/index.m3u8?token=Mm9QYnQ1ZkpyYWllaEoydWh
 https://starshare.st/live/P4B9TB9xR8/humongous2tonight/23550.ts
 
 #EXTINF:-1 tvg-chno="112" tvg-id="NHL.Network.HD.us2" tvg-name="NHL Network" tvg-logo="http://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s58570_dark_360w_270h.png" group-title="TV",NHL Network
-https://nhl-firetv.amagi.tv/playlist.m3u8
+http://hardcoremedia.xyz/live/rabdsbmz/3731346838/167982.ts
 
 #EXTINF:-1 tvg-chno="113" tvg-id="Nick.Jr.HD.us2" tvg-name="Nick Jr" tvg-logo="https://schedulesdirect-api20141201-logos.s3.dualstack.us-east-1.amazonaws.com/stationLogos/s19211_dark_360w_270h.png" group-title="TV",Nick Jr
 http://hardcoremedia.xyz/live/rabdsbmz/3731346838/137683.ts

M3U8/fetch.py

@@ -5,6 +5,7 @@ from pathlib import Path
 
 from playwright.async_api import async_playwright
 from scrapers import (
+    cdnlivetv,
     embedhd,
     fawa,
     istreameast,
@@ -61,15 +62,15 @@ async def main() -> None:
             xtrnl_brwsr = await network.browser(p, external=True)
 
             pw_tasks = [
+                asyncio.create_task(cdnlivetv.scrape(hdl_brwsr)),
                 asyncio.create_task(embedhd.scrape(hdl_brwsr)),
                 asyncio.create_task(pixel.scrape(hdl_brwsr)),
                 asyncio.create_task(ppv.scrape(xtrnl_brwsr)),
                 asyncio.create_task(roxie.scrape(hdl_brwsr)),
                 asyncio.create_task(sport9.scrape(xtrnl_brwsr)),
-                asyncio.create_task(streamcenter.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(streamsgate.scrape(hdl_brwsr)),
-                asyncio.create_task(webcast.scrape(hdl_brwsr)),
             ]
 
             httpx_tasks = [
@@ -82,6 +83,7 @@ async def main() -> None:
                 asyncio.create_task(tvapp.scrape()),
                 asyncio.create_task(volokit.scrape()),
                 asyncio.create_task(xstreameast.scrape()),
+                asyncio.create_task(webcast.scrape()),
             ]
 
             await asyncio.gather(*(pw_tasks + httpx_tasks))
@@ -98,7 +100,8 @@ async def main() -> None:
             await network.client.aclose()
 
     additions = (
-        embedhd.urls
+        cdnlivetv.urls
+        | embedhd.urls
         | fawa.urls
         | istreameast.urls
         | livetvsx.urls

