doms/iptv
1
0
Fork 0
mirror of https://github.com/doms9/iptv.git synced 2026-01-21 03:59:03 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

e

Browse source 
parse 'important games' section for totalsportek.py
This commit is contained in:
doms9 2026-01-20 15:18:17 -05:00
parent 0b7a4b1ae5
commit 00000d9553
1 changed files with 35 additions and 36 deletions
Download patch file Download diff file Expand all files Collapse all files

45
M3U8/scrapers/totalsportek.py
View file

@ -1,6 +1,6 @@
import re import re
from functools import partial from functools import partial
from urllib.parse import urljoin from urllib.parse import urljoin, urlparse
from selectolax.parser import HTMLParser from selectolax.parser import HTMLParser
@ -26,7 +26,9 @@ MIRRORS = [
] ]
def fix_league(s: str) -> str: def fix_txt(s: str) -> str:
s = " ".join(s.split())
return s.upper() if s.islower() else s return s.upper() if s.islower() else s
@ -34,9 +36,9 @@ async def process_event(href: str, url_num: int) -> tuple[str | None, str | None
valid_m3u8 = re.compile(r'var\s+(\w+)\s*=\s*"([^"]*)"', re.IGNORECASE) valid_m3u8 = re.compile(r'var\s+(\w+)\s*=\s*"([^"]*)"', re.IGNORECASE)
for x, mirror in enumerate(MIRRORS, start=1): for x, mirror in enumerate(MIRRORS, start=1):
base = mirror["base"] base: str = mirror["base"]
hex_decode = mirror["hex_decode"] hex_decode: bool = mirror["hex_decode"]
url = urljoin(base, href) url = urljoin(base, href)
@ -61,11 +63,10 @@ async def process_event(href: str, url_num: int) -> tuple[str | None, str | None
log.warning(f"M{x} | URL {url_num}) No Clappr source found.") log.warning(f"M{x} | URL {url_num}) No Clappr source found.")
continue continue
raw = match[2] raw: str = match[2]
try: try:
m3u8_url = bytes.fromhex(raw).decode("utf-8") if hex_decode else raw m3u8_url = bytes.fromhex(raw).decode("utf-8") if hex_decode else raw
except Exception as e: except Exception as e:
log.warning(f"M{x} | URL {url_num}) Decoding failed: {e}") log.warning(f"M{x} | URL {url_num}) Decoding failed: {e}")
continue continue
@ -75,13 +76,10 @@ async def process_event(href: str, url_num: int) -> tuple[str | None, str | None
return m3u8_url, iframe_src return m3u8_url, iframe_src
else:
log.warning(f"M{x} | URL {url_num}) No M3U8 found") log.warning(f"M{x} | URL {url_num}) No M3U8 found")
return None, None return None, None
return None, None
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]]:
events = [] events = []
@ -93,30 +91,31 @@ async def get_events(url: str, cached_keys: list[str]) -> list[dict[str, str]]:
sport = "Live Event" sport = "Live Event"
for box in soup.css(".div-main-box"): for node in soup.css("a"):
for node in box.iter(): if not node.attributes.get("class"):
if not (node_class := node.attributes.get("class")):
continue continue
if "my-1" in node_class: if (parent := node.parent) and "my-1" in parent.attributes.get("class", ""):
if span := node.css_first("span"): if span := node.css_first("span"):
sport = span.text(strip=True) sport = span.text(strip=True)
if node.tag == "a" and "nav-link2" in node_class: sport = fix_txt(sport)
if not (time_node := node.css_first(".col-3")):
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
href = urlparse(href).path if href.startswith("http") else href
if not (time_node := node.css_first(".col-3 span")):
continue continue
if time_node.text(strip=True) != "MatchStarted": if time_node.text(strip=True) != "MatchStarted":
continue continue
if not (href := node.attributes.get("href")) or href.startswith("http"): event_name = fix_txt(" vs ".join(teams))
continue
sport = fix_league(sport)
teams = [t.text(strip=True) for t in node.css(".col-7 .col-12")]
event_name = " vs ".join(teams)
if f"[{sport}] {event_name} ({TAG})" in cached_keys: if f"[{sport}] {event_name} ({TAG})" in cached_keys:
continue continue