update M3U8

- re-add xstreameast.py

M3U8/fetch.py

@@ -8,9 +8,7 @@ from scrapers import (
     cdnlivetv,
     embedhd,
     fawa,
-    fsports,
     istreameast,
-    listapreta,
     livetvsx,
     mainportal,
     ovogoal,
@@ -26,6 +24,7 @@ from scrapers import (
     tvapp,
     watchfooty,
     webcast,
+    xstreameast,
 )
 from scrapers.utils import get_logger, network
 
@@ -64,7 +63,6 @@ async def main() -> None:
             pw_tasks = [
                 asyncio.create_task(cdnlivetv.scrape(hdl_brwsr)),
                 asyncio.create_task(embedhd.scrape(hdl_brwsr)),
-                # asyncio.create_task(fsports.scrape(xtrnl_brwsr)),
                 asyncio.create_task(ppv.scrape(xtrnl_brwsr)),
                 asyncio.create_task(roxie.scrape(hdl_brwsr)),
             ]
@@ -72,7 +70,6 @@ async def main() -> None:
             httpx_tasks = [
                 asyncio.create_task(fawa.scrape()),
                 asyncio.create_task(istreameast.scrape()),
-                # asyncio.create_task(listapreta.scrape()),
                 asyncio.create_task(mainportal.scrape()),
                 asyncio.create_task(ovogoal.scrape()),
                 asyncio.create_task(pawa.scrape()),
@@ -84,6 +81,7 @@ async def main() -> None:
                 asyncio.create_task(totalsportek.scrape()),
                 asyncio.create_task(tvapp.scrape()),
                 asyncio.create_task(webcast.scrape()),
+                asyncio.create_task(xstreameast.scrape()),
             ]
 
             await asyncio.gather(*(pw_tasks + httpx_tasks))
@@ -103,9 +101,7 @@ async def main() -> None:
         cdnlivetv.urls
         | embedhd.urls
         | fawa.urls
-        | fsports.urls
         | istreameast.urls
-        | listapreta.urls
         | livetvsx.urls
         | mainportal.urls
         | ovogoal.urls
@@ -121,6 +117,7 @@ async def main() -> None:
         | tvapp.urls
         | watchfooty.urls
         | webcast.urls
+        | xstreameast.urls
     )
 
     live_events: list[str] = []

M3U8/scrapers/fsports.py

@@ -1,143 +0,0 @@
-import asyncio
-from functools import partial
-from urllib.parse import urljoin
-
-from playwright.async_api import Browser
-from selectolax.parser import HTMLParser
-
-from .utils import Cache, Time, get_logger, leagues, network
-
-log = get_logger(__name__)
-
-urls: dict[str, dict[str, str | float]] = {}
-
-TAG = "FSPRTS"
-
-CACHE_FILE = Cache(TAG, exp=5_400)
-
-BASE_URL = "https://fsportshds.xyz"
-
-SPORT_URLS = {
-    # "Fighting": urljoin(BASE_URL, "mmastreams.php"),
-    "Basketball": urljoin(BASE_URL, "nbastreams.php"),
-    # "Ice Hockey": urljoin(BASE_URL, "nhlstreams.php"),
-    # "American Football": urljoin(BASE_URL, "nflstreams.php")
-} | {
-    sport: urljoin(BASE_URL, f"{sport}streams.php".lower())
-    for sport in [
-        "Football",
-        # "Boxing",
-        # "F1",
-        # "MLB",
-        # "MotoGP",
-    ]
-}
-
-
-async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
-    tasks = [network.request(url, log=log) for url in SPORT_URLS.values()]
-
-    results = await asyncio.gather(*tasks)
-
-    events = []
-
-    if not (
-        soups := [(HTMLParser(html.content), html.url) for html in results if html]
-    ):
-        return events
-
-    for soup, url in soups:
-        sport = next((k for k, v in SPORT_URLS.items() if v == url), "Live Event")
-
-        for card in soup.css(".media.btn.btn-default.btn-lg.btn-block"):
-            if not (name_elem := card.css_first("h4")):
-                continue
-
-            if card.css_first('[id^="countdown-"]'):
-                continue
-
-            if not (a_elem := card.css_first("a")) or not (
-                href := a_elem.attributes.get("href")
-            ):
-                continue
-
-            name = name_elem.text(strip=True)
-
-            if f"[{sport}] {name} ({TAG})" in cached_keys:
-                continue
-
-            events.append(
-                {
-                    "sport": sport,
-                    "event": name,
-                    "link": urljoin(BASE_URL, href),
-                }
-            )
-
-    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)")
-
-        now = Time.clean(Time.now())
-
-        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(
-                        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,
-                    )
-
-                    sport, event = ev["sport"], ev["event"]
-
-                    key = f"[{sport}] {event} ({TAG})"
-
-                    tvg_id, logo = leagues.get_tvg_info(sport, event)
-
-                    entry = {
-                        "url": url,
-                        "logo": logo,
-                        "base": "https://vividmosaica.com/",
-                        "timestamp": now.timestamp(),
-                        "id": tvg_id or "Live.Event.us",
-                        "link": link,
-                    }
-
-                    cached_urls[key] = entry
-
-                    if url:
-                        valid_count += 1
-
-                        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)

