update M3U8

This commit is contained in:
GitHub Actions Bot 2026-04-05 17:01:02 -04:00
parent b9ffecf2d1
commit 55c8b7cfd3
4 changed files with 1326 additions and 1386 deletions

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff

View file

@ -68,7 +68,7 @@ async def main() -> None:
asyncio.create_task(roxie.scrape(hdl_brwsr)), asyncio.create_task(roxie.scrape(hdl_brwsr)),
asyncio.create_task(streamcenter.scrape(hdl_brwsr)), asyncio.create_task(streamcenter.scrape(hdl_brwsr)),
# asyncio.create_task(streamhub.scrape(xtrnl_brwsr)), # asyncio.create_task(streamhub.scrape(xtrnl_brwsr)),
asyncio.create_task(streamsgate.scrape(xtrnl_brwsr)), # asyncio.create_task(streamsgate.scrape(xtrnl_brwsr)),
] ]
httpx_tasks = [ httpx_tasks = [

View file

@ -1,165 +1,165 @@
import re import re
from functools import partial from functools import partial
from playwright.async_api import Browser from playwright.async_api import Browser
from .utils import Cache, Time, get_logger, leagues, network from .utils import Cache, Time, get_logger, leagues, network
log = get_logger(__name__) log = get_logger(__name__)
urls: dict[str, dict[str, str | float]] = {} urls: dict[str, dict[str, str | float]] = {}
TAG = "PPV" TAG = "PPV"
CACHE_FILE = Cache(TAG, exp=10_800) CACHE_FILE = Cache(TAG, exp=10_800)
API_FILE = Cache(f"{TAG}-api", exp=19_800) API_FILE = Cache(f"{TAG}-api", exp=19_800)
API_MIRRORS = [ API_MIRRORS = [
"https://api.ppv.to/api/streams", "https://api.ppv.to/api/streams",
"https://api.ppv.cx/api/streams", "https://api.ppv.cx/api/streams",
"https://api.ppv.sh/api/streams", "https://api.ppv.sh/api/streams",
"https://api.ppv.la/api/streams", "https://api.ppv.la/api/streams",
] ]
def fix_url(s: str) -> str: def fix_url(s: str) -> str:
pattern = re.compile(r"index\.m3u8$", re.I) pattern = re.compile(r"index\.m3u8$", re.I)
return pattern.sub(r"tracks-v1a1/mono.ts.m3u8", s) return pattern.sub(r"tracks-v1a1/mono.ts.m3u8", s)
async def get_events(url: str, cached_keys: list[str]) -> list[dict[str, str]]: async def get_events(url: str, cached_keys: list[str]) -> list[dict[str, str]]:
now = Time.clean(Time.now()) now = Time.clean(Time.now())
if not (api_data := API_FILE.load(per_entry=False)): if not (api_data := API_FILE.load(per_entry=False)):
log.info("Refreshing API cache") log.info("Refreshing API cache")
api_data = {"timestamp": now.timestamp()} api_data = {"timestamp": now.timestamp()}
if r := await network.request(url, log=log): if r := await network.request(url, log=log):
api_data: dict = r.json() api_data: dict = r.json()
API_FILE.write(api_data) API_FILE.write(api_data)
events = [] events = []
start_dt = now.delta(minutes=-30) start_dt = now.delta(hours=-1)
end_dt = now.delta(minutes=30) end_dt = now.delta(minutes=5)
for stream_group in api_data.get("streams", []): for stream_group in api_data.get("streams", []):
sport = stream_group["category"] sport = stream_group["category"]
if sport == "24/7 Streams": if sport == "24/7 Streams":
continue continue
for event in stream_group.get("streams", []): for event in stream_group.get("streams", []):
name = event.get("name") name = event.get("name")
start_ts = event.get("starts_at") start_ts = event.get("starts_at")
logo = event.get("poster") logo = event.get("poster")
iframe = event.get("iframe") iframe = event.get("iframe")
if not (name and start_ts and iframe): if not (name and start_ts and iframe):
continue continue
if f"[{sport}] {name} ({TAG})" in cached_keys: if f"[{sport}] {name} ({TAG})" in cached_keys:
continue continue
event_dt = Time.from_ts(start_ts) event_dt = Time.from_ts(start_ts)
if not start_dt <= event_dt <= end_dt: if not start_dt <= event_dt <= end_dt:
continue continue
events.append( events.append(
{ {
"sport": sport, "sport": sport,
"event": name, "event": name,
"link": f"{iframe}#player=clappr#autoplay=true", "link": f"{iframe}#player=clappr#autoplay=true",
"logo": logo, "logo": logo,
"timestamp": event_dt.timestamp(), "timestamp": event_dt.timestamp(),
} }
) )
return events return events
async def scrape(browser: Browser) -> None: async def scrape(browser: Browser) -> None:
cached_urls = CACHE_FILE.load() cached_urls = CACHE_FILE.load()
valid_urls = {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"]}
valid_count = cached_count = len(valid_urls) valid_count = cached_count = len(valid_urls)
urls.update(valid_urls) urls.update(valid_urls)
log.info(f"Loaded {cached_count} event(s) from cache") log.info(f"Loaded {cached_count} event(s) from cache")
if not (api_url := await network.get_base(API_MIRRORS)): if not (api_url := await network.get_base(API_MIRRORS)):
log.warning("No working PPV mirrors") log.warning("No working PPV mirrors")
CACHE_FILE.write(cached_urls) CACHE_FILE.write(cached_urls)
return return
log.info(f'Scraping from "{api_url}"') log.info(f'Scraping from "{api_url}"')
if events := await get_events(api_url, cached_urls.keys()): if events := await get_events(api_url, cached_urls.keys()):
log.info(f"Processing {len(events)} new URL(s)") log.info(f"Processing {len(events)} new URL(s)")
async with network.event_context(browser, stealth=False) as context: async with network.event_context(browser, stealth=False) as context:
for i, ev in enumerate(events, start=1): for i, ev in enumerate(events, start=1):
async with network.event_page(context) as page: async with network.event_page(context) as page:
handler = partial( handler = partial(
network.process_event, network.process_event,
url=(link := ev["link"]), url=(link := ev["link"]),
url_num=i, url_num=i,
page=page, page=page,
timeout=6, timeout=6,
log=log, log=log,
) )
url = await network.safe_process( url = await network.safe_process(
handler, handler,
url_num=i, url_num=i,
semaphore=network.PW_S, semaphore=network.PW_S,
log=log, log=log,
) )
sport, event, logo, ts = ( sport, event, logo, ts = (
ev["sport"], ev["sport"],
ev["event"], ev["event"],
ev["logo"], ev["logo"],
ev["timestamp"], ev["timestamp"],
) )
key = f"[{sport}] {event} ({TAG})" key = f"[{sport}] {event} ({TAG})"
tvg_id, pic = leagues.get_tvg_info(sport, event) tvg_id, pic = leagues.get_tvg_info(sport, event)
entry = { entry = {
"url": url, "url": url,
"logo": logo or pic, "logo": logo or pic,
"base": link, "base": link,
"timestamp": ts, "timestamp": ts,
"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
entry["url"] = fix_url(url) entry["url"] = fix_url(url)
urls[key] = entry urls[key] = entry
log.info(f"Collected and cached {valid_count - cached_count} new event(s)") log.info(f"Collected and cached {valid_count - cached_count} new event(s)")
else: else:
log.info("No new events found") log.info("No new events found")
CACHE_FILE.write(cached_urls) CACHE_FILE.write(cached_urls)