e

- edit scraping for livetvsx.py
- edit caching for streamsgate.py
- edit caching for streamhub.py
- misc edits.

M3U8/scrapers/livetvsx.py

@@ -1,7 +1,6 @@
-import asyncio
+import re
 from functools import partial
 
-from playwright.async_api import Browser, Page, TimeoutError
 from selectolax.parser import HTMLParser
 
 from .utils import Cache, Time, get_logger, leagues, network
@@ -17,83 +16,61 @@ CACHE_FILE = Cache(TAG, exp=10_800)
 BASE_URL = "https://livetv.sx/export/webmasters.php"
 
 
-async def process_event(
+async def process_event(url: str, url_num: int) -> tuple[str | None, str | None]:
-    url: str,
+    nones = None, None
-    url_num: int,
-    page: Page,
-) -> str | None:
 
-    captured: list[str] = []
+    if not (ev_data_1 := await network.request(url, log=log)):
+        log.warning(f"URL {url_num}) Failed to load url. (EVD1)")
+        return nones
 
-    got_one = asyncio.Event()
+    soup_1 = HTMLParser(ev_data_1.content)
 
-    handler = partial(
+    for a_elem in soup_1.css("a"):
-        network.capture_req,
+        if not (src_title := a_elem.attributes.get("title")) or (
-        captured=captured,
+            "aliez" not in src_title.lower()
-        got_one=got_one,
+        ):
-    )
+            continue
 
-    page.on("request", handler)
+        href = a_elem.attributes["href"]
-
-    try:
-        resp = await page.goto(
-            url,
-            wait_until="domcontentloaded",
-            timeout=10_000,
-        )
-
-        if not resp or resp.status != 200:
-            log.warning(
-                f"URL {url_num}) Status Code: {resp.status if resp else 'None'}"
-            )
-            return
-
-        try:
-            event_a = page.locator('a[title*="Aliez"]').first
-
-            href = await event_a.get_attribute("href", timeout=1_250)
-        except TimeoutError:
-            log.warning(f"URL {url_num}) No valid sources found.")
-            return
 
         event_url = href if href.startswith("http") else f"https:{href}"
+        break
 
-        await page.goto(
+    else:
-            event_url,
+        log.warning(f"URL {url_num}) No valid sources found.")
-            wait_until="domcontentloaded",
+        return nones
-            timeout=5_000,
-        )
 
-        wait_task = asyncio.create_task(got_one.wait())
+    if not (ev_data_2 := await network.request(event_url, log=log)):
+        log.warning(f"URL {url_num}) Failed to load url. (EVD2)")
+        return nones
 
-        try:
+    soup_2 = HTMLParser(ev_data_2.content)
-            await asyncio.wait_for(wait_task, timeout=6)
-        except asyncio.TimeoutError:
-            log.warning(f"URL {url_num}) Timed out waiting for M3U8.")
-            return
 
-        finally:
+    ifr_1 = soup_2.css_first("tr > td > iframe")
-            if not wait_task.done():
-                wait_task.cancel()
 
-                try:
+    if not ifr_1 or not (ifr_1_src := ifr_1.attributes.get("src")):
-                    await wait_task
+        log.warning(f"URL {url_num}) No iframe element found.")
-                except asyncio.CancelledError:
+        return nones
-                    pass
 
-        if captured:
+    ifr_1_src = "".join(
-            log.info(f"URL {url_num}) Captured M3U8")
+        (ifr_1_src if ifr_1_src.startswith("http") else f"https:{ifr_1_src}").split()
-            return captured[0]
+    )
 
-        log.warning(f"URL {url_num}) No M3U8 captured after waiting.")
+    if not (ev_data_3 := await network.request(ifr_1_src, log=log)):
-        return
+        log.warning(f"URL {url_num}) Failed to load url. (EVD3)")
+        return nones
 
-    except Exception as e:
+    pattern = re.compile(r'pl\.init\((\'|\")([^"]*)(\'|\")\)', re.I)
-        log.warning(f"URL {url_num}) {e}")
-        return
 
