Upload vtv_scraper.py

vtv_scraper.py

@@ -1,130 +1,36 @@
-"""
-VTV Channels Scraper
-Fetches stream URLs from hd.xemtv.net PHP endpoints for VTV1-VTV10 + VTV Cần Thơ
-import requests, re, time, threading
-
-UA = {
-    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36",
-    "Accept-Language": "vi-VN,vi;q=0.9",
-    "Referer": "https://hd.xemtv.net/",
-}
-
-XEMTV_PHP_ENDPOINTS = {
-    "vtv1":  "https://hd.xemtv.net/kenh/vtv1.php",
-    "vtv2":  "https://hd.xemtv.net/kenh/vtv2.php",
-    "vtv3":  "https://hd.xemtv.net/kenh/vtv3.php",
-    "vtv4":  "https://hd.xemtv.net/kenh/vtv4.php",
-    "vtv5":  "https://hd.xemtv.net/kenh/vtv5.php",
-    "vtv6":  "https://hd.xemtv.net/kenh/vtv6.php",
-    "vtv7":  "https://hd.xemtv.net/kenh/vtv7.php",
-    "vtv8":  "https://hd.xemtv.net/kenh/vtv8.php",
-    "vtv9":  "https://hd.xemtv.net/kenh/vtv9.php",
-    "vtv10": "https://hd.xemtv.net/kenh/vtv10.php",
-}
-
-CHANNEL_NAMES = {
-    "vtv1": "VTV1", "vtv2": "VTV2", "vtv3": "VTV3", "vtv4": "VTV4",
-    "vtv5": "VTV5", "vtv6": "VTV6", "vtv7": "VTV7", "vtv8": "VTV8",
-    "vtv9": "VTV9", "vtv10": "VTV Cần Thơ",
-}
-
-CDN_FALLBACK = {
-    "vtv1":  "https://vtvgolive-failover.vtvdigital.vn/vtvgo/vtv1-manifest.m3u8",
-    "vtv2":  "https://vtvgolive-failover.vtvdigital.vn/vtvgo/vtv2-manifest.m3u8",
-    "vtv3":  "https://vtvgolive-failover.vtvdigital.vn/vtvgo/vtv3-manifest.m3u8",
-    "vtv4":  "https://vtvgolive-failover.vtvdigital.vn/vtvgo/vtv4-manifest.m3u8",
-    "vtv5":  "https://vtvgolive-failover.vtvdigital.vn/vtvgo/vtv5-manifest.m3u8",
-    "vtv6":  "https://vtvgolive-failover.vtvdigital.vn/vtvgo/vtv6-manifest.m3u8",
-    "vtv7":  "https://vtvgolive-failover.vtvdigital.vn/vtvgo/vtv7-manifest.m3u8",
-    "vtv8":  "https://vtvgolive-failover.vtvdigital.vn/vtvgo/vtv8-manifest.m3u8",
-    "vtv9":  "https://vtvgolive-failover.vtvdigital.vn/vtvgo/vtv9-manifest.m3u8",
-    "vtv10": "https://vtvgolive-failover.vtvdigital.vn/vtvgo/vtv10-manifest.m3u8",
-    "_fpt_vtv1":  "https://live.fptplay53.net/fnxch2/vtv1hd_abr.smil/chunklist.m3u8",
-    "_fpt_vtv2":  "https://live.fptplay53.net/fnxch2/vtv2hd_abr.smil/chunklist.m3u8",
-    "_fpt_vtv3":  "https://live.fptplay53.net/fnxch2/vtv3hd_abr.smil/chunklist.m3u8",
-    "_fpt_vtv4":  "https://live.fptplay53.net/fnxch2/vtv4hd_abr.smil/chunklist.m3u8",
-    "_fpt_vtv5":  "https://live-a.fptplay53.net/live/media/VTV5HD/live_hls_avc/index.m3u8",
-    "_fpt_vtv6":  "https://live.fptplay53.net/fnxch2/vtv6hd_abr.smil/chunklist.m3u8",
-    "_fpt_vtv7":  "https://live.fptplay53.net/fnxhd1/vtv7hd_vhls.smil/chunklist_b5000000.m3u8",
-    "_fpt_vtv8":  "https://live.fptplay53.net/epzhd1/vtv8hd_vhls.smil/chunklist.m3u8",
-    "_fpt_vtv9":  "https://live.fptplay53.net/fnxhd1/vtv9hd_vhls.smil/chunklist.m3u8",
-    "_fpt_vtv10": "https://live.fptplay53.net/fnxch2/vtvcantho_abr.smil/chunklist.m3u8",
-}
-
-_vtv_cache = {}
-_vtv_lock = threading.Lock()
-_CACHE_TTL = 180
-
-def _cached(key):
-    with _vtv_lock:
-        if key in _vtv_cache and time.time() - _vtv_cache[key]['t'] < _CACHE_TTL:
-            return _vtv_cache[key]['d']
-    return None
-
-def _set_cache(key, data):
-    with _vtv_lock:
-        _vtv_cache[key] = {'t': time.time(), 'd': data}
-
-def extract_m3u8_from_html(html):
-    if not html:
-        return None
-    m = re.search(r"file\s*:\s*['\"]([^'\"]*\.m3u8[^'\"]*)['\"]", html, re.IGNORECASE)
-    if m:
