doms/iptv
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

e

Browse source
This commit is contained in:
doms9 2025-12-05 04:10:29 -05:00
parent 1c377388ac
commit 00000d9c9a
3 changed files with 353 additions and 179 deletions
Download patch file Download diff file Expand all files Collapse all files

6
M3U8/fetch.py
View file

@ -12,7 +12,7 @@ from scrapers import (
shark, shark,
sport9, sport9,
streambtw, streambtw,
streameast, streamcenter,
streamfree, streamfree,
strmd, strmd,
tvpass, tvpass,
@ -53,7 +53,7 @@ async def main() -> None:
asyncio.create_task(shark.scrape(network.client)), asyncio.create_task(shark.scrape(network.client)),
asyncio.create_task(sport9.scrape(network.client)), asyncio.create_task(sport9.scrape(network.client)),
asyncio.create_task(streambtw.scrape(network.client)), asyncio.create_task(streambtw.scrape(network.client)),
#asyncio.create_task(streameast.scrape(network.client)), asyncio.create_task(streamcenter.scrape(network.client)),
asyncio.create_task(streamfree.scrape(network.client)), asyncio.create_task(streamfree.scrape(network.client)),
asyncio.create_task(strmd.scrape(network.client)), asyncio.create_task(strmd.scrape(network.client)),
asyncio.create_task(tvpass.scrape(network.client)), asyncio.create_task(tvpass.scrape(network.client)),
@ -71,7 +71,7 @@ async def main() -> None:
| shark.urls | shark.urls
| sport9.urls | sport9.urls
| streambtw.urls | streambtw.urls
| streameast.urls | streamcenter.urls
| strmd.urls | strmd.urls
| streamfree.urls | streamfree.urls
| tvpass.urls | tvpass.urls