M3U8/scrapers/listapreta.py

@@ -1,171 +0,0 @@
-from functools import partial
-
-from .utils import Cache, Time, get_logger, leagues, network
-
-log = get_logger(__name__)
-
-urls: dict[str, dict[str, str | float]] = {}
-
-TAG = "LISTA"
-
-CACHE_FILE = Cache(TAG, exp=28_800)
-
-API_URL = "https://listapreta.site/sports-widget/events.php"
-
-
-async def process_event(url: str, url_num: int) -> tuple[str | None, str | None]:
-    nones = None, None
-
-    event_id = url.split("id=")[-1]
-
-    if not (
-        token_req := await network.request(
-            "https://lista-preta-tv.site/generate_token.php",
-            params={"id": event_id},
-            log=log,
-        )
-    ):
-        log.warning(f"URL {url_num}) Failed to load token data.")
-        return nones
-
-    if not (token_data := token_req.json()):
-        log.warning(f"URL {url_num}) No token data available.")
-        return nones
-
-    elif not (token := token_data.get("token")) or not (exp := token_data.get("exp")):
-        log.warning(f"URL {url_num}) No token data available.")
-        return nones
-
-    ref = f"https://lista-preta-tv.site/player-all.html?id={event_id}"
-
-    if not (
-        m3u8_req := await network.request(
-            "https://lista-preta-tv.site/m3u8.php",
-            headers={"Referer": ref},
-            params={"id": event_id, "token": token, "exp": exp},
-            follow_redirects=False,
-            log=log,
-        )
-    ):
-        log.warning(f"URL {url_num}) Unable to fetch M3U8 request.")
-        return nones
-
-    elif not (m3u8 := m3u8_req.headers.get("Location")):
-        log.warning(f"URL {url_num}) Unable to fetch M3U8 request.")
-        return nones
-
-    log.info(f"URL {url_num}) Captured M3U8")
-
-    return m3u8, ref
-
-
-async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
-    now = Time.clean(Time.now())
-
-    events = []
-
-    if not (api_req := await network.request(API_URL, log=log)):
-        return events
-
-    elif not (api_data := api_req.json()) or api_data.get("error"):
-        return events
-
-    for event in api_data:
-        sport = event.get("sport")
-
-        t1, t2 = event.get("home"), event.get("away")
-
-        if not (sport and t1 and t2):
-            continue
-
-        event_name = f"{t1} vs {t2}"
-
-        if f"[{sport}] {event_name} ({TAG})" in cached_keys:
-            continue
-
-        event_dt = Time.from_str(event["start"], timezone="UTC")
-
-        if event_dt.date() != now.date():
-            continue
-
-        if not (channels := event.get("channels")):
-            continue
-
-        event_links: list[str] = [channel["url"] for channel in channels]
-
-        link = event_links[0]
-
-        events.append(
-            {
-                "sport": sport,
-                "event": event_name,
-                "link": link,
-                "timestamp": now.timestamp(),
-            }
-        )
-
-    return events
-
-
-async def scrape() -> 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('Scraping from "https://listapreta.site"')
-
-    if events := await get_events(cached_urls.keys()):
-        log.info(f"Processing {len(events)} new URL(s)")
-
-        for i, ev in enumerate(events, start=1):
-            handler = partial(
-                process_event,
-                url=(link := ev["link"]),
-                url_num=i,
-            )
-
-            url, iframe = await network.safe_process(
-                handler,
-                url_num=i,
-                semaphore=network.HTTP_S,
-                log=log,
-            )
-
-            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": iframe,
-                "timestamp": ts,
-                "id": tvg_id or "Live.Event.us",
-                "link": link,
-            }
-
-            cached_urls[key] = entry
-
-            if url:
-                valid_count += 1
-
-                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)

