Update wc2026_scraper.py

wc2026_scraper.py

@@ -1,5 +1,6 @@
 """
 World Cup 2026 - NEWS uses same 8-source search as hashtag (NOT Google News)
+Timezone: UTC+7 (Asia/Ho_Chi_Minh)
 """
 import requests, re, time, threading
 from bs4 import BeautifulSoup
@@ -9,14 +10,21 @@ from concurrent.futures import ThreadPoolExecutor, as_completed
 
 BONGDA_HEADERS = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36","Accept":"application/json, text/javascript, */*; q=0.01","Accept-Language":"vi-VN,vi;q=0.9","Referer":"https://bongda.com.vn/giai-dau/24254/standings/world-cup","X-Requested-With":"XMLHttpRequest"}
 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'}
-WC_ID=24254;VN_TZ=timezone(timedelta(hours=7));CACHE={};LOCK=threading.Lock()
+WC_ID=24254
+VN_TZ=timezone(timedelta(hours=7))
+CACHE={}
+LOCK=threading.Lock()
+
 def _clean(s):return re.sub(r'\s+',' ',str(s or'')).strip()
+
 def _cached(key,ttl=120):
     with LOCK:
         if key in CACHE and time.time()-CACHE[key]['t']<ttl:return CACHE[key]['d']
     return None
+
 def _set(key,data):
     with LOCK:CACHE[key]={'t':time.time(),'d':data}
+
 def _bongda(endpoint):
     try:
         r=requests.get(f"https://bongda.com.vn{endpoint}",headers=BONGDA_HEADERS,timeout=10)
@@ -25,9 +33,11 @@ def _bongda(endpoint):
             if data.get("status")=="success":return data.get("html","")
     except:pass
     return""
+
 def _fetch(url,timeout=12):
     try:r=requests.get(url,headers=UA,timeout=timeout,allow_redirects=True);r.encoding='utf-8';return r.text if r.status_code==200 else''
     except:return''
+
 def _get_og_image(url):
     try:
         r=requests.get(url,headers=UA,timeout=8,allow_redirects=True);r.encoding='utf-8'
@@ -37,7 +47,9 @@ def _get_og_image(url):
         if m:img=m.group(1);return('https:'+img if img.startswith('//') else img)
     except:pass
     return''
+
 def _utc_to_vn(date_str):
+    """Convert UTC date string to VN timezone (UTC+7)"""
     try:
         dt_str=date_str.replace('Z','+00:00')
         if '+' not in dt_str and 'T' in dt_str:dt_str+='+00:00'
@@ -62,20 +74,26 @@ def scrape_fixtures():
                     except:match['status']='upcoming'
                 matches.append(match)
     except:pass
-    r={'matches':matches,'total':len(matches)};_set('wc_fix',r);return r
+    r={'matches':matches,'total':len(matches),'timezone':'UTC+7'}
+    _set('wc_fix',r)
+    return r
 
 def scrape_standings():
     c=_cached('wc_bxh',180)
     if c is not None:return c
     html=_bongda(f"/api/league-table/home?tournament_id={WC_ID}&is_detail=True")
     if not html:html=_bongda(f"/api/league-table/home?tournament_id={WC_ID}")
-    r={'html':html};_set('wc_bxh',r);return r
+    r={'html':html}
+    _set('wc_bxh',r)
+    return r
 
 def scrape_stats():
     c=_cached('wc_stats',600)
     if c is not None:return c
     html=_bongda(f"/api/event-standing/player-performance?tournament_id={WC_ID}")
-    r={'html':html};_set('wc_stats',r);return r
+    r={'html':html}
+    _set('wc_stats',r)
+    return r
 
 def scrape_history():return scrape_standings()
 def scrape_h2h(event_id):return{'html':_bongda(f"/api/fixtures/head-to-head?event_id={event_id}")}
@@ -83,7 +101,6 @@ def scrape_lineups(event_id):return{'html':_bongda(f"/api/fixtures/lineups?event
 def scrape_match_detail(event_id):return{'html':_bongda(f"/api/fixtures/commentaries?event_id={event_id}")}
 def scrape_summary():return scrape_standings()
 
-# === NEWS: uses SAME 8-source search as hashtag (NOT Google News) ===
 def _search_source(url_tpl, topic, selector, base_url='', limit=6):
     """Generic search on a VN news site."""
     items=[]
@@ -122,7 +139,6 @@ def scrape_wc_news():
         url_tpl,selector,base,source=cfg
         items=_search_source(url_tpl,topic,selector,base,8)
         return [(item,source) for item in items]
-    # bongda.com.vn + bongdaplus.vn via Jina (JS-protected) — keyword-filter for World Cup
     def _fetch_bongda_jina():
         out=[]
         kws=['world cup','wc 2026','world cup 2026','tuyển','đội tuyển','vòng loại','fifa']
@@ -147,12 +163,10 @@ def scrape_wc_news():
                     all_news.append({'title':item['title'],'link':item['link'],'img':'','source':source})
             except:pass
     
-    # Deduplicate
     seen=set();unique=[]
     for n in all_news:
         if n['link'] not in seen:seen.add(n['link']);unique.append(n)
     
-    # Fetch og:image for first 12
     def _fill(item):
         if not item.get('img'):item['img']=_get_og_image(item['link'])
     with ThreadPoolExecutor(6) as ex:
@@ -161,7 +175,8 @@ def scrape_wc_news():
             try:f.result()
             except:pass
     
-    _set('wc_news',unique[:30]);return unique[:30]
+    _set('wc_news',unique[:30])
+    return unique[:30]
 
 def scrape_road_to_wc():
     """Road to WC also uses direct search (not Google News)."""
@@ -174,7 +189,8 @@ def scrape_road_to_wc():
             if item['link'] not in[x['link'] for x in articles]:
                 img=_get_og_image(item['link'])
                 articles.append({'title':item['title'],'link':item['link'],'img':img,'source':'VnExpress','type':'road'})
-    _set('wc_road',articles[:20]);return articles[:20]
+    _set('wc_road',articles[:20])
+    return articles[:20]
 
 def get_wc2026_all():
     c=_cached('wc_all',90)
@@ -186,4 +202,7 @@ def get_wc2026_all():
             key=futs[f]
             try:data[key]=f.result()
             except:data[key]={} if key in('fixtures','standings','stats') else[]
-    data['summary']=data.get('standings',{});_set('wc_all',data);return data
+    data['summary']=data.get('standings',{})
+    data['timezone']='UTC+7'
+    _set('wc_all',data)
+    return data