M3U8/scrapers/cdnlivetv.py

@@ -0,0 +1,151 @@
+from functools import partial
+from urllib.parse import urljoin
+
+from playwright.async_api import Browser
+
+from .utils import Cache, Time, get_logger, leagues, network
+
+log = get_logger(__name__)
+
+urls: dict[str, dict[str, str | float]] = {}
+
+TAG = "CDNTV"
+
+CACHE_FILE = Cache(TAG, exp=10_800)
+
+API_FILE = Cache(f"{TAG}-api", exp=19_800)
+
+API_URL = "https://api.cdn-live.tv"
+
+
+async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
+    now = Time.clean(Time.now())
+
+    events = []
+
+    if not (api_data := API_FILE.load(per_entry=False)):
+        log.info("Refreshing API cache")
+
+        if r := await network.request(
+            urljoin(API_URL, "api/v1/events/sports"),
+            log=log,
+            params={"user": "cdnlivetv", "plan": "free"},
+        ):
+            api_data = r.json().get("cdn-live-tv", {"timestamp": now.timestamp()})
+
+        API_FILE.write(api_data)
+
+    start_dt = now.delta(minutes=-30)
+    end_dt = now.delta(minutes=30)
+
+    sports = [key for key in api_data.keys() if not key.islower()]
+
+    for sport in sports:
+        event_info = api_data[sport]
+
+        for event in event_info:
+            t1, t2 = event["awayTeam"], event["homeTeam"]
+
+            name = f"{t1} vs {t2}"
+
+            league = event["tournament"]
+
+            if f"[{league}] {name} ({TAG})" in cached_keys:
+                continue
+
+            event_dt = Time.from_str(event["start"], timezone="UTC")
+
+            if not start_dt <= event_dt <= end_dt:
+                continue
+
+            if not (channels := event.get("channels")):
+                continue
+
+            event_links: list[str] = [channel["url"] for channel in channels]
+
+            # if not (
+            #     link := (
+            #         event_links[0]
+            #         if len(event_links) == 1
+            #         else await network.get_base(event_links)
+            #     )
+            # ):
+            #     continue
+
+            link = event_links[0]
+
+            events.append(
+                {
+                    "sport": league,
+                    "event": name,
+                    "link": link,
+                    "timestamp": event_dt.timestamp(),
+                }
+            )
+
+    return events
+
+
+async def scrape(browser: Browser) -> 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 "{API_URL}"')
+
+    events = await get_events(cached_urls.keys())
+
+    if events:
+        log.info(f"Processing {len(events)} new URL(s)")
+
+        async with network.event_context(browser) as context:
+            for i, ev in enumerate(events, start=1):
+                async with network.event_page(context) as page:
+                    handler = partial(
+                        network.process_event,
+                        url=(link := ev["link"]),
+                        url_num=i,
+                        page=page,
+                        log=log,
+                    )
+
+                    url = await network.safe_process(
+                        handler,
+                        url_num=i,
+                        semaphore=network.PW_S,
+                        log=log,
+                    )
+
+                    if url:
+                        sport, event, ts = (
+                            ev["sport"],
+                            ev["event"],
+                            ev["timestamp"],
+                        )
+
+                        key = f"[{sport}] {event} ({TAG})"
+
+                        tvg_id, logo = leagues.get_tvg_info(sport, event)
+
+                        entry = {
+                            "url": url,
+                            "logo": logo,
+                            "base": link,
+                            "timestamp": ts,
+                            "id": tvg_id or "Live.Event.us",
+                            "link": link,
+                        }
+
+                        urls[key] = cached_urls[key] = entry
+
+    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)

M3U8/scrapers/ovogoal.py

@@ -11,9 +11,7 @@ urls: dict[str, dict[str, str | float]] = {}
 
 TAG = "OVOGOAL"
 
-CACHE_FILE = Cache(TAG, exp=10_800)
+CACHE_FILE = Cache(TAG, exp=19_800)
-
-HTML_CACHE = Cache(f"{TAG}-html", exp=19_800)
 
 BASE_URL = "https://ovogoal.plus"
 
@@ -48,27 +46,22 @@ async def process_event(url: str, url_num: int) -> tuple[str | None, str | None]
     return match[3], iframe_src
 
 
-async def refresh_html_cache() -> dict[str, dict[str, str | float]]:
+async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
-    log.info("Refreshing HTML cache")
+    events = []
-
-    now = Time.clean(Time.now())
-
-    events = {}
 
     if not (html_data := await network.request(BASE_URL, log=log)):
         return events
 
     soup = HTMLParser(html_data.content)
 
+    sport = "Live Event"
+
     for card in soup.css(".stream-row"):
         if (not (watch_btn_elem := card.css_first(".watch-btn"))) or (
             not (onclick := watch_btn_elem.attributes.get("onclick"))
         ):
             continue
 
-        if not (event_time_elem := card.css_first(".stream-time")):
-            continue
-
         if not (event_name_elem := card.css_first(".stream-info")):
             continue
 
@@ -76,50 +69,20 @@ async def refresh_html_cache() -> dict[str, dict[str, str | float]]:
 
         event_name = event_name_elem.text(strip=True)
 
-        event_time = event_time_elem.text(strip=True)
+        if f"[{sport}] {event_name} ({TAG})" in cached_keys:
+            continue
 
-        event_dt = Time.from_str(f"{now.date()} {event_time}", timezone="CET")
+        events.append(
-
+            {
-        sport = "Live Event"
+                "sport": sport,
-
+                "event": event_name,
-        key = f"[{sport}] {event_name} ({TAG})"
+                "link": href,
-
+            }
-        events[key] = {
+        )
-            "sport": sport,
-            "event": event_name,
-            "link": href,
-            "event_ts": event_dt.timestamp(),
-            "timestamp": now.timestamp(),
-        }
 
     return events
 
 
-async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
-    now = Time.clean(Time.now())
-
-    if not (events := HTML_CACHE.load()):
-        events = await refresh_html_cache()
-
-        HTML_CACHE.write(events)
-
-    live = []
-
-    start_ts = now.delta(minutes=-30).timestamp()
-    end_ts = now.delta(minutes=30).timestamp()
-
-    for k, v in events.items():
-        if k in cached_keys:
-            continue
-
-        if not start_ts <= v["event_ts"] <= end_ts:
-            continue
-
-        live.append(v)
-
-    return live
-
-
 async def scrape() -> None:
     cached_urls = CACHE_FILE.load()
 
