update EPG

fix tvpass.py scraping

M3U8/fetch.py

@@ -18,9 +18,9 @@ from scrapers import (
     sport9,
     streambtw,
     streamcenter,
-    streamfree,
     streamhub,
     streamsgate,
+    totalsportek,
     tvpass,
     watchfooty,
     webcast,
@@ -70,6 +70,8 @@ async def main() -> None:
                 asyncio.create_task(streamcenter.scrape(xtrnl_brwsr)),
                 asyncio.create_task(streamhub.scrape(xtrnl_brwsr)),
                 asyncio.create_task(streamsgate.scrape(xtrnl_brwsr)),
+                asyncio.create_task(totalsportek.scrape(hdl_brwsr)),
+                asyncio.create_task(tvpass.scrape(hdl_brwsr)),
                 asyncio.create_task(webcast.scrape(hdl_brwsr)),
             ]
 
@@ -79,9 +81,7 @@ async def main() -> None:
                 asyncio.create_task(pawa.scrape()),
                 asyncio.create_task(shark.scrape()),
                 asyncio.create_task(streambtw.scrape()),
-                asyncio.create_task(streamfree.scrape()),
+                asyncio.create_task(xstreameast.scrape()),
-                asyncio.create_task(tvpass.scrape()),
-                # asyncio.create_task(xstreameast.scrape()),
             ]
 
             await asyncio.gather(*(pw_tasks + httpx_tasks))
@@ -111,9 +111,9 @@ async def main() -> None:
         | sport9.urls
         | streambtw.urls
         | streamcenter.urls
-        | streamfree.urls
         | streamhub.urls
         | streamsgate.urls
+        | totalsportek.urls
         | tvpass.urls
         | watchfooty.urls
         | webcast.urls

M3U8/scrapers/streambtw.py

@@ -1,7 +1,7 @@
 import base64
+import json
 import re
 from functools import partial
-from urllib.parse import urljoin
 
 from selectolax.parser import HTMLParser
 
@@ -53,26 +53,47 @@ async def get_events() -> list[dict[str, str]]:
 
     soup = HTMLParser(html_data.content)
 
-    for card in soup.css(".league"):
+    script_text = None
-        if not (league_elem := card.css_first(".league-title")):
-            continue
 
-        for event in card.css(".match"):
+    for s in soup.css("script"):
-            if not (match_elem := event.css_first(".match-name")):
+        t = s.text() or ""
-                continue
 
-            if (not (watch_btn := event.css_first("a.watch-btn"))) or (
+        if "const DATA" in t:
-                not (href := watch_btn.attributes.get("href"))
+            script_text = t
-            ):
+            break
-                continue
 
-            league, name = league_elem.text(strip=True), match_elem.text(strip=True)
+    if not script_text:
+        return events
+
+    if not (
+        match := re.search(r"const\s+DATA\s*=\s*(\[\s*.*?\s*\]);", script_text, re.S)
+    ):
+        return events
+
+    data_js = match[1].replace("\n      ", "").replace("\n    ", "")
+    s1 = re.sub(r"{\s", '{"', data_js)
+    s2 = re.sub(r':"', '":"', s1)
+    s3 = re.sub(r":\[", '":[', s2)
+    s4 = re.sub(r"},\]", "}]", s3)
+    s5 = re.sub(r'",\s', '","', s4)
+
+    data: list[dict[str, str]] = json.loads(s5)
+
+    for matches in data:
+        league = matches["title"]
+
+        items: list[dict[str, str]] = matches["items"]
+
+        for info in items:
+            title = info["title"]
+
+            url = info["url"]
 
             events.append(
                 {
                     "sport": fix_league(league),
-                    "event": name,
+                    "event": title,
-                    "link": urljoin(BASE_URL, href),
+                    "link": url,
                 }
             )
 

