mirror of
https://github.com/doms9/iptv.git
synced 2026-03-07 11:18:25 +01:00
176 lines
4.3 KiB
Python
176 lines
4.3 KiB
Python
import asyncio
|
|
import re
|
|
from functools import partial
|
|
|
|
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 = "WEBCAST"
|
|
|
|
CACHE_FILE = Cache(TAG, exp=19_800)
|
|
|
|
BASE_URLS = {
|
|
"MLB": "https://mlbwebcast.com",
|
|
# "NFL": "https://nflwebcast.com",
|
|
"NHL": "https://slapstreams.com",
|
|
}
|
|
|
|
|
|
def fix_event(s: str) -> str:
|
|
return " vs ".join(s.split("@"))
|
|
|
|
|
|
async def process_event(url: str, url_num: int) -> str | None:
|
|
if not (event_data := await network.request(url, log=log)):
|
|
log.info(f"URL {url_num}) Failed to load url.")
|
|
|
|
return
|
|
|
|
soup = HTMLParser(event_data.content)
|
|
|
|
if not (iframe := soup.css_first('iframe[name="srcFrame"]')):
|
|
log.warning(f"URL {url_num}) No iframe element found.")
|
|
|
|
return
|
|
|
|
if not (iframe_src := iframe.attributes.get("src")):
|
|
log.warning(f"URL {url_num}) No iframe source found.")
|
|
|
|
return
|
|
|
|
if not (
|
|
iframe_src_data := await network.request(
|
|
iframe_src,
|
|
headers={"Referer": url},
|
|
log=log,
|
|
)
|
|
):
|
|
log.info(f"URL {url_num}) Failed to load iframe source.")
|
|
|
|
return
|
|
|
|
pattern = re.compile(r"source:\s+(\'|\")(.*)(\'|\")", re.I)
|
|
|
|
if not (match := pattern.search(iframe_src_data.text)):
|
|
log.warning(f"URL {url_num}) No Clappr source found.")
|
|
|
|
return
|
|
|
|
log.info(f"URL {url_num}) Captured M3U8")
|
|
|
|
return match[2]
|
|
|
|
|
|
async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
|
|
tasks = [network.request(url, log=log) for url in BASE_URLS.values()]
|
|
|
|
results = await asyncio.gather(*tasks)
|
|
|
|
events = []
|
|
|
|
if not (
|
|
soups := [(HTMLParser(html.content), html.url) for html in results if html]
|
|
):
|
|
return events
|
|
|
|
for soup, url in soups:
|
|
sport = next((k for k, v in BASE_URLS.items() if v == url), "Live Event")
|
|
|
|
for row in soup.css("tr.singele_match_date"):
|
|
if not (vs_node := row.css_first("td.teamvs a")):
|
|
continue
|
|
|
|
event_name = vs_node.text(strip=True)
|
|
|
|
for span in vs_node.css("span.mtdate"):
|
|
date = span.text(strip=True)
|
|
|
|
event_name = event_name.replace(date, "").strip()
|
|
|
|
if not (href := vs_node.attributes.get("href")):
|
|
continue
|
|
|
|
event = fix_event(event_name)
|
|
|
|
if f"[{sport}] {event} ({TAG})" in cached_keys:
|
|
continue
|
|
|
|
events.append(
|
|
{
|
|
"sport": sport,
|
|
"event": event,
|
|
"link": href,
|
|
}
|
|
)
|
|
|
|
return events
|
|
|
|
|
|
async def scrape() -> 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(f'Scraping from "{' & '.join(BASE_URLS.values())}"')
|
|
|
|
events = await get_events(cached_urls.keys())
|
|
|
|
if events:
|
|
log.info(f"Processing {len(events)} new URL(s)")
|
|
|
|
now = Time.clean(Time.now())
|
|
|
|
for i, ev in enumerate(events, start=1):
|
|
handler = partial(
|
|
process_event,
|
|
url=(link := ev["link"]),
|
|
url_num=i,
|
|
)
|
|
|
|
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": BASE_URLS[sport],
|
|
"timestamp": now.timestamp(),
|
|
"id": tvg_id or "Live.Event.us",
|
|
"link": link,
|
|
}
|
|
|
|
cached_urls[key] = entry
|
|
|
|
if url:
|
|
valid_count += 1
|
|
|
|
urls[key] = entry
|
|
|
|
if new_count := valid_count - 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)
|