e

- edit scraping method for webcast.py

M3U8/fetch.py

@@ -67,7 +67,6 @@ async def main() -> None:
                 # asyncio.create_task(fsports.scrape(xtrnl_brwsr)),
                 asyncio.create_task(ppv.scrape(xtrnl_brwsr)),
                 asyncio.create_task(roxie.scrape(hdl_brwsr)),
-                asyncio.create_task(webcast.scrape(hdl_brwsr)),
             ]
 
             httpx_tasks = [
@@ -84,6 +83,7 @@ async def main() -> None:
                 asyncio.create_task(streamtpnew.scrape()),
                 asyncio.create_task(totalsportek.scrape()),
                 asyncio.create_task(tvapp.scrape()),
+                asyncio.create_task(webcast.scrape()),
             ]
 
             await asyncio.gather(*(pw_tasks + httpx_tasks))

M3U8/scrapers/webcast.py

@@ -1,7 +1,8 @@
+import ast
 import asyncio
+import re
 from functools import partial
 
-from playwright.async_api import Browser
 from selectolax.parser import HTMLParser
 
 from .utils import Cache, Time, get_logger, leagues, network
@@ -12,7 +13,7 @@ urls: dict[str, dict[str, str | float]] = {}
 
 TAG = "WEBCAST"
 
-CACHE_FILE = Cache(TAG, exp=19_800)
+CACHE_FILE = Cache(TAG, exp=12_600)
 
 BASE_URLS = {
     "MLB": "https://mlbwebcast.com",
@@ -25,6 +26,65 @@ def fix_event(s: str) -> str:
     return " vs ".join(s.split("@"))
 
 
+async def process_event(url: str, url_num: int) -> str | None:
+    if not (event_data := await network.request(url, log=log)):
+        log.warning(f"URL {url_num}) Failed to load url.")
+        return
+
+    soup = HTMLParser(event_data.content)
+
+    if not (iframe := soup.css_first('iframe[name="srcFrame"]')):
+        log.warning(f"URL {url_num}) No iframe element found.")
+        return
+
+    if not (iframe_src := iframe.attributes.get("src")):
+        log.warning(f"URL {url_num}) No iframe source found.")
+        return
+
+    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
+
+    pattern = re.compile(r'var\s+\w*=\[([^"]*)\];', re.I)
+
+    if not (match := pattern.search(iframe_src_data.text)):
+        log.warning(f"URL {url_num}) No Clappr source found.")
+        return
+
+    try:
+        ev_id, ev_ts, ev_pt = ast.literal_eval(match[1])
+    except ValueError:
+        log.warning(f"URL {url_num}) Failed to parse event info.")
+        return
+
+    params: dict[str, int | str] = dict(zip(["id", "ts", "pt"], [ev_id, ev_ts, ev_pt]))
+
+    if not (
+        api_data := await network.request(
+            "https://mlbwebcast.com/stream/check_stream.php",
+            headers={"Referer": iframe_src},
+            params=params,
+            log=log,
+        )
+    ):
+        log.warning(f"URL {url_num}) Failed to make php request.")
+        return
+
+    elif (data := api_data.json()).get("error"):
+        log.warning(f"URL {url_num}) Failed to make php request.")
+        return
+
+    log.info(f"URL {url_num}) Captured M3U8")
+
+    return data.get("url")
+
+
 async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
     tasks = [network.request(url, log=log) for url in BASE_URLS.values()]
 
@@ -70,7 +130,7 @@ async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
     return events
 
 
-async def scrape(browser: Browser) -> None:
+async def scrape() -> None:
     cached_urls = CACHE_FILE.load()
 
     valid_urls = {k: v for k, v in cached_urls.items() if v["url"]}
@@ -88,45 +148,41 @@ async def scrape(browser: Browser) -> None:
 
         now = Time.clean(Time.now())
 
-        async with network.event_context(browser) as context:
+        for i, ev in enumerate(events, start=1):
-            for i, ev in enumerate(events, start=1):
+            handler = partial(
-                async with network.event_page(context) as page:
+                process_event,
-                    handler = partial(
+                url=(link := ev["link"]),
-                        network.process_event,
+                url_num=i,
-                        url=(link := ev["link"]),
+            )
-                        url_num=i,
-                        page=page,
-                        log=log,
-                    )
 
-                    url = await network.safe_process(
+            url = await network.safe_process(
-                        handler,
+                handler,
-                        url_num=i,
+                url_num=i,
-                        semaphore=network.PW_S,
+                semaphore=network.PW_S,
-                        log=log,
+                log=log,
-                    )
+            )
 
-                    sport, event = ev["sport"], ev["event"]
+            sport, event = ev["sport"], ev["event"]
 
-                    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": BASE_URLS[sport],
+                "base": BASE_URLS[sport],
-                        "timestamp": now.timestamp(),
+                "timestamp": now.timestamp(),
-                        "id": tvg_id or "Live.Event.us",
+                "id": tvg_id or "Live.Event.us",
-                        "link": link,
+                "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
 
         log.info(f"Collected and cached {valid_count - cached_count} new event(s)")