mirror of
https://github.com/doms9/iptv.git
synced 2026-01-21 03:59:03 +01:00
e
remove watchfooty replace lotus with time4tv
This commit is contained in:
doms9
parent
934cd137bb
commit
00000d9c6d
5 changed files with 146 additions and 465 deletions
|
|
@ -6,7 +6,6 @@ from pathlib import Path
|
|||
from scrapers import (
|
||||
fawa,
|
||||
istreameast,
|
||||
lotus,
|
||||
pixel,
|
||||
ppv,
|
||||
roxie,
|
||||
|
|
@ -17,8 +16,8 @@ from scrapers import (
|
|||
streamhub,
|
||||
streamsgate,
|
||||
strmd,
|
||||
time4tv,
|
||||
tvpass,
|
||||
watchfooty,
|
||||
webcast,
|
||||
)
|
||||
from scrapers.utils import get_logger, network
|
||||
|
|
@ -50,7 +49,6 @@ async def main() -> None:
|
|||
tasks = [
|
||||
asyncio.create_task(fawa.scrape()),
|
||||
asyncio.create_task(istreameast.scrape()),
|
||||
asyncio.create_task(lotus.scrape()),
|
||||
asyncio.create_task(pixel.scrape()),
|
||||
asyncio.create_task(ppv.scrape()),
|
||||
asyncio.create_task(roxie.scrape()),
|
||||
|
|
@ -61,8 +59,8 @@ async def main() -> None:
|
|||
asyncio.create_task(streamhub.scrape()),
|
||||
asyncio.create_task(streamsgate.scrape()),
|
||||
asyncio.create_task(strmd.scrape()),
|
||||
asyncio.create_task(time4tv.scrape()),
|
||||
asyncio.create_task(tvpass.scrape()),
|
||||
# asyncio.create_task(watchfooty.scrape()),
|
||||
asyncio.create_task(webcast.scrape()),
|
||||
]
|
||||
|
||||
|
|
@ -71,7 +69,6 @@ async def main() -> None:
|
|||
additions = (
|
||||
fawa.urls
|
||||
| istreameast.urls
|
||||
| lotus.urls
|
||||
| pixel.urls
|
||||
| ppv.urls
|
||||
| roxie.urls
|
||||
|
|
@ -82,8 +79,8 @@ async def main() -> None:
|
|||
| streamfree.urls
|
||||
| streamhub.urls
|
||||
| streamsgate.urls
|
||||
| time4tv.urls
|
||||
| tvpass.urls
|
||||
| watchfooty.urls
|
||||
| webcast.urls
|
||||
)
|
||||
|
||||
|
|
|
|||
|
|
@ -1,138 +0,0 @@
|
|||
from functools import partial
|
||||
|
||||
from playwright.async_api import async_playwright
|
||||
|
||||
from .utils import Cache, Time, get_logger, leagues, network
|
||||
|
||||
log = get_logger(__name__)
|
||||
|
||||
urls: dict[str, dict[str, str | float]] = {}
|
||||
|
||||
TAG = "LOTUS"
|
||||
|
||||
CACHE_FILE = Cache(f"{TAG.lower()}.json", exp=5_400)
|
||||
|
||||
API_CACHE = Cache(f"{TAG.lower()}-api.json", exp=28_800)
|
||||
|
||||
BASE_URL = "https://lotusgamehd.xyz/api-event.php"
|
||||
|
||||
|
||||
def fix_league(s: str) -> str:
|
||||
return " ".join(x.capitalize() for x in s.split()) if len(s) > 5 else s.upper()
|
||||
|
||||
|
||||
async def get_events(cached_keys: list[str]) -> list[dict[str, str]]:
|
||||
now = Time.clean(Time.now())
|
||||
|
||||
if not (api_data := API_CACHE.load(per_entry=False)):
|
||||
api_data = {}
|
||||
|
||||
if r := await network.request(BASE_URL, log=log):
|
||||