-        url = m.group(1).strip()
-        if len(url) > 20:
-            return url
-    m = re.search(r"(https?://[^\s\"'<>\\]+\.m3u8[^\s\"'<>\\]*)", html, re.IGNORECASE)
-    if m:
-        url = m.group(1).strip()
-        if len(url) > 20:
-            return url
-    return None
-
-def fetch_vtv_stream(channel_id):
-    channel_id = channel_id.lower().strip()
-    name_map = {
-        'vtvct': 'vtv10', 'vtv-can-tho': 'vtv10', 'vtv can tho': 'vtv10',
-        'vtv_can_tho': 'vtv10', 'cantho': 'vtv10', 'cần thơ': 'vtv10',
-        'vietnam_vtv1': 'vtv1', 'vietnam_vtv2': 'vtv2', 'vietnam_vtv3': 'vtv3',
-        'vietnam_vtv4': 'vtv4', 'vietnam_vtv5': 'vtv5', 'vietnam_vtv6': 'vtv6',
-        'vietnam_vtv7': 'vtv7', 'vietnam_vtv8': 'vtv8', 'vietnam_vtv9': 'vtv9',
-    }
-    channel_id = name_map.get(channel_id, channel_id)
-    cached = _cached(channel_id)
-    if cached:
-        return cached
-    vtvgourl = CDN_FALLBACK.get(channel_id)
-    if vtvgourl:
-        _set_cache(channel_id, vtvgourl)
-        return vtvgourl
-    php_url = XEMTV_PHP_ENDPOINTS.get(channel_id)
-    if php_url:
-        try:
-            r = requests.get(php_url, headers=UA, timeout=15, allow_redirects=True, verify=False)
-            if r.status_code == 200:
-                m3u8 = extract_m3u8_from_html(r.text)
-                if m3u8:
-                    _set_cache(channel_id, m3u8)
-                    return m3u8
-        except:
-            pass
-    fpt_key = f"_fpt_{channel_id}"
-    fpt_url = CDN_FALLBACK.get(fpt_key)
-    if fpt_url:
-        _set_cache(channel_id, fpt_url)
-        return fpt_url
-    return None
-
-def get_all_vtv_streams():
-    channels = []
-    for ch_id, php_url in XEMTV_PHP_ENDPOINTS.items():
-        stream_url = fetch_vtv_stream(ch_id)
-        channels.append({
-            'id': ch_id,
-            'name': CHANNEL_NAMES.get(ch_id, ch_id.upper()),
-            'stream_url': stream_url,
-        })
-    return channels
-
-XEMTV_CHANNELS = {v: k for k, v in CHANNEL_NAMES.items()}
-CDN_STREAMS = {v: k for k, v in CDN_FALLBACK.items()}
+"""VTV Scraper - xemtv.us + FPTPlay + VTVGo + canthotv"""
+import re, json, os, time
+import requests
+from bs4 import BeautifulSoup
+
+HEADERS = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36","Accept-Language":"vi-VN,vi;q=0.9,en;q=0.8"}
+
+def get_vtv_streams():
+    """Get all VTV channel streams"""
+    from vtv_api import CHANNELS, get_stream
+    results = []
+    for ch in CHANNELS:
+        stream = get_stream(ch["id"])
+        if stream:
+            results.append({"channel": ch, "stream": stream})
+    return results
+
+def get_vtvnambo_videos():
+    """Get VTV Nam Bo videos"""
+    try:
+        url = "https://xemtv.us/vtv-nam-bo.html"
+        r = requests.get(url, headers=HEADERS, timeout=15)
+        if r.status_code != 200: return []
+        r.encoding = "utf-8"
+        soup = BeautifulSoup(r.text, "lxml")
+        videos = []
+        for a in soup.find_all("a", href=True):
+            href = a.get("href", "")
+            if "/video/" in href:
+                title = a.get_text(strip=True)
+                if title and len(title) > 5:
+                    if not href.startswith("http"):
+                        href = "https://xemtv.us" + href
+                    videos.append({"title": title, "link": href, "source": "xemtv"})
+        return videos[:20]
+    except: return []