M3U8/scrapers/streamfree.py

@@ -1,85 +0,0 @@
-from urllib.parse import urljoin
-
-from .utils import Cache, Time, get_logger, leagues, network
-
-log = get_logger(__name__)
-
-urls: dict[str, dict[str, str | float]] = {}
-
-TAG = "STRMFREE"
-
-CACHE_FILE = Cache(TAG, exp=19_800)
-
-BASE_URL = "https://streamfree.to/"
-
-
-async def get_events() -> dict[str, dict[str, str | float]]:
-    events = {}
-
-    if not (
-        r := await network.request(
-            urljoin(BASE_URL, "streams"),
-            log=log,
-        )
-    ):
-        return events
-
-    api_data: dict = r.json()
-
-    now = Time.clean(Time.now())
-
-    for streams in api_data.get("streams", {}).values():
-        if not streams:
-            continue
-
-        for stream in streams:
-            sport, name, stream_key = (
-                stream.get("league"),
-                stream.get("name"),
-                stream.get("stream_key"),
-            )
-
-            if not (sport and name and stream_key):
-                continue
-
-            key = f"[{sport}] {name} ({TAG})"
-
-            tvg_id, logo = leagues.get_tvg_info(sport, name)
-
-            events[key] = {
-                "url": network.build_proxy_url(
-                    tag=TAG,
-                    path=f"{stream_key}/index.m3u8",
-                    query={"stream_name": name},
-                ),
-                "logo": logo,
-                "base": BASE_URL,
-                "timestamp": now.timestamp(),
-                "id": tvg_id or "Live.Event.us",
-            }
-
-    return events
-
-
-async def scrape() -> None:
-    if cached := CACHE_FILE.load():
-        urls.update(cached)
-
-        log.info(f"Loaded {len(urls)} event(s) from cache")
-
-        return
-
-    log.info(f'Scraping from "{BASE_URL}"')
-
-    events = await network.safe_process(
-        get_events,
-        url_num=1,
-        semaphore=network.HTTP_S,
-        log=log,
-    )
-
-    urls.update(events or {})
-
-    CACHE_FILE.write(urls)
-
-    log.info(f"Collected and cached {len(urls)} new event(s)")

M3U8/scrapers/totalsportek.py

@@ -0,0 +1,147 @@
+from functools import partial
+from urllib.parse import urljoin, urlparse
+
+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 = "TOTALSPRTK"
+
+CACHE_FILE = Cache(TAG, exp=28_800)
+
+BASE_URL = "https://live3.totalsportek777.com/"
+
+
+def fix_txt(s: str) -> str:
+    s = " ".join(s.split())
+
+    return s.upper() if s.islower() else s
+
+
+async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
+    events = []
+
+    if not (html_data := await network.request(BASE_URL, log=log)):
+        return events
+
+    soup = HTMLParser(html_data.content)
+
+    sport = "Live Event"
+
+    for node in soup.css("a"):
+        if not node.attributes.get("class"):
+            continue
+
+        if (parent := node.parent) and "my-1" in parent.attributes.get("class", ""):
+            if span := node.css_first("span"):
+                sport = span.text(strip=True)
+
+        sport = fix_txt(sport)
+
+        if not (teams := [t.text(strip=True) for t in node.css(".col-7 .col-12")]):
+            continue
+
+        if not (href := node.attributes.get("href")):
+            continue
+
+        href = urlparse(href).path if href.startswith("http") else href
+
+        if not (time_node := node.css_first(".col-3 span")):
+            continue
+
+        if time_node.text(strip=True) != "MatchStarted":
+            continue
+
+        event_name = fix_txt(" vs ".join(teams))
+
+        if f"[{sport}] {event_name} ({TAG})" in cached_keys:
+            continue
+
+        events.append(
+            {
+                "sport": sport,
+                "event": 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}"')
+
+    events = await get_events(cached_urls.keys())
+
+    log.info(f"Processing {len(events)} new URL(s)")
+
+    if events:
+        now = Time.clean(Time.now())
+
+        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=ev["link"],
+                        url_num=i,
+                        page=page,
+                        log=log,
+                    )
+
+                    url = await network.safe_process(
+                        handler,
+                        url_num=i,
+                        semaphore=network.PW_S,
+                        log=log,
+                        timeout=6,
+                    )
+
+                    sport, event, link = (
+                        ev["sport"],
+                        ev["event"],
+                        ev["link"],
+                    )
+
+                    key = f"[{sport}] {event} ({TAG})"
+
+                    tvg_id, logo = leagues.get_tvg_info(sport, event)
+
+                    entry = {
+                        "url": url,
+                        "logo": logo,
+                        "base": link,
+                        "timestamp": now.timestamp(),
+                        "id": tvg_id or "Live.Event.us",
+                        "link": link,
+                    }
+
+                    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:
+        log.info("No new events found")
+
+    CACHE_FILE.write(cached_urls)

M3U8/scrapers/tvpass.py

@@ -1,4 +1,8 @@
-import re
+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
 
