e

- re-add ovogoal.py

M3U8/fetch.py

@@ -12,6 +12,7 @@ from scrapers import (
     istreameast,
     livetvsx,
     mainportal,
+    ovogoal,
     pawa,
     roxie,
     shark,
@@ -71,6 +72,7 @@ async def main() -> None:
                 asyncio.create_task(istreameast.scrape()),
                 # asyncio.create_task(livetvsx.scrape()),
                 asyncio.create_task(mainportal.scrape()),
+                asyncio.create_task(ovogoal.scrape()),
                 asyncio.create_task(pawa.scrape()),
                 asyncio.create_task(shark.scrape()),
                 asyncio.create_task(streamcenter.scrape()),
@@ -103,6 +105,7 @@ async def main() -> None:
         | istreameast.urls
         | livetvsx.urls
         | mainportal.urls
+        | ovogoal.urls
         | pawa.urls
         | roxie.urls
         | shark.urls

M3U8/scrapers/ovogoal.py

@@ -0,0 +1,144 @@
+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 = "OVO"
+
+CACHE_FILE = Cache(TAG, exp=28_800)
+
+BASE_URL = "https://ovogoaal.com"
+
+
+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
+
+    if not (
+        iframe_src_data := await network.request(
+            iframe_src,
+            headers={"Referer": url},
+            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
+
+    log.info(f"URL {url_num}) Captured M3U8")
+
+    return match[3], iframe_src
+
+
+async def get_events() -> 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 card in soup.css(".main-content .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_name_elem := card.css_first(".stream-info")):
+            continue
+
+        href = onclick.split(".href=")[-1].replace("'", "")
+
+        event_name = event_name_elem.text(strip=True)
+
+        events.append(
+            {
+                "sport": sport,
+                "event": event_name,
+                "link": urljoin(f"{html_data.url}", href),
+            }
+        )
+
+    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)")
+
+        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:
+                urls[key] = entry
+
+        log.info(f"Collected and cached {len(urls)} event(s)")
+
+    else:
+        log.info("No events found")
+
+    CACHE_FILE.write(cached_urls)