- remove xstreameast.py
- add totalsportek mirror
This commit is contained in:
doms9 2026-04-18 01:29:27 -04:00
parent b98c834004
commit 00000d967c
3 changed files with 80 additions and 231 deletions

View file

@ -11,11 +11,12 @@ log = get_logger(__name__)
urls: dict[str, dict[str, str | float]] = {}
TAG = "TOTALSPRTK"
CACHE_FILE = Cache("TSPRTK", exp=28_800)
CACHE_FILE = Cache(TAG, exp=28_800)
BASE_URL = "https://live3.totalsportek.fyi"
BASES = {
"TSPRTK1": "https://live.totalsportek.fyi",
"TSPRTK3": "https://live3.totalsportek.fyi",
}
def fix_txt(s: str) -> str:
@ -24,36 +25,43 @@ def fix_txt(s: str) -> str:
return s.upper() if s.islower() else s
async def process_event(url: str, url_num: int) -> str | None:
if not (event_data := await network.request(url, log=log)):
log.warning(f"URL {url_num}) Failed to load url.")
async def process_ts1(ifr_src: str, url_num: int) -> str | None:
if not (ifr_src_data := await network.request(ifr_src, log=log)):
log.info(f"URL {url_num}) Failed to load iframe source.")
return
soup_1 = HTMLParser(event_data.content)
valid_m3u8 = re.compile(r'(var|const)\s+(\w+)\s*=\s*"([^"]*)"', re.I)
iframe_1 = soup_1.css_first("iframe")
if not iframe_1 or not (iframe_1_src := iframe_1.attributes.get("src")):
log.warning(f"URL {url_num}) No iframe element found. (IFR1)")
if not (match := valid_m3u8.search(ifr_src_data.text)):
log.warning(f"URL {url_num}) No Clappr source found.")
return
if not (iframe_1_src_data := await network.request(iframe_1_src, log=log)):
if len(encoded := match[2]) < 20:
encoded = match[3]
log.info(f"URL {url_num}) Captured M3U8")
return bytes.fromhex(encoded).decode("utf-8")
async def process_ts3(ifr_src: str, url_num: int) -> str | None:
if not (ifr_1_src_data := await network.request(ifr_src, log=log)):
log.warning(f"URL {url_num}) Failed to load iframe source. (IFR1)")
return
soup_2 = HTMLParser(iframe_1_src_data.content)
soup_2 = HTMLParser(ifr_1_src_data.content)
iframe_2 = soup_2.css_first("iframe")
ifr_2 = soup_2.css_first("iframe")
if not iframe_2 or not (iframe_2_src := iframe_2.attributes.get("src")):
if not ifr_2 or not (ifr_2_src := ifr_2.attributes.get("src")):
log.warning(f"URL {url_num}) No iframe element found. (IFR2)")
return
if not (
iframe_2_src_data := await network.request(
iframe_2_src,
ifr_2_src_data := await network.request(
ifr_2_src,
headers={"Referer": ifr_src},
log=log,
headers={"Referer": iframe_1_src},
)
):
log.warning(f"URL {url_num}) Failed to load iframe source. (IFR2)")
@ -61,7 +69,7 @@ async def process_event(url: str, url_num: int) -> str | None:
valid_m3u8 = re.compile(r'currentStreamUrl\s+=\s+"([^"]*)"', re.I)
if not (match := valid_m3u8.search(iframe_2_src_data.text)):
if not (match := valid_m3u8.search(ifr_2_src_data.text)):
log.warning(f"URL {url_num}) No Clappr source found.")
return
@ -70,52 +78,74 @@ async def process_event(url: str, url_num: int) -> str | None:
return json.loads(f'"{match[1]}"')
async def process_event(url: str, url_num: int, tag: str) -> str | None:
if not (event_data := await network.request(url, log=log)):
log.warning(f"URL {url_num}) Failed to load url.")
return
soup = HTMLParser(event_data.content)
iframe = soup.css_first("iframe")
if not iframe or not (iframe_src := iframe.attributes.get("src")):
log.warning(f"URL {url_num}) No valid iframe source found.")
return
return (
await process_ts1(iframe_src, url_num)
if tag == "TSPRTK1"
else await process_ts3(iframe_src, url_num)
)
async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
events = []
if not (html_data := await network.request(BASE_URL, log=log)):
if not (html_data := await network.request(BASES["TSPRTK1"], log=log)):
return events
soup = HTMLParser(html_data.content)
sport = "Live Event"
for node in soup.css("a"):
if not node.attributes.get("class"):
continue
for tag, url in BASES.items():
for node in soup.css("a"):
if not node.attributes.get("class"):
continue
if (parent := node.parent) and "my-1" in parent.attributes.get("class", ""):
if span := node.css_first("span"):
sport = span.text(strip=True)
if (parent := node.parent) and "my-1" in parent.attributes.get("class", ""):
if span := node.css_first("span"):
sport = span.text(strip=True)
sport = fix_txt(sport)
sport = fix_txt(sport)
if not (teams := [t.text(strip=True) for t in node.css(".col-7 .col-12")]):
continue
if not (teams := [t.text(strip=True) for t in node.css(".col-7 .col-12")]):
continue
if not (href := node.attributes.get("href")):
continue
if not (href := node.attributes.get("href")):
continue
href = urlparse(href).path if href.startswith("http") else href
href = urlparse(href).path if href.startswith("http") else href
if not (time_node := node.css_first(".col-3 span")):
continue
if not (time_node := node.css_first(".col-3 span")):
continue
if time_node.text(strip=True).lower() != "matchstarted":
continue
if time_node.text(strip=True).lower() != "matchstarted":
continue
event_name = fix_txt(" vs ".join(teams))
event_name = fix_txt(" vs ".join(teams))
if f"[{sport}] {event_name} ({TAG})" in cached_keys:
continue
if f"[{sport}] {event_name} ({tag})" in cached_keys:
continue
events.append(
{
"sport": sport,
"event": event_name,
"link": urljoin(f"{html_data.url}", href),
}
)
events.append(
{
"sport": sport,
"event": event_name,
"tag": tag,
"link": urljoin(url, href),
}
)
return events
@ -131,7 +161,7 @@ async def scrape() -> None:
log.info(f"Loaded {cached_count} event(s) from cache")
log.info(f'Scraping from "{BASE_URL}"')
log.info('Scraping from "https://live.totalsportek.fyi"')
if events := await get_events(cached_urls.keys()):
log.info(f"Processing {len(events)} new URL(s)")
@ -143,6 +173,7 @@ async def scrape() -> None:
process_event,
url=(link := ev["link"]),
url_num=i,
tag=(tag := ev["tag"]),
)
url = await network.safe_process(
@ -154,7 +185,7 @@ async def scrape() -> None:
sport, event = ev["sport"], ev["event"]
key = f"[{sport}] {event} ({TAG})"
key = f"[{sport}] {event} ({tag})"
tvg_id, logo = leagues.get_tvg_info(sport, event)