M3U8/scrapers/streamcenter.py

@@ -10,7 +10,7 @@ urls: dict[str, dict[str, str | float]] = {}
 
 TAG = "STRMCNTR"
 
-CACHE_FILE = Cache(TAG, exp=19_800)
+CACHE_FILE = Cache(TAG, exp=28_800)
 
 API_URL = "https://backend.streamcenter.live/api/Parties"
 

M3U8/scrapers/xstreameast.py

@@ -0,0 +1,179 @@
+import asyncio
+import re
+from functools import partial
+from urllib.parse import urljoin
+
+from selectolax.parser import HTMLParser
+
+from .utils import Cache, Time, get_logger, leagues, network
+
+log = get_logger(__name__)
+
+urls: dict[str, dict[str, str | float]] = {}
+
+TAG = "XSTRMEST"
+
+CACHE_FILE = Cache(TAG, exp=10_800)
+
+BASE_URL = "https://xstreameast.com"
+
+SPORT_URLS = [
+    urljoin(BASE_URL, f"categories/{sport}/")
+    for sport in [
+        # "mlb",
+        "mma",
+        "nba",
+        # "nfl",
+        # "nhl",
+        "soccer",
+        "wwe",
+    ]
+]
+
+
+async def process_event(url: str, url_num: int) -> tuple[str | None, str | None]:
+    nones = None, None
+
+    if not (html_data := await network.request(url, log=log)):
+        log.warning(f"URL {url_num}) Failed to load url.")
+        return nones
+
+    soup = HTMLParser(html_data.content)
+
+    iframe = soup.css_first("iframe")
+
+    if not iframe or not (iframe_src := iframe.attributes.get("src")):
+        log.warning(f"URL {url_num}) No iframe element found.")
+        return nones
+
+    elif iframe_src == "about:blank":
+        log.warning(f"URL {url_num}) No iframe element found.")
+        return nones
+
+    if not (iframe_src_data := await network.request(iframe_src, log=log)):
+        log.warning(f"URL {url_num}) Failed to load iframe source.")
+        return nones
+
+    valid_m3u8 = re.compile(r'(var|const)\s+(\w+)\s*=\s*"([^"]*)"', re.I)
+
+    if not (match := valid_m3u8.search(iframe_src_data.text)):
+        log.warning(f"URL {url_num}) No Clappr source found.")
+        return nones
+
+    if len(encoded := match[2]) < 20:
+        encoded = match[3]
+
+    log.info(f"URL {url_num}) Captured M3U8")
+
+    return bytes.fromhex(encoded).decode("utf-8"), iframe_src
+
+
+async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
+    tasks = [network.request(url, log=log) for url in SPORT_URLS]
+
+    results = await asyncio.gather(*tasks)
+
+    events = []
+
+    if not (soups := [HTMLParser(html.content) for html in results if html]):
+        return events
+
+    sport = "Live Event"
+
+    for soup in soups:
+        if sport_header := soup.css_first("h1.text-3xl"):
+            header = sport_header.text(strip=True)
+
+            sport = header.split("Streams")[0].strip()
+
+        for card in soup.css("article.game-card"):
+            if not (team_elem := card.css_first("h2.text-xl.font-semibold")):
+                continue
+
+            if not (link_elem := card.css_first("a.stream-button")) or not (
+                href := link_elem.attributes.get("href")
+            ):
+                continue
+
+            if (
+                not (live_badge := card.css_first("span.bg-green-600"))
+                or live_badge.text(strip=True) != "LIVE"
+            ):
+                continue
+
+            event_name = team_elem.text(strip=True)
+
+            if f"[{sport}] {event_name} ({TAG})" in cached_keys:
+                continue
+
+            events.append(
+                {
+                    "sport": sport,
+                    "event": event_name,
+                    "link": href,
+                }
+            )
+
+    return events
+
+
+async def scrape() -> 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)")
+
+        now = Time.clean(Time.now())
+
+        for i, ev in enumerate(events, start=1):
+            handler = partial(
+                process_event,
+                url=(link := ev["link"]),
+                url_num=i,
+            )
+
+            url, iframe = await network.safe_process(
+                handler,
+                url_num=i,
+                semaphore=network.HTTP_S,
+                log=log,
+            )
+
+            sport, event = ev["sport"], ev["event"]
+
+            key = f"[{sport}] {event} ({TAG})"
+
+            tvg_id, logo = leagues.get_tvg_info(sport, event)
+
+            entry = {
+                "url": url,
+                "logo": logo,
+                "base": iframe,
+                "timestamp": now.timestamp(),
+                "id": tvg_id or "Live.Event.us",
+                "link": link,
+            }
+
+            cached_urls[key] = entry
+
+            if url:
+                valid_count += 1
+
+                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