@@ -138,6 +101,8 @@ async def scrape() -> None:
     if events:
         log.info(f"Processing {len(events)} new URL(s)")
 
+        now = Time.clean(Time.now())
+
         for i, ev in enumerate(events, start=1):
             handler = partial(
                 process_event,
@@ -152,11 +117,7 @@ async def scrape() -> None:
                 log=log,
             )
 
-            sport, event, ts = (
+            sport, event = ev["sport"], ev["event"]
-                ev["sport"],
-                ev["event"],
-                ev["event_ts"],
-            )
 
             key = f"[{sport}] {event} ({TAG})"
 
@@ -166,7 +127,7 @@ async def scrape() -> None:
                 "url": url,
                 "logo": logo,
                 "base": iframe,
-                "timestamp": ts,
+                "timestamp": now.timestamp(),
                 "id": tvg_id or "Live.Event.us",
                 "link": link,
             }

M3U8/scrapers/pawa.py

@@ -61,6 +61,8 @@ async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
 
     feed = feedparser.parse(html_data.content)
 
+    sport = "Live Event"
+
     for entry in feed.entries:
         if not (link := entry.get("link")):
             continue
@@ -68,8 +70,6 @@ async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
         if not (title := entry.get("title")):
             continue
 
-        sport = "Live Event"
-
         title = title.replace(" v ", " vs ")
 
         if f"[{sport}] {title} ({TAG})" in cached_keys:

M3U8/scrapers/utils/config.py

@@ -149,7 +149,7 @@ class Leagues:
         league: str,
     ) -> bool:
 
-        pattern = re.compile(r"\s+(?:-|vs\.?|at|@)\s+", re.IGNORECASE)
+        pattern = re.compile(r"\s+(?:-|vs\.?|at|@)\s+", re.I)
 
         if pattern.search(event):
             t1, t2 = re.split(pattern, event)

M3U8/scrapers/utils/webwork.py

@@ -215,10 +215,7 @@ class Network:
 
         escaped = [re.escape(i) for i in invalids]
 
-        pattern = re.compile(
+        pattern = re.compile(rf"^(?!.*({'|'.join(escaped)})).*\.m3u8", re.I)
-            rf"^(?!.*({'|'.join(escaped)})).*\.m3u8",
-            re.IGNORECASE,
-        )
 
         if pattern.search(req.url):
             captured.append(req.url)

M3U8/scrapers/volokit.py

@@ -13,9 +13,7 @@ urls: dict[str, dict[str, str | float]] = {}
 
 TAG = "VOLOKIT"
 
-CACHE_FILE = Cache(TAG, exp=10_800)
+CACHE_FILE = Cache(TAG, exp=19_800)
-
-HTML_CACHE = Cache(f"{TAG}-html", exp=19_800)
 
 BASE_URL = "http://volokit.xyz"
 
@@ -71,98 +69,48 @@ async def process_event(url: str, url_num: int) -> str | None:
     return match[1]
 
 
-async def refresh_html_cache(
+async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
-    url: str,
+    sport_urls = {
-    sport: str,
+        sport.upper(): urljoin(BASE_URL, f"sport/{sport}/") for sport in SPORT_ENDPOINTS
-    now: Time,
+    }
-) -> dict[str, dict[str, str | float]]:
 
-    events = {}
+    tasks = [network.request(url, log=log) for url in sport_urls.values()]
 
-    if not (html_data := await network.request(url, log=log)):
+    results = await asyncio.gather(*tasks)
+
+    events = []
+
+    if not (
+        soups := [(HTMLParser(html.content), html.url) for html in results if html]
+    ):
         return events
 
-    soup = HTMLParser(html_data.content)
+    for soup, url in soups:
+        for card in soup.css("#events .table .vevent.theevent"):
+            if not (href := card.css_first("a").attributes.get("href")):
+                continue
 
-    date = now.date()
+            if not (name_node := card.css_first(".teamtd.event")):
+                continue
 
