doms/iptv
1
0
Fork 1
mirror of https://github.com/doms9/iptv.git synced 2026-03-07 11:18:25 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

e

Browse source 
edit tvapp.py scraping
This commit is contained in:
doms9 2026-02-13 00:42:13 -05:00
parent 166fb66aa1
commit 00000d9812
1 changed files with 9 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

26
M3U8/scrapers/tvapp.py
View file

@ -25,7 +25,7 @@ def fix_url(s: str) -> str:
return urljoin(f"http://{base}", parsed.path.replace("tracks-v1a1/", "")) return urljoin(f"http://{base}", parsed.path.replace("tracks-v1a1/", ""))
async def get_events(cached_keys: list[str]) -> list[dict[str, str]]: async def get_events() -> list[dict[str, str]]:
events = [] events = []
if not (html_data := await network.request(BASE_URL, log=log)): if not (html_data := await network.request(BASE_URL, log=log)):
@ -45,9 +45,6 @@ async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
for a in row.css("a.list-group-item[href]"): for a in row.css("a.list-group-item[href]"):
event_name = a.text(strip=True).split(":", 1)[0] event_name = a.text(strip=True).split(":", 1)[0]
if f"[{sport}] {event_name} ({TAG})" in cached_keys:
continue
if not (href := a.attributes.get("href")): if not (href := a.attributes.get("href")):
continue continue
@ -63,17 +60,16 @@ async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
async def scrape(browser: Browser) -> None: async def scrape(browser: Browser) -> None:
cached_urls = CACHE_FILE.load() if cached := CACHE_FILE.load():
urls.update(cached)
cached_count = len(cached_urls) log.info(f"Loaded {len(urls)} event(s) from cache")
urls.update(cached_urls) return
log.info(f"Loaded {cached_count} event(s) from cache")
log.info(f'Scraping from "{BASE_URL}"') log.info(f'Scraping from "{BASE_URL}"')
events = await get_events(cached_urls.keys()) events = await get_events()
log.info(f"Processing {len(events)} new URL(s)") log.info(f"Processing {len(events)} new URL(s)")
@ -118,12 +114,8 @@ async def scrape(browser: Browser) -> None:
"link": link, "link": link,
} }
urls[key] = cached_urls[key] = entry urls[key] = entry
if new_count := len(cached_urls) - cached_count: log.info(f"Collected and cached {len(urls)} new event(s)")
log.info(f"Collected and cached {new_count} new event(s)")
else: CACHE_FILE.write(urls)
log.info("No new events found")
CACHE_FILE.write(cached_urls)