e

M3U8/scrapers/fstv.py

@@ -1,3 +1,4 @@
+from functools import partial
 from pathlib import Path
 from urllib.parse import unquote, urljoin
 
@@ -20,14 +21,48 @@ MIRRORS = [
 CACHE_FILE = Cache(Path(__file__).parent / "caches" / "fstv.json", exp=10_800)
 
 
+async def process_event(
+    client: httpx.AsyncClient,
+    url: str,
+    url_num: int,
+) -> tuple[str, str]:
+
+    try:
+        r = await client.get(url)
+        r.raise_for_status()
+    except Exception as e:
+        log.error(f'URL {url_num}) Failed to fetch "{url}": {e}')
+
+        return "", ""
+
+    soup = HTMLParser(r.text)
+
+    if category_links := soup.css(".common-list-category .category-item a"):
+        match_name = category_links[-1].text(strip=True)
+    else:
+        match_name = None
+
+    if not match_name or match_name.lower() == "vs":
+        if og_title := soup.css_first("meta[property='og:title']"):
+            match_name = (
+                og_title.attributes.get("content", "").split(" start on")[0].strip()
+            )
+
+    if not (ifr := soup.css_first("iframe")):
+        log.info(f"URL {url_num}) No M3U8 found")
+        return "", ""
+
+    if src := ifr.attributes.get("src"):
+        log.info(f"URL {url_num}) Captured M3U8")
+        return match_name or "", unquote(src).split("link=")[-1]
+
+
 async def get_events(
     client: httpx.AsyncClient,
     base_url: str,
     cached_hrefs: set[str],
 ) -> list[dict[str, str]]:
 
-    log.info(f'Scraping from "{base_url}"')
-
     try:
         r = await client.get(base_url)
         r.raise_for_status()
@@ -76,42 +111,6 @@ async def get_events(
     return events
 
 
-async def process_event(
-    client: httpx.AsyncClient,
-    url: str,
-    url_num: int,
-) -> tuple[str, str]:
-
-    try:
-        r = await client.get(url)
-        r.raise_for_status()
-    except Exception as e:
-        log.error(f'URL {url_num}) Failed to fetch "{url}"\n{e}')
-
-        return "", ""
-
-    soup = HTMLParser(r.text)
-
-    if category_links := soup.css(".common-list-category .category-item a"):
-        match_name = category_links[-1].text(strip=True)
-    else:
-        match_name = None
-
-    if not match_name or match_name.lower() == "vs":
-        if og_title := soup.css_first("meta[property='og:title']"):
-            match_name = (
-                og_title.attributes.get("content", "").split(" start on")[0].strip()
-            )
-
-    if not (ifr := soup.css_first("iframe")):
-        log.info(f"URL {url_num}) No M3U8 found")
-        return "", ""
-
-    if src := ifr.attributes.get("src", ""):
-        log.info(f"URL {url_num}) Captured M3U8")
-        return match_name or "", unquote(src).split("link=")[-1]
-
-
 async def scrape(client: httpx.AsyncClient) -> None:
     cached_urls = CACHE_FILE.load()
     cached_hrefs = {entry["href"] for entry in cached_urls.values()}
@@ -125,6 +124,8 @@ async def scrape(client: httpx.AsyncClient) -> None:
         CACHE_FILE.write(cached_urls)
         return
 
+    log.info(f'Scraping from "{base_url}"')
+
     events = await get_events(
         client,
         base_url,
@@ -136,15 +137,9 @@ async def scrape(client: httpx.AsyncClient) -> None:
     now = Time.now().timestamp()
 
     for i, ev in enumerate(events, start=1):
-        match_name, url = await network.safe_process(
-            lambda: process_event(
-                client,
-                ev["link"],
-                url_num=i,
-            ),
-            url_num=i,
-            log=log,
-        )
+        handler = partial(process_event, client=client, url=ev["link"], url_num=i)
+
+        match_name, url = await network.safe_process(handler, url_num=i, log=log)
 
         if url:
             sport = ev["sport"]