-    if date_node := soup.css_first("tr.date"):
+            name = fix_event(name_node.text(strip=True))
-        date = date_node.text(strip=True)
 
-    for card in soup.css("#events .table .vevent.theevent"):
+            sport = next((k for k, v in sport_urls.items() if v == url), "Live Event")
-        if not (href := card.css_first("a").attributes.get("href")):
-            continue
 
-        name_node = card.css_first(".teamtd.event")
+            if f"[{sport}] {name} ({TAG})" in cached_keys:
+                continue
 
-        time_node = card.css_first(".time")
+            events.append(
-
+                {
-        if not (name_node and time_node):
+                    "sport": sport,
-            continue
+                    "event": name,
-
+                    "link": href,
-        name, time = name_node.text(strip=True), time_node.text(strip=True)
+                }
-
+            )
-        event_sport = SPORT_ENDPOINTS[sport]
-
-        event_name = fix_event(name)
-
-        event_dt = Time.from_str(f"{date} {time}", timezone="UTC")
-
-        key = f"[{event_sport}] {event_name} ({TAG})"
-
-        events[key] = {
-            "sport": event_sport,
-            "event": event_name,
-            "link": href,
-            "event_ts": event_dt.timestamp(),
-            "timestamp": now.timestamp(),
-        }
 
     return events
 
 
-async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
-    now = Time.clean(Time.now())
-
-    if not (events := HTML_CACHE.load()):
-        log.info("Refreshing HTML cache")
-
-        sport_urls = {
-            sport: urljoin(BASE_URL, f"sport/{sport}") for sport in SPORT_ENDPOINTS
-        }
-
-        tasks = [
-            refresh_html_cache(
-                url,
-                sport,
-                now,
-            )
-            for sport, url in sport_urls.items()
-        ]
-
-        results = await asyncio.gather(*tasks)
-
-        events = {k: v for data in results for k, v in data.items()}
-
-        HTML_CACHE.write(events)
-
-    live = []
-
-    start_ts = now.delta(minutes=-30).timestamp()
-    end_ts = now.delta(minutes=30).timestamp()
-
-    for k, v in events.items():
-        if k in cached_keys:
-            continue
-
-        if not start_ts <= v["event_ts"] <= end_ts:
-            continue
-
-        live.append(v)
-
-    return live
-
-
 async def scrape() -> None:
     cached_urls = CACHE_FILE.load()
 
@@ -181,6 +129,8 @@ async def scrape() -> None:
     if events:
         log.info(f"Processing {len(events)} new URL(s)")
 
+        now = Time.clean(Time.now())
+
         for i, ev in enumerate(events, start=1):
             handler = partial(
                 process_event,
@@ -195,11 +145,7 @@ async def scrape() -> None:
                 log=log,
             )
 
-            sport, event, ts = (
+            sport, event = ev["sport"], ev["event"]
-                ev["sport"],
-                ev["event"],
-                ev["event_ts"],
-            )
 
             key = f"[{sport}] {event} ({TAG})"
 
@@ -209,7 +155,7 @@ async def scrape() -> None:
                 "url": url,
                 "logo": logo,
                 "base": link,
-                "timestamp": ts,
+                "timestamp": now.timestamp(),
                 "id": tvg_id or "Live.Event.us",
                 "link": link,
             }

M3U8/scrapers/webcast.py

@@ -1,7 +1,7 @@
 import asyncio
+import re
 from functools import partial
 
-from playwright.async_api import Browser
 from selectolax.parser import HTMLParser
 
 from .utils import Cache, Time, get_logger, leagues, network
@@ -12,11 +12,10 @@ urls: dict[str, dict[str, str | float]] = {}
 
 TAG = "WEBCAST"
 
-CACHE_FILE = Cache(TAG, exp=10_800)
+CACHE_FILE = Cache(TAG, exp=19_800)
-
-HTML_CACHE = Cache(f"{TAG}-html", exp=86_400)
 
 BASE_URLS = {
+    "MLB": "https://mlbwebcast.com",
     # "NFL": "https://nflwebcast.com",
     "NHL": "https://slapstreams.com",
 }
@@ -26,99 +25,100 @@ def fix_event(s: str) -> str:
     return " vs ".join(s.split("@"))
 
 
-async def refresh_html_cache(url: str) -> dict[str, dict[str, str | float]]:
+async def process_event(url: str, url_num: int) -> str | None:
-    events = {}
+    if not (event_data := await network.request(url, log=log)):
+        log.info(f"URL {url_num}) Failed to load url.")
 
