e

fix streamhub scraping
misc edits

M3U8/scrapers/pixel.py

@@ -1,5 +1,4 @@
 import json
-import re
 
 from playwright.async_api import async_playwright
 
@@ -49,8 +48,6 @@ async def get_events() -> dict[str, dict[str, str | float]]:
 
     events = {}
 
-    pattern = re.compile(r"https?://[^\s'\"]+?\.m3u8(?:\?[^\s'\"]*)?", re.IGNORECASE)
-
     for event in api_data.get("events", []):
         event_dt = Time.from_str(event["date"], timezone="UTC")
 
@@ -66,19 +63,18 @@ async def get_events() -> dict[str, dict[str, str | float]]:
         stream_urls = [(i, f"server{i}URL") for i in range(1, 4)]
 
         for z, stream_url in stream_urls:
-            if stream_link := channel_info.get(stream_url):
-                if pattern.search(stream_link):
-                    key = f"[{sport}] {event_name} {z} ({TAG})"
+            if (stream_link := channel_info.get(stream_url)) and stream_link != "null":
+                key = f"[{sport}] {event_name} {z} ({TAG})"
 
-                    tvg_id, logo = leagues.get_tvg_info(sport, event_name)
+                tvg_id, logo = leagues.get_tvg_info(sport, event_name)
 
-                    events[key] = {
-                        "url": stream_link,
-                        "logo": logo,
-                        "base": "https://pixelsport.tv",
-                        "timestamp": now.timestamp(),
-                        "id": tvg_id or "Live.Event.us",
-                    }
+                events[key] = {
+                    "url": stream_link,
+                    "logo": logo,
+                    "base": "https://pixelsport.tv",
+                    "timestamp": now.timestamp(),
+                    "id": tvg_id or "Live.Event.us",
+                }
 
     return events
 

M3U8/scrapers/shark.py

@@ -47,7 +47,6 @@ async def process_event(
 async def refresh_html_cache(
     client: httpx.AsyncClient, now_ts: float
 ) -> dict[str, dict[str, str | float]]:
-
     log.info("Refreshing HTML cache")
 
     try:

M3U8/scrapers/sport9.py

@@ -29,7 +29,7 @@ async def get_html_data(
         r = await client.get(url, params={"date": date})
         r.raise_for_status()
     except Exception as e:
-        log.error(f'Failed to fetch "{url}": {e}')
+        log.error(f'Failed to fetch "{r.url}": {e}')
 
         return b""
 

M3U8/scrapers/streamcenter.py

@@ -42,7 +42,7 @@ async def refresh_api_cache(
         r = await client.get(BASE_URL, params={"pageNumber": 1, "pageSize": 500})
         r.raise_for_status()
     except Exception as e:
-        log.error(f'Failed to fetch "{BASE_URL}": {e}')
+        log.error(f'Failed to fetch "{r.url}": {e}')
 
         return []
 

M3U8/scrapers/streamfree.py

@@ -17,12 +17,10 @@ BASE_URL = "https://streamfree.to/"
 
 async def refresh_api_cache(client: httpx.AsyncClient) -> dict[str, dict[str, list]]:
     try:
-        url = urljoin(BASE_URL, "streams")
-
-        r = await client.get(url)
+        r = await client.get(urljoin(BASE_URL, "streams"))
         r.raise_for_status()
     except Exception as e:
-        log.error(f'Failed to fetch "{url}": {e}')
+        log.error(f'Failed to fetch "{r.url}": {e}')
 
         return {}
 

M3U8/scrapers/streamhub.py

@@ -36,15 +36,21 @@ CATEGORIES = {
 }
 
 
-async def get_html_data(client: httpx.AsyncClient, sport_id: str) -> bytes:
-    try:
-        url = urljoin(BASE_URL, f"events/{Time.now().date()}")
+async def get_html_data(
+    client: httpx.AsyncClient,
+    date: str,
+    sport_id: str,
+) -> bytes:
 
-        r = await client.get(url, params={"sport_id": sport_id})
+    try:
+        r = await client.get(
+            urljoin(BASE_URL, f"events/{date}"),
+            params={"sport_id": sport_id},
+        )
 
         r.raise_for_status()
     except Exception as e:
-        log.error(f'Failed to fetch "{url}": {e}')
+        log.error(f'Failed to fetch "{r.url}": {e}')
 
         return b""
 
@@ -53,11 +59,12 @@ async def get_html_data(client: httpx.AsyncClient, sport_id: str) -> bytes:
 
 async def refresh_html_cache(
     client: httpx.AsyncClient,
+    date: str,
     sport_id: str,
     ts: float,
 ) -> dict[str, dict[str, str | float]]:
 
-    html_data = await get_html_data(client, sport_id)
+    html_data = await get_html_data(client, date, sport_id)
 
     soup = HTMLParser(html_data)
 
@@ -113,12 +120,16 @@ async def get_events(
     if not (events := HTML_CACHE.load()):
         log.info("Refreshing HTML cache")
 
+        dates = [now.date(), now.delta(days=1).date()]
+
         tasks = [
             refresh_html_cache(
                 client,
+                date,
                 sport_id,
                 now.timestamp(),
             )
+            for date in dates
             for sport_id in CATEGORIES.values()
         ]
 
@@ -184,7 +195,7 @@ async def scrape(client: httpx.AsyncClient) -> None:
                     ev["event"],
                     ev["logo"],
                     ev["link"],
-                    ev["timestamp"],
+                    ev["event_ts"],
                 )
 
                 key = f"[{sport}] {event} ({TAG})"