e

change base url for totalsportek.py (duplicate source)

M3U8/fetch.py

@@ -71,6 +71,7 @@ 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(webcast.scrape(hdl_brwsr)),
                 asyncio.create_task(watchfooty.scrape(xtrnl_brwsr)),
             ]
@@ -83,7 +84,6 @@ async def main() -> None:
                 asyncio.create_task(shark.scrape()),
                 # asyncio.create_task(streambtw.scrape()),
                 asyncio.create_task(streamfree.scrape()),
-                asyncio.create_task(totalsportek.scrape()),
                 asyncio.create_task(tvpass.scrape()),
                 asyncio.create_task(xstreameast.scrape()),
             ]

M3U8/scrapers/totalsportek.py

@@ -1,7 +1,7 @@
-import re
 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
@@ -12,18 +12,9 @@ urls: dict[str, dict[str, str | float]] = {}
 
 TAG = "TOTALSPRTK"
 
-CACHE_FILE = Cache(f"{TAG.lower()}", exp=28_800)
+CACHE_FILE = Cache(TAG, exp=28_800)
 
-MIRRORS = [
+BASE_URL = "https://live3.totalsportek777.com/"
-    {
-        "base": "https://live.totalsportek777.com/",
-        "hex_decode": True,
-    },
-    {
-        "base": "https://live2.totalsportek777.com/",
-        "hex_decode": False,
-    },
-]
 
 
 def fix_txt(s: str) -> str:
@@ -32,59 +23,10 @@ def fix_txt(s: str) -> str:
     return s.upper() if s.islower() else s
 
 
-async def process_event(href: str, url_num: int) -> tuple[str | None, str | None]:
+async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
-    valid_m3u8 = re.compile(r'var\s+(\w+)\s*=\s*"([^"]*)"', re.IGNORECASE)
-
-    for x, mirror in enumerate(MIRRORS, start=1):
-        base: str = mirror["base"]
-
-        hex_decode: bool = mirror["hex_decode"]
-
-        url = urljoin(base, href)
-
-        if not (html_data := await network.request(url, log=log)):
-            log.info(f"M{x} | URL {url_num}) Failed to load url.")
-
-            return None, None
-
-        soup = HTMLParser(html_data.content)
-
-        iframe = soup.css_first("iframe")
-
-        if not iframe or not (iframe_src := iframe.attributes.get("src")):
-            log.warning(f"M{x} | URL {url_num}) No iframe element found.")
-            continue
-
-        if not (iframe_src_data := await network.request(iframe_src, log=log)):
-            log.warning(f"M{x} | URL {url_num}) Failed to load iframe source.")
-            continue
-
-        if not (match := valid_m3u8.search(iframe_src_data.text)):
-            log.warning(f"M{x} | URL {url_num}) No Clappr source found.")
-            continue
-
-        raw: str = match[2]
-
-        try:
-            m3u8_url = bytes.fromhex(raw).decode("utf-8") if hex_decode else raw
-        except Exception as e:
-            log.warning(f"M{x} | URL {url_num}) Decoding failed: {e}")
-            continue
-
-        if m3u8_url and iframe_src:
-            log.info(f"M{x} | URL {url_num}) Captured M3U8")
-
-            return m3u8_url, iframe_src
-
-        log.warning(f"M{x} | URL {url_num}) No M3U8 found")
-
-    return None, None
-
-
-async def get_events(url: str, cached_keys: list[str]) -> list[dict[str, str]]:
     events = []
 
-    if not (html_data := await network.request(url, log=log)):
+    if not (html_data := await network.request(BASE_URL, log=log)):
         return events
 
     soup = HTMLParser(html_data.content)
@@ -124,14 +66,14 @@ async def get_events(url: str, cached_keys: list[str]) -> list[dict[str, str]]:
             {
                 "sport": sport,
                 "event": event_name,
-                "href": href,
+                "link": urljoin(BASE_URL, href),
             }
         )
 
     return events
 
 
-async def scrape() -> None:
+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"]}
@@ -142,61 +84,59 @@ async def scrape() -> None:
 
     log.info(f"Loaded {cached_count} event(s) from cache")
 
-    if not (base_url := await network.get_base([mirr["base"] for mirr in MIRRORS])):
+    log.info(f'Scraping from "{BASE_URL}"')
-        log.warning("No working TotalSportek mirrors")
 
-        CACHE_FILE.write(cached_urls)
+    events = await get_events(cached_urls.keys())
-
-        return
-
-    log.info(f'Scraping from "{base_url}"')
-
-    events = await get_events(base_url, cached_urls.keys())
 
     log.info(f"Processing {len(events)} new URL(s)")
 
     if events:
         now = Time.clean(Time.now())
 
-        for i, ev in enumerate(events, start=1):
+        async with network.event_context(browser) as context:
-            handler = partial(
+            for i, ev in enumerate(events, start=1):
-                process_event,
+                async with network.event_page(context) as page:
-                href=ev["href"],
+                    handler = partial(
-                url_num=i,
+                        network.process_event,
-            )
+                        url=ev["link"],
+                        url_num=i,
+                        page=page,
+                        log=log,
+                    )
 
-            url, iframe = await network.safe_process(
+                    url = await network.safe_process(
-                handler,
+                        handler,
-                url_num=i,
+                        url_num=i,
-                semaphore=network.HTTP_S,
+                        semaphore=network.PW_S,
-                log=log,
+                        log=log,
-            )
+                        timeout=6,
+                    )
 
-            sport, event, href = (
+                    sport, event, link = (
-                ev["sport"],
+                        ev["sport"],
-                ev["event"],
+                        ev["event"],
-                ev["href"],
+                        ev["link"],
-            )
+                    )
 
-            key = f"[{sport}] {event} ({TAG})"
+                    key = f"[{sport}] {event} ({TAG})"
 
-            tvg_id, logo = leagues.get_tvg_info(sport, event)
+                    tvg_id, logo = leagues.get_tvg_info(sport, event)
 
-            entry = {
+                    entry = {
-                "url": url,
+                        "url": url,
-                "logo": logo,
+                        "logo": logo,
-                "base": iframe,
+                        "base": link,
-                "timestamp": now.timestamp(),
+                        "timestamp": now.timestamp(),
-                "id": tvg_id or "Live.Event.us",
+                        "id": tvg_id or "Live.Event.us",
-                "href": href,
+                        "link": link,
-            }
+                    }
 
-            cached_urls[key] = entry
+                    cached_urls[key] = entry
 
-            if url:
+                    if url:
-                valid_count += 1
+                        valid_count += 1
 
-                urls[key] = entry
+                        urls[key] = entry
 
     if new_count := valid_count - cached_count:
         log.info(f"Collected and cached {new_count} new event(s)")