e

- change scrape window for istreameast.py
- harden scraping method for roxie.py
- catch nulls for ppv.py
- change scraping method for totalsportek.py
- misc edits.

M3U8/scrapers/totalsportek.py

@@ -1,7 +1,8 @@
+import json
+import re
 from functools import partial
 from urllib.parse import urljoin, urlparse
 
-from playwright.async_api import Browser
 from selectolax.parser import HTMLParser
 
 from .utils import Cache, Time, get_logger, leagues, network
@@ -23,6 +24,64 @@ def fix_txt(s: str) -> str:
     return s.upper() if s.islower() else s
 
 
+async def process_event(url: str, url_num: int) -> str | None:
+    if not (event_data := await network.request(url, log=log)):
+        log.info(f"URL {url_num}) Failed to load url.")
+
+        return
+
+    soup_1 = HTMLParser(event_data.content)
+
+    if not (iframe_1 := soup_1.css_first("iframe")):
+        log.warning(f"URL {url_num}) No iframe element found.")
+
+        return
+
+    if not (iframe_1_src := iframe_1.attributes.get("src")):
+        log.warning(f"URL {url_num}) No iframe source found.")
+
+        return
+
+    if not (iframe_1_src_data := await network.request(iframe_1_src, log=log)):
+        log.info(f"URL {url_num}) Failed to load iframe source.")
+
+        return
+
+    soup_2 = HTMLParser(iframe_1_src_data.content)
+
+    if not (iframe_2 := soup_2.css_first("iframe")):
+        log.warning(f"URL {url_num}) No iframe element found.")
+
+        return
+
+    if not (iframe_2_src := iframe_2.attributes.get("src")):
+        log.warning(f"URL {url_num}) No iframe source found.")
+
+        return
+
+    if not (
+        iframe_2_src_data := await network.request(
+            iframe_2_src,
+            log=log,
+            headers={"Referer": iframe_1_src},
+        )
+    ):
+        log.info(f"URL {url_num}) Failed to load iframe source.")
+
+        return
+
+    valid_m3u8 = re.compile(r'currentStreamUrl\s+=\s+"([^"]*)"', re.I)
+
+    if not (match := valid_m3u8.search(iframe_2_src_data.text)):
+        log.warning(f"URL {url_num}) No Clappr source found.")
+
+        return
+
+    log.info(f"URL {url_num}) Captured M3U8")
+
+    return json.loads(f'"{match[1]}"')
+
+
 async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
     events = []
 
@@ -54,7 +113,7 @@ async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
         if not (time_node := node.css_first(".col-3 span")):
             continue
 
-        if time_node.text(strip=True) != "MatchStarted":
+        if time_node.text(strip=True).lower() != "matchstarted":
             continue
 
         event_name = fix_txt(" vs ".join(teams))
@@ -73,7 +132,7 @@ 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"]}
@@ -93,50 +152,45 @@ async def scrape(browser: Browser) -> None:
     if events:
         now = Time.clean(Time.now())
 
-        async with network.event_context(browser) as context:
-            for i, ev in enumerate(events, start=1):
-                async with network.event_page(context) as page:
-                    handler = partial(
-                        network.process_event,
-                        url=ev["link"],
-                        url_num=i,
-                        page=page,
-                        log=log,
-                    )
+        for i, ev in enumerate(events, start=1):
+            handler = partial(
+                process_event,
+                url=ev["link"],
+                url_num=i,
+            )
 
-                    url = await network.safe_process(
-                        handler,
-                        url_num=i,
-                        semaphore=network.PW_S,
-                        log=log,
-                        timeout=6,
-                    )
+            url = await network.safe_process(
+                handler,
+                url_num=i,
+                semaphore=network.HTTP_S,
+                log=log,
+            )
 
-                    sport, event, link = (
-                        ev["sport"],
-                        ev["event"],
-                        ev["link"],
-                    )
+            sport, event, link = (
+                ev["sport"],
+                ev["event"],
+                ev["link"],
+            )
 
-                    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 = {
-                        "url": url,
-                        "logo": logo,
-                        "base": link,
-                        "timestamp": now.timestamp(),
-                        "id": tvg_id or "Live.Event.us",
-                        "link": link,
-                    }
+            entry = {
+                "url": url,
+                "logo": logo,
+                "base": link,
+                "timestamp": now.timestamp(),
+                "id": tvg_id or "Live.Event.us",
+                "link": link,
+            }
 
-                    cached_urls[key] = entry
+            cached_urls[key] = entry
 
-                    if url:
-                        valid_count += 1
+            if url:
+                valid_count += 1
 
-                        urls[key] = entry
+                urls[key] = entry
 
     if new_count := valid_count - cached_count:
         log.info(f"Collected and cached {new_count} new event(s)")