-    if not (html_data := await network.request(url, log=log)):
+        return
+
+    soup = HTMLParser(event_data.content)
+
+    if not (iframe := soup.css_first('iframe[name="srcFrame"]')):
+        log.warning(f"URL {url_num}) No iframe element found.")
+
+        return
+
+    if not (iframe_src := iframe.attributes.get("src")):
+        log.warning(f"URL {url_num}) No iframe source found.")
+
+        return
+
+    if not (
+        iframe_src_data := await network.request(
+            iframe_src,
+            headers={"Referer": url},
+            log=log,
+        )
+    ):
+        log.info(f"URL {url_num}) Failed to load iframe source.")
+
+        return
+
+    pattern = re.compile(r"source:\s+(\'|\")(.*)(\'|\")", re.I)
+
+    if not (match := pattern.search(iframe_src_data.text)):
+        log.warning(f"URL {url_num}) No Clappr source found.")
+
+        return
+
+    log.info(f"URL {url_num}) Captured M3U8")
+
+    return match[2]
+
+
+async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
+    tasks = [network.request(url, log=log) for url in BASE_URLS.values()]
+
+    results = await asyncio.gather(*tasks)
+
+    events = []
+
+    if not (
+        soups := [(HTMLParser(html.content), html.url) for html in results if html]
+    ):
         return events
 
-    now = Time.clean(Time.now())
+    for soup, url in soups:
+        sport = next((k for k, v in BASE_URLS.items() if v == url), "Live Event")
 
-    soup = HTMLParser(html_data.content)
+        for row in soup.css("tr.singele_match_date"):
+            if not (vs_node := row.css_first("td.teamvs a")):
+                continue
 
-    title = soup.css_first("title").text(strip=True)
+            event_name = vs_node.text(strip=True)
 
-    sport = "NFL" if "NFL" in title else "NHL"
+            for span in vs_node.css("span.mtdate"):
+                date = span.text(strip=True)
 
-    date_text = now.strftime("%B %d, %Y")
+                event_name = event_name.replace(date, "").strip()
 
-    if date_row := soup.css_first("tr.mdatetitle"):
+            if not (href := vs_node.attributes.get("href")):
-        if mtdate_span := date_row.css_first("span.mtdate"):
+                continue
-            date_text = mtdate_span.text(strip=True)
 
-    for row in soup.css("tr.singele_match_date"):
+            event = fix_event(event_name)
-        if not (time_node := row.css_first("td.matchtime")):
-            continue
 
-        time = time_node.text(strip=True)
+            if f"[{sport}] {event} ({TAG})" in cached_keys:
+                continue
 
-        if not (vs_node := row.css_first("td.teamvs a")):
+            events.append(
-            continue
+                {
-
+                    "sport": sport,
-        event_name = vs_node.text(strip=True)
+                    "event": event,
-
+                    "link": href,
-        for span in vs_node.css("span.mtdate"):
+                }
-            date = span.text(strip=True)
+            )
-
-            event_name = event_name.replace(date, "").strip()
-
-        if not (href := vs_node.attributes.get("href")):
-            continue
-
-        event_dt = Time.from_str(f"{date_text} {time} PM", timezone="EST")
-
-        event = fix_event(event_name)
-
-        key = f"[{sport}] {event} ({TAG})"
-
-        events[key] = {
-            "sport": sport,
-            "event": event,
-            "link": href,
-            "event_ts": event_dt.timestamp(),
-            "timestamp": now.timestamp(),
-        }
 
     return events
 
 
-async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
+async def scrape() -> None:
-    now = Time.clean(Time.now())
-
-    if not (events := HTML_CACHE.load()):
-        log.info("Refreshing HTML cache")
-
-        tasks = [refresh_html_cache(url) for url in BASE_URLS.values()]
-
-        results = await asyncio.gather(*tasks)
-
-        events = {k: v for data in results for k, v in data.items()}
-
-        HTML_CACHE.write(events)
-
-    live = []
-
-    start_ts = now.delta(minutes=-30).timestamp()
-    end_ts = now.delta(minutes=30).timestamp()
-
-    for k, v in events.items():
-        if k in cached_keys:
-            continue
-
-        if not start_ts <= v["event_ts"] <= end_ts:
-            continue
-
-        live.append(v)
-
-    return live
-
-
-async def scrape(browser: Browser) -> None:
     cached_urls = CACHE_FILE.load()
 
