doms/iptv
0
0
Fork 1
mirror of https://github.com/doms9/iptv.git synced 2026-06-14 12:36:27 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

e

Browse source 
- edit scraping for streambiz.py
This commit is contained in:
doms9 2026-06-08 20:48:36 -04:00
parent c0a01a26be
commit 00000d9543
1 changed files with 5 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

28
M3U8/scrapers/streambiz.py
View file

@ -1,5 +1,4 @@
import asyncio import asyncio
import re
from functools import partial from functools import partial
from urllib.parse import urljoin from urllib.parse import urljoin
@ -12,7 +11,7 @@ log = get_logger(__name__)
urls: dict[str, dict[str, str | float]] = {} urls: dict[str, dict[str, str | float]] = {}
TAG = "SPRTPASS" TAG = "STRMBIZ"
CACHE_FILE = Cache(TAG, exp=10_800) CACHE_FILE = Cache(TAG, exp=10_800)
@ -118,8 +117,6 @@ async def process_event(
async def get_events(cached_links: set[str]) -> list[dict[str, str]]: async def get_events(cached_links: set[str]) -> list[dict[str, str]]:
now = Time.clean(Time.now())
tasks = [network.request(url, log=log) for url in SPORT_URLS.values()] tasks = [network.request(url, log=log) for url in SPORT_URLS.values()]
results = await asyncio.gather(*tasks) results = await asyncio.gather(*tasks)
@ -131,11 +128,6 @@ async def get_events(cached_links: set[str]) -> list[dict[str, str]]:
): ):
return events return events
start_dt = now.delta(minutes=-30)
end_dt = now.delta(minutes=30)
date_ptrn = re.compile(r"\d{4}-\d{2}-\d{2}T\d{2}:\d{2}Z", re.I)
for soup, url in soups: for soup, url in soups:
sport = next((k for k, v in SPORT_URLS.items() if v == url), "Live Event") sport = next((k for k, v in SPORT_URLS.items() if v == url), "Live Event")
@ -146,25 +138,13 @@ async def get_events(cached_links: set[str]) -> list[dict[str, str]]:
elif cached_links & {link := urljoin(BASE_URL, href)}: elif cached_links & {link := urljoin(BASE_URL, href)}:
continue continue
if (scr_elem := event.css_first("script")) and ( if not event.css_first("span.status-badge.badge.bg-success"):
match := date_ptrn.search(scr_elem.text(strip=True))
):
event_dt = Time.fromisoformat(match[0]).to_tz("EST")
elif event.css_first('span[id*="gameStatus-"]'):
event_dt = now
else:
continue
if not start_dt <= event_dt <= end_dt:
continue continue
events.append( events.append(
{ {
"sport": sport, "sport": sport,
"link": link, "link": link,
"timestamp": event_dt.timestamp(),
} }
) )
@ -189,6 +169,8 @@ async def scrape(browser: Browser) -> None:
if events := await get_events(cached_links): if events := await get_events(cached_links):
log.info(f"Processing {len(events)} URL(s)") log.info(f"Processing {len(events)} URL(s)")
now = Time.clean(Time.now())
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:
@ -214,7 +196,7 @@ async def scrape(browser: Browser) -> None:
"url": url, "url": url,
"logo": logo, "logo": logo,
"base": ifr_src, "base": ifr_src,
"timestamp": ev["timestamp"], "timestamp": now.timestamp(),
"id": tvg_id or "Live.Event.us", "id": tvg_id or "Live.Event.us",
"link": link, "link": link,
} }