@@ -8,73 +12,144 @@ urls: dict[str, dict[str, str | float]] = {}
 
 TAG = "TVPASS"
 
-CACHE_FILE = Cache(TAG, exp=86_400)
+CACHE_FILE = Cache(TAG, exp=10_800)
 
-BASE_URL = "https://tvpass.org/playlist/m3u"
+HTML_CACHE = Cache(f"{TAG}-html", exp=28_800)
+
+BASE_URL = "https://thetvapp.to"
 
 
-async def get_events() -> dict[str, dict[str, str | float]]:
+async def refresh_html_cache(now_ts: float) -> dict[str, dict[str, str | float]]:
+    log.info("Refreshing HTML cache")
+
     events = {}
 
-    if not (r := await network.request(BASE_URL, log=log)):
+    if not (html_data := await network.request(BASE_URL, log=log)):
         return events
 
-    now = Time.clean(Time.now())
+    soup = HTMLParser(html_data.content)
 
-    data = r.text.splitlines()
+    for row in soup.css(".row"):
+        if not (h3_elem := row.css_first("h3")):
+            continue
 
-    for i, line in enumerate(data, start=1):
+        sport = h3_elem.text(strip=True)
-        if line.startswith("#EXTINF"):
-            tvg_id_match = re.search(r'tvg-id="([^"]*)"', line)
 
-            tvg_name_match = re.search(r'tvg-name="([^"]*)"', line)
+        if sport.lower() == "live tv channels":
+            continue
 
-            group_title_match = re.search(r'group-title="([^"]*)"', line)
+        for a in row.css("a.list-group-item[href]"):
+            if not (href := a.attributes.get("href")):
+                continue
 
-            tvg = tvg_id_match[1] if tvg_id_match else None
+            if not (span := a.css_first("span")):
+                continue
 
-            if not tvg and (url := data[i]).endswith("/sd"):
+            event_time = span.text(strip=True)
-                if tvg_name := tvg_name_match[1]:
-                    sport = group_title_match[1].upper().strip()
 
-                    event = "(".join(tvg_name.split("(")[:-1]).strip()
+            event_dt = Time.from_str(event_time, timezone="UTC")
 
-                    key = f"[{sport}] {event} ({TAG})"
+            event_name = a.text(strip=True).split(":")[0]
 
-                    channel = url.split("/")[-2]
+            key = f"[{sport}] {event_name} ({TAG})"
 
-                    tvg_id, logo = leagues.info(sport)
+            events[key] = {
-
+                "sport": sport,
-                    events[key] = {
+                "event": event_name,
-                        "url": f"http://origin.thetvapp.to/hls/{channel}/mono.m3u8",
+                "link": urljoin(BASE_URL, href),
-                        "logo": logo,
+                "event_ts": event_dt.timestamp(),
-                        "id": tvg_id or "Live.Event.us",
+                "timestamp": now_ts,
-                        "base": "https://tvpass.org",
+            }
-                        "timestamp": now.timestamp(),
-                    }
 
     return events
 
 
-async def scrape() -> None:
+async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
-    if cached := CACHE_FILE.load():
+    now = Time.clean(Time.now())
-        urls.update(cached)
 
-        log.info(f"Loaded {len(urls)} event(s) from cache")
+    if not (events := HTML_CACHE.load()):
+        events = await refresh_html_cache(now.timestamp())
 
-        return
+        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)
+
+    urls.update(cached_urls)
+
+    log.info(f"Loaded {cached_count} event(s) from cache")
 
     log.info(f'Scraping from "{BASE_URL}"')
 
-    events = await network.safe_process(
+    events = await get_events(cached_urls.keys())
-        get_events,
-        url_num=1,
-        semaphore=network.HTTP_S,
-        log=log,
-    )
 
-    urls.update(events or {})
+    log.info(f"Processing {len(events)} new URL(s)")
 
-    CACHE_FILE.write(urls)
+    if events:
+        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=ev["link"],
+                        url_num=i,
+                        page=page,
+                        log=log,
+                    )
 