api_data: dict = r.json()
|
||||
|
||||
api_data["timestamp"] = now.timestamp()
|
||||
|
||||
API_CACHE.write(api_data)
|
||||
|
||||
events = []
|
||||
|
||||
for info in api_data.get("days", []):
|
||||
event_dt = Time.from_str(info["day_et"], timezone="ET")
|
||||
|
||||
if now.date() != event_dt.date():
|
||||
continue
|
||||
|
||||
for event in info["items"]:
|
||||
if (event_league := event["league"]) == "channel tv":
|
||||
continue
|
||||
|
||||
sport = fix_league(event_league)
|
||||
|
||||
event_name = event["title"]
|
||||
|
||||
if f"[{sport}] {event_name} ({TAG})" in cached_keys:
|
||||
continue
|
||||
|
||||
event_streams: list[dict[str, str]] = event["streams"]
|
||||
|
||||
if not (event_link := event_streams[0].get("link")):
|
||||
continue
|
||||
|
||||
events.append(
|
||||
{
|
||||
"sport": sport,
|
||||
"event": event_name,
|
||||
"link": event_link,
|
||||
"timestamp": now.timestamp(),
|
||||
}
|
||||
)
|
||||
|
||||
return events
|
||||
|
||||
|
||||
async def scrape() -> None:
|
||||
cached_urls = CACHE_FILE.load()
|
||||
|
||||
cached_count = len(cached_urls)
|
||||
|
||||
urls.update(cached_urls)
|
||||
|
||||
log.info(f"Loaded {cached_count} event(s) from cache")
|
||||
|
||||
log.info(f'Scraping from "{BASE_URL}"')
|
||||
|
||||
events = await get_events(cached_urls.keys())
|
||||
|
||||
log.info(f"Processing {len(events)} new URL(s)")
|
||||
|
||||
if events:
|
||||
async with async_playwright() as p:
|
||||
browser, context = await network.browser(p)
|
||||
|
||||
for i, ev in enumerate(events, start=1):
|
||||
handler = partial(
|
||||
network.process_event,
|
||||
url=ev["link"],
|
||||
url_num=i,
|
||||
context=context,
|
||||
log=log,
|
||||
)
|
||||
|
||||
url = await network.safe_process(
|
||||
handler,
|
||||
url_num=i,
|
||||
log=log,
|
||||
)
|
||||
|
||||
if url:
|
||||
sport, event, link, ts = (
|
||||
ev["sport"],
|
||||
ev["event"],
|
||||
ev["link"],
|
||||
ev["timestamp"],
|
||||
)
|
||||
|
||||
tvg_id, logo = leagues.get_tvg_info(sport, event)
|
||||
|
||||
key = f"[{sport}] {event} ({TAG})"
|
||||
|
||||
entry = {
|
||||
"url": url,
|
||||
"logo": logo,
|
||||
"base": "https://vividmosaica.com/",
|
||||
"timestamp": ts,
|
||||
"id": tvg_id or "Live.Event.us",
|
||||
"link": link,
|
||||
}
|
||||
|
||||
urls[key] = cached_urls[key] = entry
|
||||
|
||||
await browser.close()
|
||||
|
||||
if new_count := len(cached_urls) - cached_count:
|
||||
log.info(f"Collected and cached {new_count} new event(s)")
|
||||
|
||||
else:
|
||||
log.info("No new events found")
|
||||
|
||||
CACHE_FILE.write(cached_urls)
|
||||
138
M3U8/scrapers/time4tv.py
Normal file
138
M3U8/scrapers/time4tv.py
Normal file
|
|
@ -0,0 +1,138 @@
|
|||
import re
|
||||
from functools import partial
|
||||
from urllib.parse import urljoin
