e

M3U8/scrape/streambtw.py

@@ -0,0 +1,112 @@
+import json
+import re
+from pathlib import Path
+from urllib.parse import urljoin
+
+import httpx
+from selectolax.parser import HTMLParser
+
+from .utils import get_logger, load_ts_cache, now, safe_process_event
+
+log = get_logger(__name__)
+
+urls: dict[str, dict[str, str | float]] = {}
+
+BASE_URL = "https://streambtw.com/"
+
+CACHE_FILE = Path(__file__).parent / "caches" / "streambtw.json"
+
+
+async def process_event(
+    client: httpx.AsyncClient,
+    url: str,
+    url_num: int,
+) -> str | None:
+
+    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
+
+    valid_m3u8 = re.compile(
+        r'var\s+randomM3u8\s*=\s*[\'"]([^\'"]+)[\'"]',
+        re.IGNORECASE,
+    )
+
+    if match := valid_m3u8.search(r.text):
+        log.info(f"URL {url_num}) Captured M3U8")
+        return match[1]
+
+    log.info(f"URL {url_num}) No M3U8 found")
+
+
+async def get_events(client: httpx.AsyncClient) -> list[dict[str, str]]:
+    try:
+        r = await client.get(BASE_URL)
+        r.raise_for_status()
+    except Exception as e:
+        log.error(f'Failed to fetch "{BASE_URL}"\n{e}')
+
+        return []
+
+    soup = HTMLParser(r.text)
+
+    events = []
+
+    for card in soup.css("div.container div.card"):
+        img = card.css_first("img.league-logo")
+
+        logo = img.attrs.get("src") if img else None
+
+        sport = card.css_first("h5.card-title").text(strip=True)
+
+        name = card.css_first("p.card-text").text(strip=True)
+
+        link = card.css_first("a.btn.btn-primary")
+
+        if href := link.attrs.get("href"):
+            events.append(
+                {
+                    "sport": sport,
+                    "event": name,
+                    "link": urljoin(BASE_URL, href),
+                    "logo": logo,
+                }
+            )
+
+    return events
+
+
+async def main(client: httpx.AsyncClient) -> None:
+    if cached := load_ts_cache(CACHE_FILE, 86400):  # find out when site updates
+        urls.update(cached)
+        log.info(f"Collected {len(urls)} event(s) from cache")
+        return
+
+    log.info(f'Scraping from "{BASE_URL}"')
+
+    events = await get_events(client)
+
+    log.info(f"Processing {len(events)} new URLs")
+
+    for i, ev in enumerate(events, start=1):
+        url = await safe_process_event(
+            lambda: process_event(client, url=ev["link"], url_num=i),
+            url_num=i,
+            log=log,
+        )
+
+        if url:
+            entry = {
+                "url": url,
+                "logo": ev["logo"],
+                "timestamp": now.timestamp(),
+            }
+
+            urls[f"[{ev['sport']}] {ev['event']}"] = entry
+
+    log.info(f"Collected {len(urls)} event(s)")
+
+    CACHE_FILE.write_text(json.dumps(urls, indent=2), encoding="utf-8")