update M3U8

M3U8/fetch.py

@@ -17,7 +17,6 @@ from scrapers import (
     streamsgate,
     streamtpnew,
     totalsportek,
-    tvapp,
     watchfooty,
     webcast,
     xyzstream,
@@ -71,7 +70,6 @@ async def main() -> None:
                 asyncio.create_task(streamsgate.scrape()),
                 asyncio.create_task(streamtpnew.scrape()),
                 asyncio.create_task(totalsportek.scrape()),
-                # asyncio.create_task(tvapp.scrape()),
                 asyncio.create_task(webcast.scrape()),
                 asyncio.create_task(xyzstream.scrape()),
             ]
@@ -102,7 +100,6 @@ async def main() -> None:
         | streamsgate.urls
         | streamtpnew.urls
         | totalsportek.urls
-        | tvapp.urls
         | watchfooty.urls
         | webcast.urls
         | xyzstream.urls

M3U8/scrapers/tvapp.py

@@ -1,140 +0,0 @@
-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 = "TVAPP"
-
-CACHE_FILE = Cache(TAG, exp=86_400)
-
-BASE_URL = "https://thetvapp.to"
-
-
-async def process_event(url: str, url_num: int) -> str | None:
-    if not (html_data := await network.request(url, log=log)):
-        log.warning(f"URL {url_num}) Failed to load url.")
-
-        return
-
-    soup = HTMLParser(html_data.content)
-
-    if not (channel_name_elem := soup.css_first("#stream_name")):
-        log.warning(f"URL {url_num}) No channel name elem found.")
-
-        return
-
-    if not (channel_name := channel_name_elem.attributes.get("name")):
-        log.warning(f"URL {url_num}) No channel name found.")
-
-        return
-
-    log.info(f"URL {url_num}) Captured M3U8")
-
-    return f"https://tvpass.org/live/{channel_name.strip()}/sd"
-
-
-async def get_events() -> list[dict[str, str]]:
-    events = []
-
-    if not (html_data := await network.request(BASE_URL, log=log)):
-        return events
-
-    now = Time.clean(Time.now())
-
-    soup = HTMLParser(html_data.content)
-
-    for row in soup.css(".row"):
-        if not (h3_elem := row.css_first("h3")):
-            continue
-
-        if (sport := h3_elem.text(strip=True)).lower() == "live tv channels":
-            continue
-
-        for a in row.css("a.list-group-item[href]"):
-            x, y = a.text(strip=True).split(":", 1)
-
-            event_name = x.split("@")[0].strip()
-
-            event_dt = Time.from_str(y.split(":", 1)[-1], timezone="UTC")
-
-            if event_dt.date() != now.date():
-                continue
-
-            if not (href := a.attributes.get("href")):
-                continue
-
-            events.append(
-                {
-                    "sport": sport,
-                    "event": event_name,
-                    "link": urljoin(f"{html_data.url}", href),
-                    "timestamp": now.timestamp(),
-                }
-            )
-
-    return events
-
-
-async def scrape() -> None:
-    if cached_urls := CACHE_FILE.load():
-        urls.update({k: v for k, v in cached_urls.items() if v["url"]})
-
-        log.info(f"Loaded {len(urls)} event(s) from cache")
-
-        return
-
-    log.info(f'Scraping from "{BASE_URL}"')
-
-    if events := await get_events():
-        log.info(f"Processing {len(events)} URL(s)")
-
-        for i, ev in enumerate(events, start=1):
-            handler = partial(
-                process_event,
-                url=(link := ev["link"]),
-                url_num=i,
-            )
-
-            url = 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": BASE_URL,
-                "timestamp": ts,
-                "id": tvg_id or "Live.Event.us",
-                "link": link,
-            }
-
-            cached_urls[key] = entry
-
-            if url:
-                urls[key] = entry
-
-        log.info(f"Collected and cached {len(urls)} event(s)")
-
-    else:
-        log.info("No events found")
-
-    CACHE_FILE.write(cached_urls)