e
This commit is contained in:
doms9
parent
6a93221b78
commit
00000d9729
1 changed files with 118 additions and 118 deletions
|
|
@ -1,118 +1,118 @@
|
||||||
import re
|
import re
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
from urllib.parse import urljoin
|
from urllib.parse import urljoin
|
||||||
|
|
||||||
import httpx
|
import httpx
|
||||||
from selectolax.parser import HTMLParser
|
from selectolax.parser import HTMLParser
|
||||||
|
|
||||||
from .utils import Cache, Time, get_logger, leagues, network
|
from .utils import Cache, Time, get_logger, leagues, network
|
||||||
|
|
||||||
log = get_logger(__name__)
|
log = get_logger(__name__)
|
||||||
|
|
||||||
urls: dict[str, dict[str, str]] = {}
|
urls: dict[str, dict[str, str]] = {}
|
||||||
|
|
||||||
BASE_URL = "https://streambtw.com/"
|
BASE_URL = "https://streambtw.com/"
|
||||||
|
|
||||||
CACHE_FILE = Cache(Path(__file__).parent / "caches" / "streambtw.json", exp=86_400)
|
CACHE_FILE = Cache(Path(__file__).parent / "caches" / "streambtw.json", exp=86_400)
|
||||||
|
|
||||||
|
|
||||||
async def process_event(
|
async def process_event(
|
||||||
client: httpx.AsyncClient,
|
client: httpx.AsyncClient,
|
||||||
url: str,
|
url: str,
|
||||||
url_num: int,
|
url_num: int,
|
||||||
) -> str | None:
|
) -> str | None:
|
||||||
try:
|
try:
|
||||||
r = await client.get(url)
|
r = await client.get(url)
|
||||||
r.raise_for_status()
|
r.raise_for_status()
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
log.error(f'URL {url_num}) Failed to fetch "{url}"\n{e}')
|
log.error(f'URL {url_num}) Failed to fetch "{url}"\n{e}')
|
||||||
return
|
return
|
||||||
|
|
||||||
valid_m3u8 = re.compile(
|
valid_m3u8 = re.compile(
|
||||||
r'var\s+randomM3u8\s*=\s*[\'"]([^\'"]+)[\'"]',
|
r'var\s+(\w+)\s*=\s*["\']?(https?:\/\/[^"\'\s>]+\.m3u8)["\']?',
|
||||||
re.IGNORECASE,
|
re.IGNORECASE,
|
||||||
)
|
)
|
||||||
|
|
||||||
if match := valid_m3u8.search(r.text):
|
if match := valid_m3u8.search(r.text):
|
||||||
log.info(f"URL {url_num}) Captured M3U8")
|
log.info(f"URL {url_num}) Captured M3U8")
|
||||||
return match[1]
|
return match[2]
|
||||||
|
|
||||||
log.info(f"URL {url_num}) No M3U8 found")
|
log.info(f"URL {url_num}) No M3U8 found")
|
||||||
|
|
||||||
|
|
||||||
async def get_events(client: httpx.AsyncClient) -> list[dict[str, str]]:
|
async def get_events(client: httpx.AsyncClient) -> list[dict[str, str]]:
|
||||||
try:
|
try:
|
||||||
r = await client.get(BASE_URL)
|
r = await client.get(BASE_URL)
|
||||||
r.raise_for_status()
|
r.raise_for_status()
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
log.error(f'Failed to fetch "{BASE_URL}": {e}')
|
log.error(f'Failed to fetch "{BASE_URL}": {e}')
|
||||||
|
|
||||||
return []
|
return []
|
||||||
|
|
||||||
soup = HTMLParser(r.text)
|
soup = HTMLParser(r.text)
|
||||||
|
|
||||||
events = []
|
events = []
|
||||||
|
|
||||||
for card in soup.css("div.container div.card"):
|