-    finally:
+    if not (match := pattern.search(ev_data_3.text)):
-        page.remove_listener("request", handler)
+        log.warning(f"URL {url_num}) No M3U8 source found.")
+        return nones
+
+    log.info(f"URL {url_num}) Captured M3U8")
+
+    m3u: str = match[2] if match[2].startswith("http") else f"https:{match[2]}"
+
+    return m3u, ifr_1_src
 
 
 async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
@@ -102,6 +79,7 @@ async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
     php_data = await network.unvd_client.get(BASE_URL, params={"lang": "en"})
 
     if php_data.status_code != 200:
+        log.warning("Failed to get php data.")
         return events
 
     soup = HTMLParser(php_data.content)
@@ -143,7 +121,7 @@ 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"]}
@@ -161,49 +139,45 @@ async def scrape(browser: Browser) -> None:
 
         now = Time.clean(Time.now())
 
-        async with network.event_context(browser, ignore_https=True) 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"]),
-                        process_event,
+                url_num=i,
-                        url=(link := ev["link"]),
+            )
-                        url_num=i,
-                        page=page,
-                    )
 
-                    url = await network.safe_process(
+            url, iframe = await network.safe_process(
-                        handler,
+                handler,
-                        url_num=i,
+                url_num=i,
-                        semaphore=network.PW_S,
+                semaphore=network.HTTP_S,
-                        log=log,
+                log=log,
-                        timeout=20,
+            )
-                    )
 
-                    sport, league, event = (
+            sport, league, event = (
-                        ev["sport"],
+                ev["sport"],
-                        ev["league"],
+                ev["league"],
-                        ev["event"],
+                ev["event"],
-                    )
+            )
 
-                    key = f"[{sport} - {league}] {event} ({TAG})"
+            key = f"[{sport} - {league}] {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": "https://livetv.sx/enx/",
+                "base": iframe,
-                        "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)")
 

M3U8/scrapers/mainportal.py

@@ -163,7 +163,7 @@ async def scrape() -> None:
             url = await network.safe_process(
                 handler,
                 url_num=i,
-                semaphore=network.PW_S,
+                semaphore=network.HTTP_S,
                 log=log,
             )
 

M3U8/scrapers/streamcenter.py

@@ -117,7 +117,7 @@ async def scrape() -> None:
             url = await network.safe_process(
                 handler,
                 url_num=i,
-                semaphore=network.PW_S,
+                semaphore=network.HTTP_S,
                 log=log,
             )
 

M3U8/scrapers/streamhub.py

@@ -13,9 +13,7 @@ urls: dict[str, dict[str, str | float]] = {}
 
 TAG = "STRMHUB"
 
-CACHE_FILE = Cache(TAG, exp=10_800)
+CACHE_FILE = Cache(TAG, exp=28_800)
-
-HTML_FILE = Cache(f"{TAG}-html", exp=19_800)
 
 BASE_URL = "https://livesports4u.net"
 
@@ -116,116 +114,78 @@ async def process_event(
         page.remove_listener("request", handler)
 
 
-async def refresh_html_cache(
+async def get_events() -> list[dict[str, str]]:
-    date: str,
+    now = Time.clean(Time.now())
-    sport_id: str,
-    ts: float,
-) -> dict[str, dict[str, str | float]]:
 
-    events = {}
+    tasks = [
-
+        network.request(
-    if not (
-        html_data := await network.request(
             urljoin(BASE_URL, f"events/{date}"),
             params={"sport_id": sport_id},
             log=log,
         )
-    ):
+        for date in [now.date(), now.delta(days=1).date()]
+        for sport_id in SPORT_ENDPOINTS
+    ]
+
+    results = await asyncio.gather(*tasks)
+
+    events = []
+
+    if not (soups := [HTMLParser(html.content) for html in results if html]):
         return events
 
-    soup = HTMLParser(html_data.content)
+    for soup in soups:
-
+        for section in soup.css(".events-section"):
-    for section in soup.css(".events-section"):
+            if not (sport_node := section.css_first(".section-titlte")):
-        if not (sport_node := section.css_first(".section-titlte")):
-            continue
-
-        sport = sport_node.text(strip=True)
-
-        for event in section.css(".section-event"):
-            event_name = "Live Event"
-
-            if teams := event.css_first(".event-competitors"):
-                home, away = teams.text(strip=True).split("vs.")
-
-                event_name = f"{away} vs {home}"
-
-            if not (event_button := event.css_first(".event-button a")) or not (
-                href := event_button.attributes.get("href")
-            ):
                 continue
 
-            event_date = event.css_first(".event-countdown").attributes.get(
+            sport = sport_node.text(strip=True)
-                "data-start"
-            )
 
-            event_dt = Time.from_str(event_date, timezone="UTC")
+            for event in section.css(".section-event"):
+                event_name = "Live Event"
 
-            key = f"[{sport}] {event_name} ({TAG})"
+                if teams := event.css_first(".event-competitors"):
+                    home, away = teams.text(strip=True).split("vs.")
 
-            events[key] = {
+                    event_name = f"{away} vs {home}"
-                "sport": sport,
+
-                "event": event_name,
+                if not (event_button := event.css_first(".event-button a")) or not (
-                "link": href,
+                    href := event_button.attributes.get("href")
-                "event_ts": event_dt.timestamp(),
+                ):
-                "timestamp": ts,
+                    continue
-            }
+
+                event_date = event.css_first(".event-countdown").attributes.get(
+                    "data-start"
+                )
+
+                event_dt = Time.from_str(event_date, timezone="UTC")
+
+                if event_dt.date() != now.date():
+                    continue
+
+                events.append(
+                    {
+                        "sport": sport,
+                        "event": event_name,
+                        "link": href,
+                        "timestamp": now.timestamp(),
+                    }
+                )
 
     return events
 
 
-async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
-    now = Time.clean(Time.now())
-
-    if not (events := HTML_FILE.load()):
-        log.info("Refreshing HTML cache")
-
-        tasks = [
-            refresh_html_cache(
-                date,
-                sport_id,
-                now.timestamp(),
-            )
-            for date in [now.date(), now.delta(days=1).date()]
-            for sport_id in SPORT_ENDPOINTS
-        ]
-
-        results = await asyncio.gather(*tasks)
-
-        events = {k: v for data in results for k, v in data.items()}
-
-        HTML_FILE.write(events)
-
-    live = []
-
-    start_ts = now.delta(minutes=-30).timestamp()
-    end_ts = now.delta(minutes=30).timestamp()
-
-    for k, v in events.items():
-        if k in cached_keys:
-            continue
-
-        if not start_ts <= v["event_ts"] <= end_ts:
-            continue
-
-        live.append(v)
-
-    return live
-
-
 async def scrape(browser: Browser) -> None:
-    cached_urls = CACHE_FILE.load()
+    if cached_urls := CACHE_FILE.load():
+        urls.update({k: v for k, v in cached_urls.items() if v["url"]})
 
-    valid_urls = {k: v for k, v in cached_urls.items() if v["url"]}
+        log.info(f"Loaded {len(urls)} event(s) from cache")
 
-    valid_count = cached_count = len(valid_urls)
+        return
-
-    urls.update(valid_urls)
-
-    log.info(f"Loaded {cached_count} event(s) from cache")
 
     log.info(f'Scraping from "{BASE_URL}"')
 
-    if events := await get_events(cached_urls.keys()):
+    if events := await get_events():
         log.info(f"Processing {len(events)} new URL(s)")
 
         async with network.event_context(browser) as context:
@@ -249,7 +209,7 @@ async def scrape(browser: Browser) -> None:
                     sport, event, ts = (
                         ev["sport"],
                         ev["event"],
-                        ev["event_ts"],
+                        ev["timestamp"],
                     )
 
                     key = f"[{sport}] {event} ({TAG})"
@@ -268,13 +228,11 @@ async def scrape(browser: Browser) -> None:
                     cached_urls[key] = entry
 
                     if url:
-                        valid_count += 1
-
                         entry["url"] = url.split("?st")[0]
 
                         urls[key] = entry
 
-        log.info(f"Collected and cached {valid_count - cached_count} new event(s)")
+        log.info(f"Collected and cached {len(urls)} new event(s)")
 
     else:
         log.info("No new events found")

M3U8/scrapers/streamsgate.py

@@ -2,7 +2,6 @@ import asyncio
 import re
 from functools import partial
 from itertools import chain
-from typing import Any
 from urllib.parse import urljoin
 
 from selectolax.parser import HTMLParser
@@ -15,9 +14,7 @@ urls: dict[str, dict[str, str | float]] = {}
 
 TAG = "STRMSGATE"
 
-CACHE_FILE = Cache(TAG, exp=10_800)
+CACHE_FILE = Cache(TAG, exp=28_800)
-
-API_FILE = Cache(f"{TAG}-api", exp=19_800)
 