|
||||
|
||||
from playwright.async_api import async_playwright
|
||||
from selectolax.parser import HTMLParser
|
||||
|
||||
from .utils import Cache, Time, get_logger, leagues, network
|
||||
|
||||
log = get_logger(__name__)
|
||||
|
||||
urls: dict[str, dict[str, str | float]] = {}
|
||||
|
||||
TAG = "TIME4TV"
|
||||
|
||||
CACHE_FILE = Cache(f"{TAG.lower()}.json", exp=5_400)
|
||||
|
||||
BASE_URL = "https://time4tv.icu/"
|
||||
|
||||
|
||||
def fix_league(s: str) -> str:
|
||||
return " ".join(x.capitalize() for x in s.split()) if len(s) > 5 else s.upper()
|
||||
|
||||
|
||||
async def get_events(cached_keys: list[str], now: Time) -> dict[dict[str, str]]:
|
||||
events = []
|
||||
|
||||
if not (html_data := await network.request(BASE_URL, log=log)):
|
||||
return events
|
||||
|
||||
pattern = re.compile(r"openPlayerPopup\(\s*(\d+)\s*\)", re.IGNORECASE)
|
||||
|
||||
soup = HTMLParser(html_data.content)
|
||||
|
||||
for row in soup.css(".wrap .row"):
|
||||
if not (date := row.css_first(".date")):
|
||||
continue
|
||||
|
||||
event_date = date.text(strip=True).replace("\t", " ")
|
||||
|
||||
try:
|
||||
event_dt = Time.from_str(event_date, fmt="%m/%d/%Y %I:%M %p")
|
||||
except ValueError:
|
||||
continue
|
||||
|
||||
if event_dt.date() != now.date():
|
||||
continue
|
||||
|
||||
league = row.css_first(".league")
|
||||
|
||||
title = row.css_first(".title")
|
||||
|
||||
hds_a = row.css_first(".hds a")
|
||||
|
||||
if not (league and title and hds_a):
|
||||
continue
|
||||
|
||||
sport, event = fix_league(league.text(strip=True)), title.text(strip=True)
|
||||
|
||||
if f"[{sport}] {event} ({TAG})" in cached_keys:
|
||||
continue
|
||||
|
||||
onclick = hds_a.attributes.get("onclick", "")
|
||||
|
||||
if not (match := pattern.search(onclick)):
|
||||
continue
|
||||
|
||||
events.append(
|
||||
{
|
||||
"sport": sport,
|
||||
"event": event,
|
||||
"link": urljoin(BASE_URL, f"player1.php?{match[1]}"),
|
||||
}
|
||||
)
|
||||
|
||||
return events
|
||||
|
||||
|
||||
async def scrape() -> None:
|
||||
cached_urls = CACHE_FILE.load()
|
||||
|
||||
cached_count = len(cached_urls)
|
||||
|
||||
urls.update(cached_urls)
|
||||
|
||||
log.info(f"Loaded {cached_count} event(s) from cache")
|
||||
|
||||
log.info(f'Scraping from "{BASE_URL}"')
|
||||
|
||||
now = Time.clean(Time.now())
|
||||
|
||||
events = await get_events(cached_urls.keys(), now)
|
||||
|
||||
log.info(f"Processing {len(events)} new URL(s)")
|
||||
|
||||
async with async_playwright() as p:
|
||||
browser, context = await network.browser(p)
|
||||
|
||||
for i, ev in enumerate(events, start=1):
|
||||
handler = partial(
|
||||
network.process_event,
|
||||
url=ev["link"],
|
||||
url_num=i,
|
||||
context=context,
|
||||
log=log,
|
||||
)
|
||||
|
