edit scraping method for roxie.py
This commit is contained in:
doms9 2026-02-11 20:29:22 -05:00
parent 2e528dd8b2
commit 00000d9a6c
2 changed files with 54 additions and 48 deletions

View file

@ -1,8 +1,8 @@
import asyncio
import re
from functools import partial
from urllib.parse import urljoin
from playwright.async_api import Browser
from selectolax.parser import HTMLParser
from .utils import Cache, Time, get_logger, leagues, network
@ -30,6 +30,22 @@ SPORT_ENDPOINTS = {
}
async def process_event(url: str, url_num: int) -> str | None:
if not (html_data := await network.request(url, log=log)):
return
valid_m3u8 = re.compile(r"'clappr',\s+'([^\"]*)'", re.IGNORECASE)
if not (match := valid_m3u8.search(html_data.text)):
log.info(f"URL {url_num}) No M3U8 found")
return
log.info(f"URL {url_num}) Captured M3U8")
return match[1]
async def refresh_html_cache(
url: str,
sport: str,
@ -99,8 +115,8 @@ async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
live = []
start_ts = now.delta(hours=-1).timestamp()
end_ts = now.delta(minutes=5).timestamp()
start_ts = now.delta(minutes=-30).timestamp()
end_ts = now.delta(minutes=30).timestamp()
for k, v in events.items():
if k in cached_keys:
@ -114,14 +130,12 @@ async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
return live
async def scrape(browser: Browser) -> None:
async def scrape() -> None:
cached_urls = CACHE_FILE.load()
valid_urls = {k: v for k, v in cached_urls.items() if v["url"]}
cached_count = len(cached_urls)
valid_count = cached_count = len(valid_urls)
urls.update(valid_urls)
urls.update(cached_urls)
log.info(f"Loaded {cached_count} event(s) from cache")
@ -132,52 +146,44 @@ async def scrape(browser: Browser) -> None:
log.info(f"Processing {len(events)} new URL(s)")
if events:
async with network.event_context(browser) as context:
for i, ev in enumerate(events, start=1):
async with network.event_page(context) as page:
handler = partial(
network.process_event,
url=ev["link"],
url_num=i,
page=page,
log=log,
)
for i, ev in enumerate(events, start=1):
handler = partial(
process_event,
url=ev["link"],
url_num=i,
)
url = await network.safe_process(
handler,
url_num=i,
semaphore=network.PW_S,
log=log,
)
url = await network.safe_process(
handler,
url_num=i,
semaphore=network.HTTP_S,
log=log,
)
sport, event, ts, link = (
ev["sport"],
ev["event"],
ev["event_ts"],
ev["link"],
)
if url:
sport, event, ts, link = (
ev["sport"],
ev["event"],
ev["event_ts"],
ev["link"],
)
tvg_id, logo = leagues.get_tvg_info(sport, event)
tvg_id, logo = leagues.get_tvg_info(sport, event)
key = f"[{sport}] {event} ({TAG})"
key = f"[{sport}] {event} ({TAG})"
entry = {
"url": url,
"logo": logo,
"base": BASE_URL,
"timestamp": ts,
"id": tvg_id or "Live.Event.us",
"link": link,
}
entry = {
"url": url,
"logo": logo,
"base": BASE_URL,
"timestamp": ts,
"id": tvg_id or "Live.Event.us",
"link": link,
}
cached_urls[key] = entry
urls[key] = cached_urls[key] = entry
if url:
valid_count += 1
urls[key] = entry
if new_count := valid_count - cached_count:
if new_count := len(cached_urls) - cached_count:
log.info(f"Collected and cached {new_count} new event(s)")
else: