From 00000d9ab1fb5935f6222988bb9ab77c18bae65f Mon Sep 17 00:00:00 2001
From: doms9 <96013514+doms9@users.noreply.github.com>
Date: Mon, 2 Mar 2026 20:02:26 -0500
Subject: [PATCH] e - edit livetvsx.py scraping

---
 M3U8/scrapers/livetvsx.py      | 55 ++++++++++++++++++++--------------
 M3U8/scrapers/pixel.py         |  7 ++++-
 M3U8/scrapers/roxie.py         |  6 +++-
 M3U8/scrapers/utils/webwork.py |  7 ++++-
 M3U8/scrapers/watchfooty.py    |  6 +++-
 5 files changed, 55 insertions(+), 26 deletions(-)

diff --git a/M3U8/scrapers/livetvsx.py b/M3U8/scrapers/livetvsx.py
index 96d1d372..76866f9f 100644
--- a/M3U8/scrapers/livetvsx.py
+++ b/M3U8/scrapers/livetvsx.py
@@ -1,4 +1,5 @@
 import asyncio
+import re
 from functools import partial
 
 import feedparser
@@ -24,9 +25,22 @@ VALID_SPORTS = [
     "Basketball",
     "Football",
     "Ice Hockey",
+    "Wrestling",
 ]
 
 
+def fix_url(s: str) -> str | None:
+    pattern = re.compile(r"eventinfo\/(\d*)", re.I)
+
+    if not (match := pattern.search(s)):
+        return
+
+    elif not (event_id := match[1]).isalnum():
+        return
+
+    return f"https://cdn.livetv872.me/cache/links/en.{event_id}.html"
+
+
 async def process_event(
     url: str,
     url_num: int,
@@ -43,43 +57,40 @@ async def process_event(
         got_one=got_one,
     )
 
+    event_id_pattern = re.compile(r"&c=(\d*)", re.I)
+
     page.on("request", handler)
 
     try:
-        await page.goto(
+        resp = await page.goto(
             url,
             wait_until="domcontentloaded",
             timeout=10_000,
         )
 
-        await page.wait_for_timeout(1_500)
+        if resp.status != 200:
+            log.warning(f"URL {url_num}) status code: {resp.status}")
+            return
 
-        buttons = await page.query_selector_all(".lnktbj a[href*='webplayer']")
+        try:
+            event_a = page.locator('a[title*="Aliez"]').first
 
-        labels = await page.eval_on_selector_all(
-            ".lnktyt span",
-            "elements => elements.map(el => el.textContent.trim().toLowerCase())",
-        )
+            href = await event_a.get_attribute("href", timeout=1_250)
 
-        for btn, label in zip(buttons, labels):
-            if label in ["web", "youtube"]:
-                continue
-
-            if not (href := await btn.get_attribute("href")):
-                continue
-
-            break
-
-        else:
+        except TimeoutError:
             log.warning(f"URL {url_num}) No valid sources found.")
             return
 
-        href = href if href.startswith("http") else f"https:{href}"
+        if match := event_id_pattern.search(href):
+            event_id = match[1]
 
-        href.replace("livetv.sx", "livetv873.me")
+            event_url = f"https://emb.apl392.me/player/live.php?id={event_id}"
+
+        else:
+            event_url = href if href.startswith("http") else f"https:{href}"
 
         await page.goto(
-            href,
+            event_url,
             wait_until="domcontentloaded",
             timeout=5_000,
         )
@@ -130,7 +141,7 @@ async def refresh_xml_cache(now_ts: float) -> dict[str, dict[str, str | float]]:
         if not (date := entry.get("published")):
             continue
 
-        if not (link := entry.get("link")):
+        if (not (link := entry.get("link"))) or (not (fixed_link := fix_url(link))):
             continue
 
         if not (title := entry.get("title")):
@@ -151,7 +162,7 @@ async def refresh_xml_cache(now_ts: float) -> dict[str, dict[str, str | float]]:
             "sport": sport,
             "league": league,
             "event": title,
-            "link": link.replace("livetv.sx", "livetv873.me"),
+            "link": fixed_link,
             "event_ts": event_dt.timestamp(),
             "timestamp": now_ts,
         }
diff --git a/M3U8/scrapers/pixel.py b/M3U8/scrapers/pixel.py
index 560cad64..28a47b97 100644
--- a/M3U8/scrapers/pixel.py
+++ b/M3U8/scrapers/pixel.py
@@ -19,12 +19,17 @@ BASE_URL = "https://pixelsport.tv"
 
 async def get_api_data(page: Page) -> dict[str, list[dict, str, str]]:
     try:
-        await page.goto(
+        resp = await page.goto(
             url := urljoin(BASE_URL, "backend/livetv/events"),
             wait_until="domcontentloaded",
             timeout=6_000,
         )
 
+        if resp.status != 200:
+            log.warning(f"{url} status code: {resp.status}")
+
+            return {}
+
         raw_json = await page.locator("pre").inner_text(timeout=5_000)
     except Exception as e:
         log.error(f'Failed to fetch "{url}": {e}')
diff --git a/M3U8/scrapers/roxie.py b/M3U8/scrapers/roxie.py
index f1af53b6..96d553b9 100644
--- a/M3U8/scrapers/roxie.py
+++ b/M3U8/scrapers/roxie.py
@@ -93,12 +93,16 @@ async def process_event(
     page.on("request", handler)
 
     try:
-        await page.goto(
+        resp = await page.goto(
             url,
             wait_until="domcontentloaded",
             timeout=6_000,
         )
 
+        if resp.status != 200:
+            log.warning(f"URL {url_num}) status code: {resp.status}")
+            return
+
         try:
             if btn := await page.wait_for_selector(
                 "button.streambutton:nth-of-type(1)",
diff --git a/M3U8/scrapers/utils/webwork.py b/M3U8/scrapers/utils/webwork.py
index 55ab510f..31f26b32 100644
--- a/M3U8/scrapers/utils/webwork.py
+++ b/M3U8/scrapers/utils/webwork.py
@@ -250,12 +250,17 @@ class Network:
         page.on("request", handler)
 
         try:
-            await page.goto(
+            resp = await page.goto(
                 url,
                 wait_until="domcontentloaded",
                 timeout=6_000,
             )
 
+            if resp.status != 200:
+                log.warning(f"URL {url_num}) status code: {resp.status}")
+
+                return
+
             wait_task = asyncio.create_task(got_one.wait())
 
             try:
diff --git a/M3U8/scrapers/watchfooty.py b/M3U8/scrapers/watchfooty.py
index 0a93b3ce..dbd5aa24 100644
--- a/M3U8/scrapers/watchfooty.py
+++ b/M3U8/scrapers/watchfooty.py
@@ -89,12 +89,16 @@ async def process_event(
     page.on("request", handler)
 
     try:
-        await page.goto(
+        resp = await page.goto(
             url,
             wait_until="domcontentloaded",
             timeout=8_000,
         )
 
+        if resp.status != 200:
+            log.warning(f"URL {url_num}) status code: {resp.status}")
+            return
+
         await page.wait_for_timeout(2_000)
 
         try: