Update app.py

app.py

@@ -2,7 +2,6 @@ import streamlit as st
 import requests
 from bs4 import BeautifulSoup
 
-# --- IPL TEAMS ---
 IPL_TEAMS = [
     "Chennai Super Kings", "Delhi Capitals", "Gujarat Titans", "Kolkata Knight Riders",
     "Lucknow Super Giants", "Mumbai Indians", "Punjab Kings", "Rajasthan Royals",
@@ -11,152 +10,113 @@ IPL_TEAMS = [
 
 BASE_URL = "https://www.cricbuzz.com"
 
-# --- Detect Team ---
+# Detect team
+
 def detect_team(user_input):
-    print(f"🟢 [DETECT] Analyzing input: {user_input}")
+    print(f"\n🟢 [DETECT] Input: {user_input}")
     for team in IPL_TEAMS:
         if team.lower() in user_input.lower():
-            print(f"✅ [DETECT] Team found: {team}")
+            print(f"✅ [DETECT] Found team: {team}")
             return team
-    print("❌ [DETECT] No IPL team detected in input.")
+    print("❌ [DETECT] No IPL team found")
     return None
 
-# --- Crawl main matches page and extract links ---
-def get_match_links_from_main_page():
-    try:
-        url = f"{BASE_URL}/cricket-series/7607/indian-premier-league-2024/matches"
-        print(f"\n🌐 [CRAWL] Fetching page: {url}")
-        headers = {"User-Agent": "Mozilla/5.0"}
-        response = requests.get(url, headers=headers)
-        print(f"✅ [CRAWL] Status code: {response.status_code}")
-
-        soup = BeautifulSoup(response.text, "html.parser")
-
-        all_a_tags = soup.find_all("a", href=True)
-        print(f"🔍 [CRAWL] Total <a> tags found: {len(all_a_tags)}")
+# Get live matches from cricbuzz homepage
 
-        links = []
-        for i in range(len(all_a_tags) - 1):
-            tag = all_a_tags[i]
-            next_tag = all_a_tags[i + 1]
-
-            text = tag.get_text().strip()
-            href = tag['href']
-
-            # Looking for IPL match result + scorecard links
-            if "cricket-scores" in href and any(team.lower() in text.lower() for team in IPL_TEAMS):
-                title = text
-                result = next_tag.get_text().strip()
-                full_url = BASE_URL + href
-                print(f"\n🎯 [MATCH FOUND]")
-                print(f"🏷️ Title: {title}")
-                print(f"📊 Result: {result}")
-                print(f"🔗 Link: {full_url}")
-
-                links.append((f"{title} – {result}", full_url))
-
-        print(f"\n✅ [DONE] Total match results extracted: {len(links)}")
-        return links
-
-    except Exception as e:
-        print(f"❌ [CRAWL ERROR] Failed to fetch match links: {e}")
-        return []
+def get_live_scores(team_name=None):
+    print("\n🌐 [LIVE] Fetching live scores page...")
+    url = "https://www.cricbuzz.com/cricket-match/live-scores"
+    headers = {"User-Agent": "Mozilla/5.0"}
+    response = requests.get(url, headers=headers)
+    print(f"✅ [LIVE] Response code: {response.status_code}")
 
-
-# --- Crawl each link and extract score ---
-def get_scores_from_links(team_name=None):
-    print("🟡 [STEP 1] Start crawling for scores...")
-    links = get_match_links_from_main_page()
-    print(f"✅ [STEP 1] Links to process: {len(links)}")
-
-    if not links:
-        print("❌ [ERROR] No links found.")
-        return ["No match links found."]
+    soup = BeautifulSoup(response.text, "html.parser")
+    matches = soup.find_all("div", class_="cb-col cb-col-100 cb-ltst-wgt-hdr")
+    print(f"🔍 [LIVE] Found {len(matches)} match blocks")
 
     results = []
+    for block in matches:
+        text = block.get_text(separator=" ").strip()
+        if team_name is None or team_name.lower() in text.lower():
+            results.append("🟢 LIVE: " + text)
+            print(f"✅ [LIVE MATCH] {text[:100]}...")
 
-    for i, (text, link) in enumerate(links):
-        print(f"\n🔗 [PROCESS] Link {i+1}: {text} -> {link}")
+    return results[:5] if results else []
 
-        if team_name and team_name.lower() not in text.lower():
-            print(f"⏭️ [SKIP] Team '{team_name}' not in link title.")
-            continue
+# Get recent results if no live match
 
-        try:
-            print(f"🌐 [FETCH] Visiting {link}...")
-            resp = requests.get(link, headers={"User-Agent": "Mozilla/5.0"})
-            print(f"✅ [FETCH] Status: {resp.status_code}")
+def get_recent_results(team_name=None):
+    try:
+        url = f"{BASE_URL}/cricket-series/7607/indian-premier-league-2024/matches"
+        print(f"\n🌐 [RECENT] Fetching matches from: {url}")
+        headers = {"User-Agent": "Mozilla/5.0"}
+        response = requests.get(url, headers=headers)
+        print(f"✅ [RECENT] Status code: {response.status_code}")
 
