diff --git a/M3U8/fetch.py b/M3U8/fetch.py index 63fe4572..acbe3da6 100644 --- a/M3U8/fetch.py +++ b/M3U8/fetch.py @@ -11,12 +11,13 @@ from scrapers import ( fsports, istreameast, mainportal, + pelotalibre, roxie, shark, streambiz, streamcenter, streamsgate, - streamtpnew, + streamtp, totalsportek, watchfooty, webcast, @@ -67,10 +68,11 @@ async def main() -> None: asyncio.create_task(fawa.scrape()), asyncio.create_task(istreameast.scrape()), asyncio.create_task(mainportal.scrape()), + asyncio.create_task(pelotalibre.scrape()), asyncio.create_task(shark.scrape()), asyncio.create_task(streamcenter.scrape()), asyncio.create_task(streamsgate.scrape()), - asyncio.create_task(streamtpnew.scrape()), + asyncio.create_task(streamtp.scrape()), asyncio.create_task(totalsportek.scrape()), asyncio.create_task(webcast.scrape()), asyncio.create_task(xyzstream.scrape()), @@ -96,12 +98,13 @@ async def main() -> None: | fsports.urls | istreameast.urls | mainportal.urls + | pelotalibre.urls | roxie.urls | shark.urls | streambiz.urls | streamcenter.urls | streamsgate.urls - | streamtpnew.urls + | streamtp.urls | totalsportek.urls | watchfooty.urls | webcast.urls diff --git a/M3U8/scrapers/pelotalibre.py b/M3U8/scrapers/pelotalibre.py new file mode 100644 index 00000000..58a03955 --- /dev/null +++ b/M3U8/scrapers/pelotalibre.py @@ -0,0 +1,117 @@ +import re +from functools import partial + +from .utils import Cache, Time, get_logger, leagues, network + +log = get_logger(__name__) + +urls: dict[str, dict[str, str | float]] = {} + +TAG = "PLIBRE" + +CACHE_FILE = Cache(TAG, exp=19_800) + +API_URL = "https://la18hd.com/eventos/json/agenda123.json" + + +async def process_event(url: str, url_num: int) -> str | None: + if not (html_data := await network.request(url, log=log)): + log.warning(f"URL {url_num}) Failed to load url.") + + return + + valid_m3u8 = re.compile(r'var\s+playbackURL\s+=\s+"([^"]*)"', re.I) + + 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 get_events() -> list[dict[str, str]]: + events = [] + + if not (api_req := await network.request(API_URL, log=log)): + return events + + elif not (api_data := api_req.json()): + return events + + for event in api_data: + if not (name := event.get("title")) or not (link := event.get("link")): + continue + + if (sport := event.get("category")) and sport == "Other": + sport = "Live Event" + + if all(existing_event["event"] != name for existing_event in events): + events.append( + { + "sport": sport, + "event": name, + "link": link, + } + ) + + return events + + +async def scrape() -> None: + if cached_urls := CACHE_FILE.load(): + urls.update({k: v for k, v in cached_urls.items() if v["url"]}) + + log.info(f"Loaded {len(urls)} event(s) from cache") + + return + + log.info('Scraping from "https://la18hd.com"') + + if events := await get_events(): + log.info(f"Processing {len(events)} URL(s)") + + now = Time.clean(Time.now()) + + for i, ev in enumerate(events, start=1): + handler = partial( + process_event, + url=(link := ev["link"]), + url_num=i, + ) + + url = await network.safe_process( + handler, + url_num=i, + semaphore=network.HTTP_S, + log=log, + ) + + sport, event = ev["sport"], ev["event"] + + key = f"[{sport}] {event} ({TAG})" + + tvg_id, logo = leagues.get_tvg_info(sport, event) + + entry = { + "url": url, + "logo": logo, + "base": link, + "timestamp": now.timestamp(), + "id": tvg_id or "Live.Event.us", + "link": link, + } + + cached_urls[key] = entry + + if url: + urls[key] = entry + + log.info(f"Collected and cached {len(urls)} event(s)") + + else: + log.info("No events found") + + CACHE_FILE.write(cached_urls) diff --git a/M3U8/scrapers/streamtpnew.py b/M3U8/scrapers/streamtp.py similarity index 86% rename from M3U8/scrapers/streamtpnew.py rename to M3U8/scrapers/streamtp.py index e31c4151..2a59d8c0 100644 --- a/M3U8/scrapers/streamtpnew.py +++ b/M3U8/scrapers/streamtp.py @@ -1,138 +1,135 @@ -import ast -import base64 -import re -from functools import partial - -from .utils import Cache, Time, get_logger, leagues, network - -log = get_logger(__name__) - -urls: dict[str, dict[str, str | float]] = {} - -TAG = "STP" - -CACHE_FILE = Cache(TAG, exp=28_800) - -API_URL = "https://streamtpnew.com/eventos.json" - - -async def process_event(url: str, url_num: int) -> str | None: - if not (event_data := await network.request(url, log=log)): - log.warning(f"URL {url_num}) Failed to load url.") - return - - digit_func_ptrn = re.compile(r"{return\s+(\d*);}", re.I) - - if not (digit_list := digit_func_ptrn.findall(event_data.text)): - log.warning(f"URL {url_num}) Unable to decode url.") - return - - embed_list_ptrn = re.compile(r"\w*=\[\[(.