||||
url = await network.safe_process(
|
||||
handler,
|
||||
url_num=i,
|
||||
log=log,
|
||||
)
|
||||
|
||||
if url:
|
||||
sport, event = ev["sport"], ev["event"]
|
||||
|
||||
tvg_id, logo = leagues.info(sport)
|
||||
|
||||
key = f"[{sport}] {event} ({TAG})"
|
||||
|
||||
entry = {
|
||||
"url": url,
|
||||
"logo": logo,
|
||||
"base": "https://vividmosaica.com/",
|
||||
"timestamp": now.timestamp(),
|
||||
"id": tvg_id or "Live.Event.us",
|
||||
}
|
||||
|
||||
urls[key] = cached_urls[key] = entry
|
||||
|
||||
await browser.close()
|
||||
|
||||
if new_count := len(cached_urls) - cached_count:
|
||||
log.info(f"Collected and cached {new_count} new event(s)")
|
||||
else:
|
||||
log.info("No new events found")
|
||||
|
||||
CACHE_FILE.write(cached_urls)
|
||||
|
|
@ -89,23 +89,22 @@ class Time(datetime):
|
|||
|
||||
else:
|
||||
formats = [
|
||||
"%B %d, %Y %H:%M",
|
||||
"%B %d, %Y %I:%M %p",
|
||||
"%B %d, %Y %I:%M:%S %p",
|
||||
"%m/%d/%Y %I:%M %p",
|
||||
"%B %d, %Y %H:%M",
|
||||
"%B %d, %Y %H:%M:%S",
|
||||
"%Y-%m-%d",
|
||||
"%Y-%m-%d %H:%M",
|
||||
"%Y-%m-%d %H:%M:%S",
|
||||
"%Y-%m-%d %H:%M %p",
|
||||
"%Y-%m-%d %I:%M %p",
|
||||
"%Y-%m-%d %H:%M %p",
|
||||
"%Y/%m/%d %H:%M",
|
||||
"%Y/%m/%d %H:%M:%S",
|
||||
"%m/%d/%Y %H:%M",
|
||||
"%m/%d/%Y %H:%M:%S",
|
||||
"%Y-%m-%dT%H:%M:%S",
|
||||
"%Y/%m/%dT%H:%M:%S.%fZ",
|
||||
"%Y-%m-%dT%H:%M:%S.%fZ",
|
||||
"%m/%d/%Y %H:%M",
|
||||
"%m/%d/%Y %I:%M %p",
|
||||
"%m/%d/%Y %H:%M:%S",
|
||||
"%a, %d %b %Y %H:%M:%S %z",
|
||||
]
|
||||
|
||||
|
|
|
|||
|
|
@ -1,315 +0,0 @@
|
|||
import asyncio
|
||||
import re
|
||||
from functools import partial
|
||||
from itertools import chain
|
||||
from typing import Any
|
||||
from urllib.parse import urljoin
|
||||
|
||||
from playwright.async_api import BrowserContext, async_playwright
|
||||
|
||||
from .utils import Cache, Time, get_logger, leagues, network
|
||||
|
||||
log = get_logger(__name__)
|
||||
|
||||
urls: dict[str, dict[str, str | float]] = {}
|
||||
|
||||
TAG = "WATCHFTY"
|
||||
|
||||
CACHE_FILE = Cache(f"{TAG.lower()}.json", exp=10_800)
|
||||
|
||||
API_FILE = Cache(f"{TAG.lower()}-api.json", exp=19_800)
|
||||
|
||||
API_URL = "https://api.watchfooty.st"
|
||||
|
||||
BASE_MIRRORS = [
|
||||
"https://www.watchfooty.top",
|
||||
"https://www.watchfooty.st",
|
||||
"https://www.watchfooty.su",
|
||||
]
|
||||
|
||||
VALID_SPORTS = [
|
||||
"american-football",
|
||||
# "australian-football",
|
||||
# "baseball",
|
||||
"basketball",
|
||||
# "cricket",
|
||||
# "darts",
|
||||
"fighting",
|
||||
"football",
|
||||
"golf",
|
||||
"hockey",
|
||||
"racing",
|
||||
# "rugby",
|
||||
# "tennis",
|
||||
# "volleyball",
|
||||
]
|
||||
|
||||
|
||||
async def refresh_api_cache(now: Time) -> list[dict[str, Any]]:
|
||||