-    cached_count = len(cached_urls)
+    valid_urls = {k: v for k, v in cached_urls.items() if v["url"]}
 
-    urls.update(cached_urls)
+    valid_count = cached_count = len(valid_urls)
+
+    urls.update(valid_urls)
 
     log.info(f"Loaded {cached_count} event(s) from cache")
 
@@ -129,47 +129,45 @@ async def scrape(browser: Browser) -> None:
     if events:
         log.info(f"Processing {len(events)} new URL(s)")
 
-        async with network.event_context(browser) as context:
+        now = Time.clean(Time.now())
-            for i, ev in enumerate(events, start=1):
-                async with network.event_page(context) as page:
-                    handler = partial(
-                        network.process_event,
-                        url=(link := ev["link"]),
-                        url_num=i,
-                        page=page,
-                        log=log,
-                    )
 
-                    url = await network.safe_process(
+        for i, ev in enumerate(events, start=1):
-                        handler,
+            handler = partial(
-                        url_num=i,
+                process_event,
-                        semaphore=network.PW_S,
+                url=(link := ev["link"]),
-                        log=log,
+                url_num=i,
-                    )
+            )
 
-                    if url:
+            url = await network.safe_process(
-                        sport, event, ts = (
+                handler,
-                            ev["sport"],
+                url_num=i,
-                            ev["event"],
+                semaphore=network.PW_S,
-                            ev["event_ts"],
+                log=log,
-                        )
+            )
 
-                        key = f"[{sport}] {event} ({TAG})"
+            sport, event = ev["sport"], ev["event"]
 
-                        tvg_id, logo = leagues.get_tvg_info(sport, event)
+            key = f"[{sport}] {event} ({TAG})"
 
-                        entry = {
+            tvg_id, logo = leagues.get_tvg_info(sport, event)
-                            "url": url,
-                            "logo": logo,
-                            "base": BASE_URLS[sport],
-                            "timestamp": ts,
-                            "id": tvg_id or "Live.Event.us",
-                            "link": link,
-                        }
 
-                        urls[key] = cached_urls[key] = entry
+            entry = {
+                "url": url,
+                "logo": logo,
+                "base": BASE_URLS[sport],
+                "timestamp": now.timestamp(),
+                "id": tvg_id or "Live.Event.us",
+                "link": link,
+            }
 
-    if new_count := len(cached_urls) - cached_count:
+            cached_urls[key] = entry
+
+            if url:
+                valid_count += 1
+
+                urls[key] = entry
+
+    if new_count := valid_count - cached_count:
         log.info(f"Collected and cached {new_count} new event(s)")
 
     else:

M3U8/scrapers/xstreameast.py

@@ -81,10 +81,9 @@ async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
     if not (soups := [HTMLParser(html.content) for html in results if html]):
         return events
 
+    sport = "Live Event"
+
     for soup in soups:
-
-        sport = "Live Event"
-
         if sport_header := soup.css_first("h1.text-3xl"):
             header = sport_header.text(strip=True)
 

readme.md

@@ -1,13 +1,13 @@
-## Base Log @ 2026-02-27 09:06 UTC
+## Base Log @ 2026-02-28 08:50 UTC
 
 ### ✅ Working Streams: 157<br>❌ Dead Streams: 4
 
 | Channel | Error (Code) | Link |
 | ------- | ------------ | ---- |
 | BET | HTTP Error (404) | `http://212.102.60.231/BET/index.m3u8` |
+| Disney | HTTP Error (000) | `http://hardcoremedia.xyz/live/rabdsbmz/3731346838/257087.ts` |
+| FYI TV | HTTP Error (000) | `http://hardcoremedia.xyz/live/rabdsbmz/3731346838/130105.ts` |
 | Golf Channel | HTTP Error (000) | `http://hardcoremedia.xyz/live/rabdsbmz/3731346838/258721.ts` |
-| MSNBC | HTTP Error (404) | `http://41.205.93.154/MSNBC/index.m3u8` |
-| NBC Sports California | HTTP Error (403) | `http://hardcoremedia.xyz/live/rabdsbmz/3731346838/136474.ts` |
 ---
 #### Base Channels URL
 ```