*)\]\];") - - if not (embed_list := embed_list_ptrn.search(event_data.text)): - log.warning(f"URL {url_num}) Unable to decode url.") - return - - embed_list_str = embed_list[0].split("=", 1)[-1].strip(";") - - embed_list: list[tuple[int, str]] = ast.literal_eval(embed_list_str) - - m3u8 = "".join( - chr( - int("".join(c for c in base64.b64decode(v).decode("utf-8") if c.isdigit())) - - sum(map(int, digit_list)) - ) - for _, v in sorted(embed_list, key=lambda i: i[0]) - ) - - log.info(f"URL {url_num}) Captured M3U8") - - return m3u8.split("ip=")[0] - - -async def get_events() -> list[dict[str, str]]: - events = [] - - if not (api_req := await network.request(API_URL, log=log)): - return events - - elif not (api_data := api_req.json()): - return events - - for event in api_data: - name = event.get("title") - - link = event.get("link") - - if not (name and link): - continue - - if (sport := event.get("category")) and sport == "Other": - sport = "Live Event" - - events.append( - { - "sport": sport, - "event": name, - "link": link, - } - ) - - return events - - -async def scrape() -> None: - if cached_urls := CACHE_FILE.load(): - urls.update({k: v for k, v in cached_urls.items() if v["url"]}) - - log.info(f"Loaded {len(urls)} event(s) from cache") - - return - - log.info('Scraping from "https://streamtpnew.com"') - - if events := await get_events(): - log.info(f"Processing {len(events)} URL(s)") - - now = Time.clean(Time.now()) - - for i, ev in enumerate(events, start=1): - handler = partial( - process_event, - url=(link := ev["link"]), - url_num=i, - ) - - url = await network.safe_process( - handler, - url_num=i, - semaphore=network.HTTP_S, - log=log, - ) - - sport, event = ev["sport"], ev["event"] - - key = f"[{sport}] {event} ({TAG})" - - tvg_id, logo = leagues.get_tvg_info(sport, event) - - entry = { - "url": url, - "logo": logo, - "base": link, - "timestamp": now.timestamp(), - "id": tvg_id or "Live.Event.us", - "link": link, - } - - cached_urls[key] = entry - - if url: - urls[key] = entry - - log.info(f"Collected and cached {len(urls)} event(s)") - - else: - log.info("No events found") - - CACHE_FILE.write(cached_urls) +import ast +import base64 +import re +from functools import partial + +from .utils import Cache, Time, get_logger, leagues, network + +log = get_logger(__name__) + +urls: dict[str, dict[str, str | float]] = {} + +TAG = "STP" + +CACHE_FILE = Cache(TAG, exp=19_800) + +API_URL = "https://streamtp-x-y-z.ws/eventos.json" + + +async def process_event(url: str, url_num: int) -> str | None: + if not (event_data := await network.request(url, log=log)): + log.warning(f"URL {url_num}) Failed to load url.") + return + + digit_func_ptrn = re.compile(r"{return\s+(\d*);}", re.I) + + if not (digit_list := digit_func_ptrn.findall(event_data.text)): + log.warning(f"URL {url_num}) Unable to decode url.") + return + + embed_list_ptrn = re.compile(r"\w*=\[\[(.*)\]\];") + + if not (embed_list := embed_list_ptrn.search(event_data.text)): + log.warning(f"URL {url_num}) Unable to decode url.") + return + + embed_list_str = embed_list[0].split("=", 1)[-1].strip(";") + + embed_list: list[tuple[int, str]] = ast.literal_eval(embed_list_str) + + m3u8 = "".join( + chr( + int("".join(c for c in base64.b64decode(v).decode("utf-8") if c.isdigit())) + - sum(map(int, digit_list)) + ) + for _, v in sorted(embed_list, key=lambda i: i[0]) + ) + + log.info(f"URL {url_num}) Captured M3U8") + + return m3u8.split("ip=")[0] + + +async def get_events() -> list[dict[str, str]]: + events = [] + + if not (api_req := await network.request(API_URL, log=log)): + return events + + elif not (api_data := api_req.json()): + return events + + for event in api_data: + if not (name := event.get("title")) or not (link := event.get("link")): + continue + + if (sport := event.get("category")) and sport == "Other": + sport = "Live Event" + + if all(existing_event["event"] != name for existing_event in events): + events.append( + { + "sport": sport, + "event": name, + "link": link, + } + ) + + return events + + +async def scrape() -> None: + if cached_urls := CACHE_FILE.load(): + urls.update({k: v for k, v in cached_urls.items() if v["url"]}) + + log.info(f"Loaded {len(urls)} event(s) from cache") + + return + + log.info('Scraping from "https://streamtpnew.com"') + + if events := await get_events(): + log.info(f"Processing {len(events)} URL(s)") + + now = Time.clean(Time.now()) + + for i, ev in enumerate(events, start=1): + handler = partial( + process_event, + url=(link := ev["link"]), + url_num=i, + ) + + url = await network.safe_process( + handler, + url_num=i, + semaphore=network.HTTP_S, + log=log, + ) + + sport, event = ev["sport"], ev["event"] + + key = f"[{sport}] {event} ({TAG})" + + tvg_id, logo = leagues.get_tvg_info(sport, event) + + entry = { + "url": url, + "logo": logo, + "base": link, + "timestamp": now.timestamp(), + "id": tvg_id or "Live.Event.us", + "link": link, + } + + cached_urls[key] = entry + + if url: + urls[key] = entry + + log.info(f"Collected and cached {len(urls)} event(s)") + + else: + log.info("No events found") + + CACHE_FILE.write(cached_urls)