for card in soup.css("div.container div.card"):
|
||||||
sport = card.css_first("h5.card-title").text(strip=True)
|
sport = card.css_first("h5.card-title").text(strip=True)
|
||||||
|
|
||||||
name = card.css_first("p.card-text").text(strip=True)
|
name = card.css_first("p.card-text").text(strip=True)
|
||||||
|
|
||||||
link = card.css_first("a.btn.btn-primary")
|
link = card.css_first("a.btn.btn-primary")
|
||||||
|
|
||||||
if not (href := link.attrs.get("href")):
|
if not (href := link.attrs.get("href")):
|
||||||
continue
|
continue
|
||||||
|
|
||||||
events.append(
|
events.append(
|
||||||
{
|
{
|
||||||
"sport": sport,
|
"sport": sport,
|
||||||
"event": name,
|
"event": name,
|
||||||
"link": urljoin(BASE_URL, href),
|
"link": urljoin(BASE_URL, href),
|
||||||
}
|
}
|
||||||
)
|
)
|
||||||
|
|
||||||
return events
|
return events
|
||||||
|
|
||||||
|
|
||||||
async def scrape(client: httpx.AsyncClient) -> None:
|
async def scrape(client: httpx.AsyncClient) -> None:
|
||||||
if cached := CACHE_FILE.load():
|
if cached := CACHE_FILE.load():
|
||||||
urls.update(cached)
|
urls.update(cached)
|
||||||
log.info(f"Loaded {len(urls)} event(s) from cache")
|
log.info(f"Loaded {len(urls)} event(s) from cache")
|
||||||
return
|
return
|
||||||
|
|
||||||
log.info(f'Scraping from "{BASE_URL}"')
|
log.info(f'Scraping from "{BASE_URL}"')
|
||||||
|
|
||||||
events = await get_events(client)
|
events = await get_events(client)
|
||||||
|
|
||||||
log.info(f"Processing {len(events)} new URL(s)")
|
log.info(f"Processing {len(events)} new URL(s)")
|
||||||
|
|
||||||
now = Time.now().timestamp()
|
now = Time.now().timestamp()
|
||||||
|
|
||||||
for i, ev in enumerate(events, start=1):
|
for i, ev in enumerate(events, start=1):
|
||||||
url = await network.safe_process(
|
url = await network.safe_process(
|
||||||
lambda: process_event(client, url=ev["link"], url_num=i),
|
lambda: process_event(client, url=ev["link"], url_num=i),
|
||||||
url_num=i,
|
url_num=i,
|
||||||
log=log,
|
log=log,
|
||||||
timeout=10,
|
timeout=10,
|
||||||
)
|
)
|
||||||
|
|
||||||
if url:
|
if url:
|
||||||
sport, event = ev["sport"], ev["event"]
|
sport, event = ev["sport"], ev["event"]
|
||||||
|
|
||||||
key = f"[{sport}] {event} (SBTW)"
|
key = f"[{sport}] {event} (SBTW)"
|
||||||
|
|
||||||
tvg_id, logo = leagues.info(sport)
|
tvg_id, logo = leagues.info(sport)
|
||||||
|
|
||||||
entry = {
|
entry = {
|
||||||
"url": url,
|
"url": url,
|
||||||
"logo": logo,
|
"logo": logo,
|
||||||
"base": BASE_URL,
|
"base": BASE_URL,
|
||||||
"timestamp": now,
|
"timestamp": now,
|
||||||
"id": tvg_id or "Live.Event.us",
|
"id": tvg_id or "Live.Event.us",
|
||||||
}
|
}
|
||||||
|
|
||||||
urls[key] = entry
|
urls[key] = entry
|
||||||
|
|
||||||
log.info(f"Collected {len(urls)} event(s)")
|
log.info(f"Collected {len(urls)} event(s)")
|
||||||
|
|
||||||
CACHE_FILE.write(urls)
|
CACHE_FILE.write(urls)
|
||||||
|
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue