From 00000d9673b2882e7a4f6550505d3cf977cc7bff Mon Sep 17 00:00:00 2001 From: doms9 <96013514+doms9@users.noreply.github.com> Date: Thu, 5 Mar 2026 22:05:43 -0500 Subject: [PATCH] e replace sport9 with sportzone --- M3U8/fetch.py | 6 +- M3U8/scrapers/sport9.py | 148 --------------------------------- M3U8/scrapers/sportzone.py | 154 +++++++++++++++++++++++++++++++++++ M3U8/scrapers/streamsgate.py | 2 +- 4 files changed, 158 insertions(+), 152 deletions(-) delete mode 100644 M3U8/scrapers/sport9.py create mode 100644 M3U8/scrapers/sportzone.py diff --git a/M3U8/fetch.py b/M3U8/fetch.py index d6d38499..85b0eeb2 100644 --- a/M3U8/fetch.py +++ b/M3U8/fetch.py @@ -16,7 +16,7 @@ from scrapers import ( ppv, roxie, shark, - sport9, + sportzone, streambtw, streamcenter, streamhub, @@ -70,7 +70,7 @@ async def main() -> None: asyncio.create_task(pixel.scrape(hdl_brwsr)), asyncio.create_task(ppv.scrape(xtrnl_brwsr)), asyncio.create_task(roxie.scrape(hdl_brwsr)), - # asyncio.create_task(sport9.scrape(xtrnl_brwsr)), + asyncio.create_task(sportzone.scrape(xtrnl_brwsr)), asyncio.create_task(streamcenter.scrape(hdl_brwsr)), # asyncio.create_task(streamhub.scrape(xtrnl_brwsr)), asyncio.create_task(streamsgate.scrape(xtrnl_brwsr)), @@ -117,7 +117,7 @@ async def main() -> None: | ppv.urls | roxie.urls | shark.urls - | sport9.urls + | sportzone.urls | streambtw.urls | streamcenter.urls | streamhub.urls diff --git a/M3U8/scrapers/sport9.py b/M3U8/scrapers/sport9.py deleted file mode 100644 index c48579b6..00000000 --- a/M3U8/scrapers/sport9.py +++ /dev/null @@ -1,148 +0,0 @@ -import asyncio -from functools import partial -from urllib.parse import urljoin - -from playwright.async_api import Browser -from selectolax.parser import HTMLParser - -from .utils import Cache, Time, get_logger, leagues, network - -log = get_logger(__name__) - -urls: dict[str, dict[str, str | float]] = {} - -TAG = "SPORT9" - -CACHE_FILE = Cache(TAG, exp=5_400) - -BASE_URL = "https://sport9.ru" - - -async def get_events(cached_keys: list[str]) -> list[dict[str, str]]: - now = Time.now() - - tasks = [ - network.request( - BASE_URL, - log=log, - params={"date": d.date()}, - ) - for d in [ - now.delta(days=-1), - now, - now.delta(days=1), - ] - ] - - results = await asyncio.gather(*tasks) - - events = [] - - if not (soups := [HTMLParser(html.content) for html in results if html]): - return events - - for soup in soups: - for card in soup.css("a.match-card"): - live_badge = card.css_first(".live-badge") - - if not live_badge or live_badge.text(strip=True).lower() != "live": - continue - - if not (sport_node := card.css_first(".tournament-name")): - continue - - sport = sport_node.text(strip=True) - - team_1_node = card.css_first(".team1 .team-name") - - team_2_node = card.css_first(".team2 .team-name") - - if team_1_node and team_2_node: - event = event = ( - f"{team_1_node.text(strip=True)} vs {team_2_node.text(strip=True)}" - ) - - elif team_1_node: - event = team_1_node.text(strip=True) - - elif team_2_node: - event = team_2_node.text(strip=True) - - else: - continue - - if f"[{sport}] {event} ({TAG})" in cached_keys: - continue - - if not (href := card.attributes.get("href")): - continue - - events.append( - { - "sport": sport, - "event": event, - "link": urljoin(BASE_URL, href), - } - ) - - return events - - -async def scrape(browser: Browser) -> None: - cached_urls = CACHE_FILE.load() - - cached_count = len(cached_urls) - - urls.update(cached_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()): - log.info(f"Processing {len(events)} new URL(s)") - - now = Time.clean(Time.now()) - - async with network.event_context(browser, stealth=False) as context: - for i, ev in enumerate(events, start=1): - async with network.event_page(context) as page: - handler = partial( - network.process_event, - url=(link := ev["link"]), - url_num=i, - page=page, - log=log, - ) - - url = await network.safe_process( - handler, - url_num=i, - semaphore=network.PW_S, - log=log, - ) - - if url: - sport, event = ev["sport"], ev["event"] - - key = f"[{sport}] {event} ({TAG})" - - tvg_id, logo = leagues.get_tvg_info(sport, event) - - entry = { - "url": url, - "logo": logo, - "base": "https://vividmosaica.com/", - "timestamp": now.timestamp(), - "id": tvg_id or "Live.Event.us", - "link": link, - } - - urls[key] = cached_urls[key] = entry - - log.info(f"Collected and cached {len(cached_urls) - cached_count} new event(s)") - - else: - log.info("No new events found") - - CACHE_FILE.write(cached_urls) diff --git a/M3U8/scrapers/sportzone.py b/M3U8/scrapers/sportzone.py new file mode 100644 index 00000000..eb5e60c8 --- /dev/null +++ b/M3U8/scrapers/sportzone.py @@ -0,0 +1,154 @@ +from functools import partial +from typing import Any + +from playwright.async_api import Browser + +from .utils import Cache, Time, get_logger, leagues, network + +log = get_logger(__name__) + +urls: dict[str, dict[str, str | float]] = {} + +TAG = "SPRTZONE" + +CACHE_FILE = Cache(TAG, exp=10_800) + +API_FILE = Cache(f"{TAG}-api", exp=19_800) + +API_URL = "https://sportzone.su/data.json" + + +async def refresh_api_cache(now_ts: float) -> list[dict[str, Any]]: + api_data = [{"timestamp": now_ts}] + + if r := await network.request(API_URL, log=log): + api_data: list[dict] = r.json().get("matches", []) + + if api_data: + for event in api_data: + event["ts"] = event.pop("timestamp") + + api_data[-1]["timestamp"] = now_ts + + return api_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) + end_dt = now.delta(minutes=30) + + for stream_group in api_data: + sport = stream_group.get("league") + + team_1, team_2 = stream_group.get("team1"), stream_group.get("team2") + + if not (sport and team_1 and team_2): + continue + + event_name = f"{team_1} vs {team_2}" + + if f"[{sport}] {event_name} ({TAG})" in cached_keys: + continue + + if not (event_ts := stream_group.get("ts")): + continue + + event_dt = Time.from_ts(int(f"{event_ts}"[:-3])) + + if not start_dt <= event_dt <= end_dt: + continue + + if not (event_channels := stream_group.get("channels")): + continue + + if not (event_links := event_channels[0].get("links")): + continue + + event_url: str = event_links[0] + + events.append( + { + "sport": sport, + "event": event_name, + "link": event_url, + } + ) + + return events + + +async def scrape(browser: Browser) -> None: + cached_urls = CACHE_FILE.load() + + valid_urls = {k: v for k, v in cached_urls.items() if v["url"]} + + valid_count = cached_count = len(valid_urls) + + urls.update(valid_urls) + + log.info(f"Loaded {cached_count} event(s) from cache") + + log.info('Scraping from "https://sportzone.su"') + + if events := await get_events(cached_urls.keys()): + log.info(f"Processing {len(events)} new URL(s)") + + now = Time.clean(Time.now()) + + async with network.event_context(browser, stealth=False) as context: + for i, ev in enumerate(events, start=1): + async with network.event_page(context) as page: + handler = partial( + network.process_event, + url=(link := ev["link"]), + url_num=i, + page=page, + log=log, + ) + + url = await network.safe_process( + handler, + url_num=i, + semaphore=network.PW_S, + log=log, + ) + + sport, event = ev["sport"], ev["event"] + + key = f"[{sport}] {event} ({TAG})" + + tvg_id, logo = leagues.get_tvg_info(sport, event) + + entry = { + "url": url, + "logo": logo, + "base": "https://vividmosaica.com/", + "timestamp": now.timestamp(), + "id": tvg_id or "Live.Event.us", + "link": link, + } + + cached_urls[key] = entry + + if url: + valid_count += 1 + + urls[key] = entry + + log.info(f"Collected and cached {valid_count - cached_count} new event(s)") + + else: + log.info("No new events found") + + CACHE_FILE.write(cached_urls) diff --git a/M3U8/scrapers/streamsgate.py b/M3U8/scrapers/streamsgate.py index 2a75cd73..f9b506a2 100644 --- a/M3U8/scrapers/streamsgate.py +++ b/M3U8/scrapers/streamsgate.py @@ -59,7 +59,7 @@ async def refresh_api_cache(now_ts: float) -> list[dict[str, Any]]: for ev in data: ev["ts"] = ev.pop("timestamp") - data[-1]["timestamp"] = now_ts + data[-1]["timestamp"] = now_ts return data