-    log.info(f"Collected and cached {len(urls)} new event(s)")
+                    url = await network.safe_process(
+                        handler,
+                        url_num=i,
+                        semaphore=network.PW_S,
+                        log=log,
+                    )
+
+                    if url:
+                        sport, event, ts, link = (
+                            ev["sport"],
+                            ev["event"],
+                            ev["event_ts"],
+                            ev["link"],
+                        )
+
+                        key = f"[{sport}] {event} ({TAG})"
+
+                        tvg_id, logo = leagues.get_tvg_info(sport, event)
+
+                        entry = {
+                            "url": url,
+                            "logo": logo,
+                            "base": BASE_URL,
+                            "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/utils/config.py

@@ -100,6 +100,7 @@ class Time(datetime):
                 "%Y-%m-%d %I:%M %p",
                 "%Y-%m-%d %H:%M %p",
                 "%Y-%m-%dT%H:%M:%S",
+                "%Y-%m-%dT%H:%M:%SZ",
                 "%Y-%m-%dT%H:%M:%S.%fZ",
                 "%Y/%m/%d %H:%M",
                 "%Y/%m/%d %H:%M:%S",

M3U8/scrapers/utils/webwork.py

@@ -6,7 +6,6 @@ from collections.abc import Awaitable, Callable
 from contextlib import asynccontextmanager
 from functools import partial
 from typing import AsyncGenerator, TypeVar
-from urllib.parse import urlencode, urljoin
 
 import httpx
 from playwright.async_api import Browser, BrowserContext, Page, Playwright, Request
@@ -39,21 +38,6 @@ class Network:
             http2=True,
         )
 
-    @staticmethod
-    def build_proxy_url(
-        tag: str,
-        path: str,
-        query: dict | None = None,
-    ) -> str:
-
-        tag = tag.lower()
-
-        return (
-            f"{urljoin(network.proxy_base, f'{tag}/{path}')}?{urlencode(query)}"
-            if query
-            else urljoin(network.proxy_base, f"{tag}/{path}")
-        )
-
     async def request(
         self,
         url: str,

M3U8/scrapers/watchfooty.py

@@ -76,7 +76,7 @@ async def process_event(
     page: Page,
 ) -> tuple[str | None, str | None]:
 
-    nones = [None for _ in range(2)]
+    nones = None, None
 
     pattern = re.compile(r"\((\d+)\)")
 

M3U8/scrapers/xstreameast.py

@@ -30,9 +30,9 @@ SPORT_ENDPOINTS = [
 
 
 async def process_event(url: str, url_num: int) -> tuple[str | None, str | None]:
-    valid_m3u8 = re.compile(r'var\s+(\w+)\s*=\s*"([^"]*)"', re.IGNORECASE)
+    valid_m3u8 = re.compile(r'(var|const)\s+(\w+)\s*=\s*"([^"]*)"', re.IGNORECASE)
 
-    nones = [None for _ in range(2)]
+    nones = None, None
 
     if not (html_data := await network.request(url, log=log)):
         log.info(f"URL {url_num}) Failed to load url.")
@@ -58,9 +58,12 @@ async def process_event(url: str, url_num: int) -> tuple[str | None, str | None]
         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(match[2]).decode("utf-8"), iframe_src
+    return bytes.fromhex(encoded).decode("utf-8"), iframe_src
 
 
 async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:

readme.md

@@ -1,11 +1,16 @@
-## Base Log @ 2026-02-07 04:18 UTC
+## Base Log @ 2026-02-08 04:41 UTC
 
-### ✅ Working Streams: 144<br>❌ Dead Streams: 2
+### ✅ Working Streams: 139<br>❌ Dead Streams: 7
 
 | Channel | Error (Code) | Link |
 | ------- | ------------ | ---- |
 | CW | HTTP Error (404) | `https://fl1.moveonjoy.com/CW_ORLANDO/index.m3u8` |
+| ESPN | HTTP Error (404) | `http://41.205.93.154/ESPN/index.m3u8` |
 | FXX | HTTP Error (404) | `https://fl1.moveonjoy.com/FXX/index.m3u8` |
+| Spectrum SportsNet LA Dodgers | HTTP Error (403) | `http://mytvstream.net:8080/live/bn80NG/909467/31636.m3u8` |
+| Sportsnet 360 | HTTP Error (403) | `http://mytvstream.net:8080/live/bn80NG/909467/2219.m3u8` |
+| Sportsnet One | HTTP Error (403) | `http://mytvstream.net:8080/live/bn80NG/909467/57297.m3u8` |
+| TSN1 | HTTP Error (403) | `http://mytvstream.net:8080/live/bn80NG/909467/57292.m3u8` |
 ---
 #### Base Channels URL
 ```