352
M3U8/scrapers/streameast.py → M3U8/scrapers/old/streameast.py
View file

@ -1,176 +1,176 @@
from functools import partial from functools import partial
from urllib.parse import urljoin from urllib.parse import urljoin
import httpx import httpx
from playwright.async_api import async_playwright from playwright.async_api import async_playwright
from selectolax.parser import HTMLParser from selectolax.parser import HTMLParser
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]] = {}
CACHE_FILE = Cache("streameast.json", exp=10_800) CACHE_FILE = Cache("streameast.json", exp=10_800)
prefixes = { prefixes = {
"ga": None, "ga": None,
"ph": None, "ph": None,
"sg": None, "sg": None,
"ch": None, "ch": None,
"ec": None, "ec": None,
"fi": None, "fi": None,
"ms": None, "ms": None,
"ps": None, "ps": None,
"cf": None, "cf": None,
"sk": None, "sk": None,
"co": "the", "co": "the",
"fun": "the", "fun": "the",
"ru": "the", "ru": "the",
"su": "the", "su": "the",
} }
MIRRORS = [ MIRRORS = [
*[f"https://streameast.{ext}" for ext in prefixes if not prefixes[ext]], *[f"https://streameast.{ext}" for ext in prefixes if not prefixes[ext]],
*[f"https://thestreameast.{ext}" for ext in prefixes if prefixes[ext] == "the"], *[f"https://thestreameast.{ext}" for ext in prefixes if prefixes[ext] == "the"],
] ]
TAG = "STRMEST" TAG = "STRMEST"
async def get_events( async def get_events(
client: httpx.AsyncClient, client: httpx.AsyncClient,
url: str, url: str,
cached_keys: set[str], cached_keys: set[str],
) -> list[dict[str, str]]: ) -> list[dict[str, str]]:
try: try:
r = await client.get(url) r = await client.get(url)
r.raise_for_status() r.raise_for_status()
except Exception as e: except Exception as e:
log.error(f'Failed to fetch "{url}": {e}') log.error(f'Failed to fetch "{url}": {e}')
return [] return []
soup = HTMLParser(r.content) soup = HTMLParser(r.content)
events = [] events = []
now = Time.clean(Time.now()) now = Time.clean(Time.now())
start_dt = now.delta(minutes=-30) start_dt = now.delta(minutes=-30)
end_dt = now.delta(minutes=30) end_dt = now.delta(minutes=30)
for section in soup.css("div.se-sport-section"): for section in soup.css("div.se-sport-section"):
if not (sport := section.attributes.get("data-sport-name", "").strip()): if not (sport := section.attributes.get("data-sport-name", "").strip()):
continue continue
for a in section.css("a.uefa-card"): for a in section.css("a.uefa-card"):
if not (href := a.attributes.get("href")): if not (href := a.attributes.get("href")):
continue continue
link = urljoin(url, href) link = urljoin(url, href)
team_spans = [t.text(strip=True) for t in a.css("span.uefa-name")] team_spans = [t.text(strip=True) for t in a.css("span.uefa-name")]
if len(team_spans) == 2: if len(team_spans) == 2:
name = f"{team_spans[0]} vs {team_spans[1]}" name = f"{team_spans[0]} vs {team_spans[1]}"
elif len(team_spans) == 1: elif len(team_spans) == 1:
name = team_spans[0] name = team_spans[0]
else: else:
continue continue
if not (time_span := a.css_first(".uefa-time")): if not (time_span := a.css_first(".uefa-time")):
continue continue
time_text = time_span.text(strip=True) time_text = time_span.text(strip=True)
timestamp = int(a.attributes.get("data-time", Time.default_8())) timestamp = int(a.attributes.get("data-time", Time.default_8()))
key = f"[{sport}] {name} ({TAG})" key = f"[{sport}] {name} ({TAG})"
if cached_keys & {key}: if cached_keys & {key}:
continue continue
event_dt = Time.from_ts(timestamp) event_dt = Time.from_ts(timestamp)
if time_text == "LIVE" or (start_dt <= event_dt <= end_dt): if time_text == "LIVE" or (start_dt <= event_dt <= end_dt):
events.append( events.append(
{ {
"sport": sport, "sport": sport,
"event": name, "event": name,
"link": link, "link": link,
"timestamp": timestamp, "timestamp": timestamp,
} }
) )
return events return events
async def scrape(client: httpx.AsyncClient) -> None: async def scrape(client: httpx.AsyncClient) -> None:
cached_urls = CACHE_FILE.load() cached_urls = CACHE_FILE.load()
cached_count = len(cached_urls) cached_count = len(cached_urls)
urls.update(cached_urls) urls.update(cached_urls)
log.info(f"Loaded {cached_count} event(s) from cache") log.info(f"Loaded {cached_count} event(s) from cache")
if not (base_url := await network.get_base(MIRRORS)): if not (base_url := await network.get_base(MIRRORS)):
log.warning("No working Streameast mirrors") log.warning("No working Streameast mirrors")
CACHE_FILE.write(cached_urls) CACHE_FILE.write(cached_urls)
return return
log.info(f'Scraping from "{base_url}"') log.info(f'Scraping from "{base_url}"')
events = await get_events( events = await get_events(
client, client,
base_url, base_url,
set(cached_urls.keys()), set(cached_urls.keys()),
) )
log.info(f"Processing {len(events)} new URL(s)") log.info(f"Processing {len(events)} new URL(s)")
if events: if events:
async with async_playwright() as p: async with async_playwright() as p:
browser, context = await network.browser(p, browser="brave") browser, context = await network.browser(p, browser="brave")
for i, ev in enumerate(events, start=1): for i, ev in enumerate(events, start=1):
handler = partial( handler = partial(
network.process_event, network.process_event,
url=ev["link"], url=ev["link"],
url_num=i, url_num=i,
context=context, context=context,
log=log, log=log,
) )
url = await network.safe_process( url = await network.safe_process(
handler, handler,
url_num=i, url_num=i,
log=log, log=log,
) )
if url: if url:
sport, event, ts = ev["sport"], ev["event"], ev["timestamp"] sport, event, ts = ev["sport"], ev["event"], ev["timestamp"]
tvg_id, logo = leagues.get_tvg_info(sport, event) tvg_id, logo = leagues.get_tvg_info(sport, event)
key = f"[{sport}] {event} ({TAG})" key = f"[{sport}] {event} ({TAG})"
entry = { entry = {
"url": url, "url": url,
"logo": logo, "logo": logo,
"base": "https://embedsports.top/", "base": "https://embedsports.top/",
"timestamp": ts, "timestamp": ts,
"id": tvg_id or "Live.Event.us", "id": tvg_id or "Live.Event.us",
} }
urls[key] = cached_urls[key] = entry urls[key] = cached_urls[key] = entry
await browser.close() await browser.close()
if new_count := len(cached_urls) - cached_count: if new_count := len(cached_urls) - cached_count:
log.info(f"Collected and cached {new_count} new event(s)") log.info(f"Collected and cached {new_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)