log.info("Refreshing API cache")
|
||||
|
||||
tasks = [
|
||||
network.request(
|
||||
urljoin(API_URL, "api/v1/matches/all"),
|
||||
log=log,
|
||||
params={"date": d.date()},
|
||||
)
|
||||
for d in [now, now.delta(days=1)]
|
||||
]
|
||||
|
||||
results = await asyncio.gather(*tasks)
|
||||
|
||||
if not (data := [*chain.from_iterable(r.json() for r in results if r)]):
|
||||
return []
|
||||
|
||||
for ev in data:
|
||||
ev["ts"] = ev.pop("timestamp")
|
||||
|
||||
data[-1]["timestamp"] = now.timestamp()
|
||||
|
||||
return data
|
||||
|
||||
|
||||
async def process_event(
|
||||
url: str,
|
||||
url_num: int,
|
||||
context: BrowserContext,
|
||||
) -> str | None:
|
||||
|
||||
pattern = re.compile(r"\((\d+)\)")
|
||||
|
||||
page = await context.new_page()
|
||||
|
||||
captured: list[str] = []
|
||||
|
||||
got_one = asyncio.Event()
|
||||
|
||||
handler = partial(
|
||||
network.capture_req,
|
||||
captured=captured,
|
||||
got_one=got_one,
|
||||
)
|
||||
|
||||
page.on("request", handler)
|
||||
|
||||
try:
|
||||
await page.goto(
|
||||
url,
|
||||
wait_until="domcontentloaded",
|
||||
timeout=15_000,
|
||||
)
|
||||
|
||||
await page.wait_for_timeout(2_000)
|
||||
|
||||
try:
|
||||
header = await page.wait_for_selector(
|
||||
"text=/Stream Links/i",
|
||||
timeout=5_000,
|
||||
)
|
||||
|
||||
text = await header.inner_text()
|
||||
except TimeoutError:
|
||||
log.warning(f"URL {url_num}) Can't find stream links header.")
|
||||
|
||||
return
|
||||
|
||||
if not (match := pattern.search(text)) or int(match[1]) == 0:
|
||||
log.warning(f"URL {url_num}) No available stream links.")
|
||||
|
||||
return
|
||||
|
||||
try:
|
||||
first_available = await page.wait_for_selector(
|
||||
'a[href*="/stream/"]',
|
||||
timeout=3_000,
|
||||
)
|
||||
except TimeoutError:
|
||||
log.warning(f"URL {url_num}) No available stream links.")
|
||||
|
||||
return
|
||||
|
||||
if not (href := await first_available.get_attribute("href")):
|
||||
log.warning(f"URL {url_num}) No available stream links.")
|
||||
|
||||
return
|
||||
|
||||
await page.goto(
|
||||
href,
|
||||
wait_until="domcontentloaded",
|
||||
timeout=5_000,
|
||||
)
|
||||
|
||||
wait_task = asyncio.create_task(got_one.wait())
|
||||
|
||||
try:
|
||||
await asyncio.wait_for(wait_task, timeout=6)
|
||||
except asyncio.TimeoutError:
|
||||
log.warning(f"URL {url_num}) Timed out waiting for M3U8.")
|
||||
|
||||
return
|
||||
|
||||
finally:
|
||||
if not wait_task.done():
|
||||
wait_task.cancel()
|
||||
|
||||
try:
|
||||
await wait_task
|
||||
except asyncio.CancelledError:
|
||||
pass
|
||||
|
||||
if captured:
|
||||
log.info(f"URL {url_num}) Captured M3U8")
|
||||
|
||||
return captured[-1]
|
||||
|
||||
log.warning(f"URL {url_num}) No M3U8 captured after waiting.")