-            soup = BeautifulSoup(resp.text, "html.parser")
+        soup = BeautifulSoup(response.text, "html.parser")
+        all_tags = soup.find_all("a", href=True)
+        print(f"🔍 [RECENT] Total <a> tags: {len(all_tags)}")
 
-            title = soup.title.text.strip() if soup.title else "No Title Found"
-            print(f"📌 [TITLE] {title}")
+        won, lost = [], []
 
-            raw_text = soup.get_text(separator="\n").strip()
-            print("🧾 [HTML TEXT] Preview:")
-            print(raw_text[:500] + "\n...")
+        for i in range(len(all_tags) - 1):
+            tag = all_tags[i]
+            next_tag = all_tags[i + 1]
 
-            summary_container = soup.find("div", class_="cb-col cb-col-100 cb-ltst-wgt-hdr")
-            summary = summary_container.text.strip() if summary_container else text
-            print(f"📋 [SUMMARY] {summary[:200]}...")
+            href = tag['href']
+            title = tag.get_text().strip()
+            result = next_tag.get_text().strip()
 
-            result = f"🕓 {title}\n{summary}\n[View Match]({link})\n"
-            results.append(result)
-            print("✅ [RESULT] Added ✔️")
+            if "cricket-scores" in href and any(t.lower() in title.lower() for t in IPL_TEAMS):
+                full_url = BASE_URL + href
+                full_text = f"{title} – {result}\n[View Match]({full_url})"
 
-        except Exception as e:
-            print(f"❌ [ERROR] Failed to process link {link}: {e}")
+                if team_name and team_name.lower() not in title.lower():
+                    continue
 
-    if not results:
-        print("❌ [FINAL] No results matched filters.")
-        return ["No scores found for the team."]
+                if "won by" in result.lower():
+                    print(f"✅ [WON] {title} => {result}")
+                    won.append(full_text)
+                elif "lost" in result.lower():
+                    print(f"🟥 [LOST] {title} => {result}")
+                    lost.append(full_text)
 
-    print(f"✅ [DONE] Returning {len(results)} results.")
-    return results
+        top_results = won[:5] + lost[:5]
+        print(f"📊 [RECENT] Total displayed: {len(top_results)}")
+        return top_results if top_results else ["No recent match results found."]
 
-# --- Fantasy placeholder ---
-def get_fantasy_stats(team_name=None):
-    print(f"[FANTASY] Placeholder for team: {team_name}")
-    return [f"Fantasy stats for {team_name or 'your team'} are currently limited. Try Dream11 or official IPL fantasy apps."]
+    except Exception as e:
+        print(f"❌ [ERROR] Failed recent match fetch: {e}")
+        return ["Error loading past matches."]
 
-# --- News placeholder ---
-def get_team_news(team_name=None):
-    print(f"[NEWS] Placeholder for team: {team_name}")
-    return [f"News for {team_name or 'IPL'} is coming soon! Stay tuned."]
+# Streamlit UI
 
-# --- Streamlit UI ---
 st.set_page_config(page_title="IPL Chatbot", layout="centered")
-st.title("🏏 IPL Chatbot with Crawl4AI-style Debugging")
-
-user_input = st.text_input("Ask me anything about IPL scores, teams, or fantasy:", placeholder="e.g. Show Mumbai Indians score")
+st.title("🏏 IPL Chatbot")
+user_input = st.text_input("Ask about IPL scores:", placeholder="e.g. Show me Mumbai Indians score")
 
 if user_input:
-    print(f"\n========== USER INPUT RECEIVED ==========\n{user_input}\n=========================================")
-    team = detect_team(user_input)
+    print(f"\n========== USER INPUT ==========")
+    print(user_input)
+    print("================================")
 
-    if "score" in user_input.lower():
-        st.subheader("📊 IPL Match Results")
-        scores = get_scores_from_links(team)
-        for score in scores:
-            st.markdown(score)
-
-    elif "fantasy" in user_input.lower():
-        st.subheader("📈 Fantasy Info")
-        for stat in get_fantasy_stats(team):
-            st.write(stat)
-
-    elif "news" in user_input.lower():
-        st.subheader("📰 News")
-        for news in get_team_news(team):
-            st.write(news)
+    team = detect_team(user_input)
 
+    scores = get_live_scores(team)
+    if scores:
+        st.subheader("🟢 Live Match(es):")
+        for s in scores:
+            st.markdown(s)
     else:
-        st.info("Try asking about 'scores', 'fantasy', or 'news' for a specific IPL team.")
+        st.warning("❌ No live match found. Showing recent results:")
+        past = get_recent_results(team)
+        for p in past:
+            st.markdown(p)
 
-with st.expander("💡 Try these examples"):
+with st.expander("💡 Try examples"):
     st.markdown("""
-- Show me Mumbai Indians score  
-- Fantasy info for RCB  
-- News about CSK  
-- What’s the latest from Gujarat Titans?
-""")
+- Show Mumbai Indians score
+- Delhi Capitals recent results
+- CSK won?
+- RCB vs MI today?
+    """)