 BASE_URL = "https://streamsgates.io"
 
@@ -85,36 +82,17 @@ async def process_event(url: str, url_num: int) -> tuple[str | None, str | None]
     return match[3], ifr_src
 
 
-async def refresh_api_cache(now_ts: float) -> list[dict[str, Any]]:
+async def get_events() -> list[dict[str, str]]:
+    now = Time.clean(Time.now())
+
     tasks = [network.request(url, log=log) for url in SPORT_URLS]
 
     results = await asyncio.gather(*tasks)
 
-    if not (data := [*chain.from_iterable(r.json() for r in results if r)]):
-        return [{"timestamp": now_ts}]
-
-    for ev in data:
-        ev["ts"] = ev.pop("timestamp")
-
-    data[-1]["timestamp"] = now_ts
-
-    return data
-
-
-async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
-    now = Time.clean(Time.now())
-
-    if not (api_data := API_FILE.load(per_entry=False, index=-1)):
-        log.info("Refreshing API cache")
-
-        api_data = await refresh_api_cache(now.timestamp())
-
-        API_FILE.write(api_data)
-
     events = []
 
-    start_dt = now.delta(hours=-2.5)
+    if not (api_data := [*chain.from_iterable(r.json() for r in results if r)]):
-    end_dt = now.delta(minutes=30)
+        return events
 
     for stream_group in api_data:
         date = stream_group.get("time")
@@ -123,34 +101,30 @@ async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
 
         t1, t2 = stream_group.get("away"), stream_group.get("home")
 
-        if not (t1 and t2):
-            continue
-
-        event = get_event(t1, t2)
-
         if not (date and sport):
             continue
 
-        if f"[{sport}] {event} ({TAG})" in cached_keys:
-            continue
-
         event_dt = Time.from_str(date, timezone="UTC")
 
-        if not start_dt <= event_dt <= end_dt:
+        if event_dt.date() != now.date():
             continue
 
-        if not (streams := stream_group.get("streams")):
+        if not (streams := stream_group.get("streams")) or not (
+            url := streams[0].get("url")
+        ):
             continue
 
-        if not (url := streams[0].get("url")):
+        if not (t1 and t2):
             continue
 
+        event = get_event(t1, t2)
+
         events.append(
             {
                 "sport": sport,
                 "event": event,
                 "link": url,
-                "timestamp": event_dt.timestamp(),
+                "timestamp": now.timestamp(),
             }
         )
 
@@ -158,19 +132,16 @@ async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
 
 
 async def scrape() -> None:
-    cached_urls = CACHE_FILE.load()
+    if cached_urls := CACHE_FILE.load():
+        urls.update({k: v for k, v in cached_urls.items() if v["url"]})
 
-    valid_urls = {k: v for k, v in cached_urls.items() if v["url"]}
+        log.info(f"Loaded {len(urls)} event(s) from cache")
 
-    valid_count = cached_count = len(valid_urls)
+        return
-
-    urls.update(valid_urls)
-
-    log.info(f"Loaded {cached_count} event(s) from cache")
 
     log.info(f'Scraping from "{BASE_URL}"')
 
-    if events := await get_events(cached_urls.keys()):
+    if events := await get_events():
         log.info(f"Processing {len(events)} new URL(s)")
 
         for i, ev in enumerate(events, start=1):
@@ -183,7 +154,7 @@ async def scrape() -> None:
             url, iframe = await network.safe_process(
                 handler,
                 url_num=i,
-                semaphore=network.PW_S,
+                semaphore=network.HTTP_S,
                 log=log,
             )
 
@@ -209,11 +180,11 @@ async def scrape() -> None:
             cached_urls[key] = entry
 
             if url:
-                valid_count += 1
+                entry["url"] = url.split("?st")[0]
 
                 urls[key] = entry
 
-        log.info(f"Collected and cached {valid_count - cached_count} new event(s)")
+        log.info(f"Collected and cached {len(urls)} new event(s)")
 
     else:
         log.info("No new events found")

M3U8/scrapers/webcast.py

@@ -157,7 +157,7 @@ async def scrape() -> None:
             url = await network.safe_process(
                 handler,
                 url_num=i,
-                semaphore=network.PW_S,
+                semaphore=network.HTTP_S,
                 log=log,
             )