e

M3U8/scrapers/ace.py

@@ -1,127 +0,0 @@
-import asyncio
-import re
-from urllib.parse import urljoin
-
-import httpx
-from selectolax.parser import HTMLParser, Node
-
-from .utils import get_base, get_logger, leagues
-
-log = get_logger(__name__)
-
-urls: dict[str, dict[str, str]] = {}
-
-MIRRORS = ["https://aceztrims.pages.dev/", "https://acestrlms.pages.dev/"]
-
-
-def is_valid_href(a: Node) -> bool:
-    href = a.attributes.get("href", "")
-    return href.startswith("/") and href != "/news/"
-
-
-async def get_schedule(client: httpx.AsyncClient, base_url: str) -> list[dict]:
-    log.info(f'Scraping from "{base_url}"')
-
-    try:
-        r = await client.get(base_url)
-        r.raise_for_status()
-    except Exception as e:
-        log.error(f'Failed to fetch "{base_url}": {e}')
-        return []
-
-    html = re.sub(r"<!--.*?-->", "", r.text, flags=re.DOTALL)
-
-    tree = HTMLParser(html)
-
-    events = []
-
-    for a in filter(is_valid_href, tree.css("a[href]")):
-        href = a.attributes.get("href", "")
-
-        title_text = a.text(strip=True)
-
-        after_time = (
-            title_text.split("//", 1)[1].strip() if "//" in title_text else title_text
-        )
-
-        if " - " in after_time:
-            sport, event_name = (x.strip() for x in after_time.split(" - ", 1))
-        else:
-            sport, event_name = "", after_time
-
-        events.append(
-            {"sport": sport, "event": event_name, "href": urljoin(base_url, href)}
-        )
-
-    return events
-
-
-async def get_m3u8_links(client: httpx.AsyncClient, url: str) -> list[str]:
-    try:
-        r = await client.get(url)
-        r.raise_for_status()
-    except Exception as e:
-        log.error(f'Failed to fetch "{url}": {e}')
-        return []
-
-    html = re.sub(r"<!--.*?-->", "", r.text, flags=re.DOTALL)
-
-    soup = HTMLParser(html)
-
-    m3u8_links = []
-
-    for btn in soup.css("button[onclick]"):
-        onclick = btn.attributes.get("onclick", "")
-
-        if match := re.search(r"src\s*=\s*['\"](.*?)['\"]", onclick):
-            link = match[1]
-
-            if ".m3u8" in link:
-                m3u8_links.append(link)
-
-    if iframe := soup.css_first("iframe#iframe"):
-        src = iframe.attributes.get("src", "")
-
-        if ".m3u8" in src and src not in m3u8_links:
-            m3u8_links.insert(
-                0,
-                src.split("cors.ricohspaces.app/")[-1],
-            )
-
-    return m3u8_links
-
-
-async def scrape(client: httpx.AsyncClient) -> None:
-    if not (base_url := await get_base(client, MIRRORS)):
-        log.warning("No working ace mirrors")
-        return
-
-    schedule = await get_schedule(client, base_url)
-
-    tasks = [get_m3u8_links(client, item["href"]) for item in schedule]
-
-    results = await asyncio.gather(*tasks)
-
-    for item, m3u8_urls in zip(schedule, results):
-        if not m3u8_urls:
-            continue
-
-        for i, link in enumerate(m3u8_urls, start=1):
-            sport, event = item["sport"], item["event"]
-
-            key = f"[{sport}] {event} (S{i})"
-
-            tvg_id, logo = leagues.info(sport)
-
-            entry = {
-                "url": link,
-                "logo": logo,
-                "id": tvg_id,
-            }
-
-            urls[key] = entry
-
-    log.info(f"Collected {len(urls)} events")
-
-
-# add caching

M3U8/scrapers/ppv.py

@@ -140,7 +140,7 @@ async def get_events(
     if not (
         api_data := load_cache(
             API_FILE,
-            exp=86400,
+            exp=86_400,
             nearest_hr=True,
             per_entry=False,
         )
@@ -238,6 +238,3 @@ async def scrape(client: httpx.AsyncClient) -> None:
         log.info("No new events found")
 
     write_cache(CACHE_FILE, cached_urls)
-
-
-# works if no cloudflare bot detection

M3U8/scrapers/streamed.py

@@ -134,7 +134,8 @@ async def refresh_html_cache(client: httpx.AsyncClient, url: str) -> dict[str, s
             "sport": sport,
             "event": event,
             "link": f"https://streamed.site/set.php?{m[1]}",
-            "ts": event_dt.timestamp(),
+            "event_ts": event_dt.timestamp(),
+            "timestamp": now.timestamp(),
         }
 
     return events
@@ -146,7 +147,7 @@ async def get_events(
     cached_keys: set[str],
 ) -> list[dict[str, str]]:
 
-    if not (events := load_cache(HTML_CACHE, exp=10_800)):
+    if not (events := load_cache(HTML_CACHE, exp=86_400)):
         events = await refresh_html_cache(client, url)
         write_cache(HTML_CACHE, events)
 
@@ -158,7 +159,7 @@ async def get_events(
         if cached_keys & {k}:
             continue
 
-        if not start_ts <= v["ts"] < end_ts:
+        if not start_ts <= v["event_ts"] < end_ts:
             continue
 
         live.append({**v})