174
M3U8/scrapers/streamcenter.py Normal file
View file

@ -0,0 +1,174 @@
from functools import partial
import httpx
from playwright.async_api import async_playwright
from .utils import Cache, Time, get_logger, leagues, network
log = get_logger(__name__)
urls: dict[str, dict[str, str | float]] = {}
CACHE_FILE = Cache("streamcenter.json", exp=10_800)
API_FILE = Cache("streamcenter-api.json", exp=28_800)
BASE_URL = "https://backendstreamcenter.youshop.pro:488/api/Parties"
TAG = "STRMCNTR"
categories = {
4: "Basketball",
9: "Football",
13: "Baseball",
14: "American Football",
15: "Motor Sport",
16: "Hockey",
17: "Fight MMA",
18: "Boxing",
19: "NCAA Sports",
20: "WWE",
21: "Tennis",
}
async def refresh_api_cache(
client: httpx.AsyncClient,
url: str,
now_ts: float,
) -> list[dict[str, str | int]]:
log.info("Refreshing API cache")
try:
r = await client.get(url, params={"pageNumber": 1, "pageSize": 500})
r.raise_for_status()
except Exception as e:
log.error(f'Failed to fetch "{url}": {e}')
return {}
data = r.json()
data[-1]["timestamp"] = now_ts
return data
async def get_events(
client: httpx.AsyncClient,
cached_keys: set[str],
) -> list[dict[str, str]]:
now = Time.clean(Time.now())
if not (api_data := API_FILE.load(per_entry=False, index=-1)):
api_data = await refresh_api_cache(
client,
BASE_URL,
now.timestamp(),
)
API_FILE.write(api_data)
events = []
start_dt = now.delta(minutes=-30)
end_dt = now.delta(minutes=30)
for stream_group in api_data:
category_id: int = stream_group.get("categoryId")
name: str = stream_group.get("gameName")
iframe: str = stream_group.get("videoUrl")
event_time: str = stream_group.get("beginPartie")
if not (name and category_id and iframe and event_time):
continue
event_dt = Time.from_str(event_time, timezone="UTC")
if not start_dt <= event_dt <= end_dt:
continue
if not (sport := categories.get(category_id)):
continue
key = f"[{sport}] {name} ({TAG})"
if cached_keys & {key}:
continue
events.append(
{
"sport": sport,
"event": name,
"link": iframe.split("<")[0],
"timestamp": event_dt.timestamp(),
}
)
return events
async def scrape(client: httpx.AsyncClient) -> 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}"')
events = await get_events(client, set(cached_urls.keys()))
log.info(f"Processing {len(events)} new URL(s)")
if events:
async with async_playwright() as p:
browser, context = await network.browser(p)
for i, ev in enumerate(events, start=1):
handler = partial(
network.process_event,
url=ev["link"],
url_num=i,
context=context,
log=log,
)
url = await network.safe_process(
handler,
url_num=i,
log=log,
)
if url:
sport, event, ts = (
ev["sport"],
ev["event"],
ev["timestamp"],
)
key = f"[{sport}] {event} ({TAG})"
tvg_id, logo = leagues.get_tvg_info(sport, event)
entry = {
"url": url,
"logo": logo,
"base": "https://streamcenter.xyz",
"timestamp": ts,
"id": tvg_id or "Live.Event.us",
}
urls[key] = cached_urls[key] = entry
await browser.close()
if new_count := len(cached_urls) - cached_count:
log.info(f"Collected and cached {new_count} new event(s)")
else:
log.info("No new events found")
CACHE_FILE.write(cached_urls)