@@ -1,21 +1,14 @@
-## Base Log @ 2026-04-15 15:46 UTC
+## Base Log @ 2026-04-16 09:55 UTC
 
-### ✅ Working Streams: 149<br>❌ Dead Streams: 12
+### ✅ Working Streams: 156<br>❌ Dead Streams: 5
 
 | Channel | Error (Code) | Link |
 | ------- | ------------ | ---- |
-| Aspire | HTTP Error (404) | `http://iptvtree.net:8080/live/7e4b0dbd/1dd755dc3f/150605.ts` |
+| FDSN Ohio | HTTP Error (404) | `http://iptvtree.net:8080/live/7e4b0dbd/1dd755dc3f/296675.ts` |
-| Comedy TV | HTTP Error (404) | `http://iptvtree.net:8080/live/7e4b0dbd/1dd755dc3f/199482.ts` |
-| Cozi TV | HTTP Error (404) | `http://iptvtree.net:8080/live/7e4b0dbd/1dd755dc3f/8392.ts` |
 | FX Movie Channel | HTTP Error (404) | `http://iptvtree.net:8080/live/7e4b0dbd/1dd755dc3f/39873.ts` |
-| Game Show Network | HTTP Error (404) | `http://iptvtree.net:8080/live/7e4b0dbd/1dd755dc3f/466.ts` |
+| Hallmark Family | HTTP Error (404) | `http://iptvtree.net:8080/live/7e4b0dbd/1dd755dc3f/304609.ts` |
-| HBO Family | HTTP Error (404) | `http://iptvtree.net:8080/live/7e4b0dbd/1dd755dc3f/760.ts` |
+| NBC Sports Bay Area | HTTP Error (404) | `http://iptvtree.net:8080/live/7e4b0dbd/1dd755dc3f/45785.ts` |
-| Lifetime | HTTP Error (404) | `http://iptvtree.net:8080/live/7e4b0dbd/1dd755dc3f/4667.ts` |
+| TLC | HTTP Error (404) | `http://iptvtree.net:8080/live/7e4b0dbd/1dd755dc3f/2362.ts` |
-| NBC Sports Boston | HTTP Error (404) | `http://iptvtree.net:8080/live/7e4b0dbd/1dd755dc3f/35132.ts` |
-| Nick Jr | HTTP Error (404) | `http://iptvtree.net:8080/live/7e4b0dbd/1dd755dc3f/14835.ts` |
-| TV One | HTTP Error (404) | `http://iptvtree.net:8080/live/7e4b0dbd/1dd755dc3f/13010.ts` |
-| The Weather Channel | HTTP Error (404) | `http://iptvtree.net:8080/live/7e4b0dbd/1dd755dc3f/2361.ts` |
-| YES Network | HTTP Error (404) | `http://iptvtree.net:8080/live/7e4b0dbd/1dd755dc3f/5519.ts` |
 ---
 #### Base Channels URL
 ```