- edit scraping for istreameast.py
This commit is contained in:
doms9 2026-04-10 21:59:49 -04:00
parent d9b1e9449c
commit 00000d9ff3

View file

@ -1,4 +1,3 @@
import base64
import re import re
from functools import partial from functools import partial
@ -17,39 +16,36 @@ CACHE_FILE = Cache(TAG, exp=10_800)
BASE_URL = "https://istreameast.app" BASE_URL = "https://istreameast.app"
async def process_event(url: str, url_num: int) -> str | None: async def process_event(url: str, url_num: int) -> tuple[str | None, str | None]:
nones = None, None
if not (event_data := await network.request(url, log=log)): if not (event_data := await network.request(url, log=log)):
log.warning(f"URL {url_num}) Failed to load url.") log.warning(f"URL {url_num}) Failed to load url.")
return nones
return
soup = HTMLParser(event_data.content) soup = HTMLParser(event_data.content)
if not (iframe := soup.css_first("iframe#wp_player")): if not (iframe := soup.css_first("iframe#wp_player")):
log.warning(f"URL {url_num}) No iframe element found.") log.warning(f"URL {url_num}) No iframe element found.")
return nones
return
if not (iframe_src := iframe.attributes.get("src")): if not (iframe_src := iframe.attributes.get("src")):
log.warning(f"URL {url_num}) No iframe source found.") log.warning(f"URL {url_num}) No iframe source found.")
return nones
return
if not (iframe_src_data := await network.request(iframe_src, log=log)): if not (iframe_src_data := await network.request(iframe_src, log=log)):
log.warning(f"URL {url_num}) Failed to load iframe source.") log.warning(f"URL {url_num}) Failed to load iframe source.")
return nones
return pattern = re.compile(r'const\s+source\s+=\s+"([^"]*)"', re.I)
pattern = re.compile(r"source:\s*window\.atob\(\s*'([^']+)'\s*\)", re.I)
if not (match := pattern.search(iframe_src_data.text)): if not (match := pattern.search(iframe_src_data.text)):
log.warning(f"URL {url_num}) No Clappr source found.") log.warning(f"URL {url_num}) No Clappr source found.")
return nones
return
log.info(f"URL {url_num}) Captured M3U8") log.info(f"URL {url_num}) Captured M3U8")
return base64.b64decode(match[1]).decode("utf-8") return match[1], iframe_src
async def get_events(cached_keys: list[str]) -> list[dict[str, str]]: async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
@ -124,7 +120,7 @@ async def scrape() -> None:
url_num=i, url_num=i,
) )
url = await network.safe_process( url, iframe = await network.safe_process(
handler, handler,
url_num=i, url_num=i,
semaphore=network.HTTP_S, semaphore=network.HTTP_S,
@ -140,7 +136,7 @@ async def scrape() -> None:
entry = { entry = {
"url": url, "url": url,
"logo": logo, "logo": logo,
"base": "https://gooz.aapmains.net", "base": iframe,
"timestamp": now.timestamp(), "timestamp": now.timestamp(),
"id": tvg_id or "Live.Event.us", "id": tvg_id or "Live.Event.us",
"link": link, "link": link,