|
||||
|
||||
return
|
||||
|
||||
except Exception as e:
|
||||
log.warning(f"URL {url_num}) Exception while processing: {e}")
|
||||
|
||||
return
|
||||
|
||||
finally:
|
||||
page.remove_listener("request", handler)
|
||||
|
||||
await page.close()
|
||||
|
||||
|
||||
async def get_events(base_url: str, cached_keys: list[str]) -> list[dict[str, str]]:
|
||||
now = Time.clean(Time.now())
|
||||
|
||||
if not (api_data := API_FILE.load(per_entry=False, index=-1)):
|
||||
api_data = await refresh_api_cache(now)
|
||||
|
||||
API_FILE.write(api_data)
|
||||
|
||||
events = []
|
||||
|
||||
pattern = re.compile(r"\-+|\(")
|
||||
|
||||
start_dt = now.delta(minutes=-30)
|
||||
end_dt = now.delta(minutes=5)
|
||||
|
||||
for event in api_data:
|
||||
match_id = event.get("matchId")
|
||||
|
||||
name = event.get("title")
|
||||
|
||||
league = event.get("league")
|
||||
|
||||
if not (match_id and name and league):
|
||||
continue
|
||||
|
||||
if event["sport"] not in VALID_SPORTS:
|
||||
continue
|
||||
|
||||
sport = pattern.split(league, 1)[0].strip()
|
||||
|
||||
if f"[{sport}] {name} ({TAG})" in cached_keys:
|
||||
continue
|
||||
|
||||
if not (ts := event.get("ts")):
|
||||
continue
|
||||
|
||||
start_ts = float(f"{ts}"[:-3])
|
||||
|
||||
event_dt = Time.from_ts(start_ts)
|
||||
|
||||
if not start_dt <= event_dt <= end_dt:
|
||||
continue
|
||||
|
||||
logo = urljoin(API_URL, poster) if (poster := event.get("poster")) else None
|
||||
|
||||
events.append(
|
||||
{
|
||||
"sport": sport,
|
||||
"event": name,
|
||||
"link": urljoin(base_url, f"stream/{match_id}"),
|
||||
"logo": logo,
|
||||
"timestamp": event_dt.timestamp(),
|
||||
}
|
||||
)
|
||||
|
||||
return events
|
||||
|
||||
|
||||
async def scrape() -> None:
|
||||
cached_urls = CACHE_FILE.load()
|
||||
|
||||
valid_urls = {k: v for k, v in cached_urls.items() if v["url"]}
|
||||
|
||||
valid_count = cached_count = len(valid_urls)
|
||||
|
||||
urls.update(valid_urls)
|
||||
|
||||
log.info(f"Loaded {cached_count} event(s) from cache")
|
||||
|
||||
if not (base_url := await network.get_base(BASE_MIRRORS)):
|
||||
log.warning("No working Watch Footy mirrors")
|
||||
|
||||
CACHE_FILE.write(cached_urls)
|
||||
|
||||
return
|
||||
|
||||
log.info(f'Scraping from "{base_url}"')
|
||||
|
||||
events = await get_events(base_url, cached_urls.keys())
|
||||
|
||||
log.info(f"Processing {len(events)} new URL(s)")
|
||||
|
||||
if events:
|
||||
async with async_playwright() as p:
|
||||
browser, context = await network.browser(p, browser="external")
|
||||
|
||||
for i, ev in enumerate(events, start=1):
|
||||
handler = partial(
|
||||
process_event,
|
||||
url=ev["link"],
|
||||
url_num=i,
|
||||
context=context,
|
||||
)
|
||||
|
||||
url = await network.safe_process(
|
||||
handler,
|
||||
url_num=i,
|
||||
log=log,
|
||||
)
|
||||
|
||||
sport, event, logo, ts, link = (
|
||||
ev["sport"],
|
||||
ev["event"],
|
||||
ev["logo"],
|
||||
ev["timestamp"],
|
||||
ev["link"],
|
||||
)
|
||||
|
||||
key = f"[{sport}] {event} ({TAG})"
|
||||
|
||||
tvg_id, pic = leagues.get_tvg_info(sport, event)
|
||||
|
||||
entry = {
|
||||
"url": url,
|
||||
"logo": logo or pic,
|
||||
"base": base_url,
|
||||
"timestamp": ts,
|
||||
"id": tvg_id or "Live.Event.us",
|
||||
"link": link,
|
||||
}
|
||||
|
||||
cached_urls[key] = entry
|
||||
|
||||
if url:
|
||||
valid_count += 1
|
||||
urls[key] = entry
|
||||
|
||||
await browser.close()
|
||||
|
||||
if new_count := valid_count - cached_count:
|
||||
log.info(f"Collected and cached {new_count} new event(s)")
|
||||
|
||||
else:
|
||||
log.info("No new events found")
|
||||
|
||||
CACHE_FILE.write(cached_urls)
|
||||
Loading…
Add table
Add a link
Reference in a new issue