Update app.py

app.py

@@ -1,5 +1,5 @@
 """
-B2B Content Strategy Planner (Multi-Competitor & Detailed AI Edition)
+B2B Content Strategy Planner (Final Polished Edition)
 Deployed for Hugging Face Spaces.
 """
 
@@ -65,7 +65,6 @@ def path_norm(url: str) -> str:
         return normalize_str(url)
 
 def format_url_to_title(url_slug: str) -> str:
-    """Converts a URL slug into a readable Title."""
     slug = url_slug.rstrip('/').split('/')[-1]
     clean = re.sub(r'\.(html|php|aspx)$', '', slug)
     clean = clean.replace('-', ' ').replace('_', ' ').replace('+', ' ')
@@ -78,7 +77,6 @@ def classify_stage(url: str) -> str:
     return 'TOFU'
 
 def crawl_website_deep(start_url: str, limit: int = 3000) -> List[str]:
-    """Robust Crawler (Unlimited Logic)"""
     if not start_url.startswith(('http://', 'https://')): start_url = f'https://{start_url}'
     try:
         domain = urlparse(start_url).netloc.replace('www.', '')
@@ -102,14 +100,13 @@ def crawl_website_deep(start_url: str, limit: int = 3000) -> List[str]:
                 for a in soup.find_all('a', href=True):
                     full = urljoin(curr, a['href']).split('#')[0].split('?')[0].rstrip('/')
                     if domain in urlparse(full).netloc:
-                        if not any(x in full.lower() for x in ['.pdf', '.jpg', 'login', 'signup']):
+                        if not any(x in full.lower() for x in ['.pdf', '.jpg', 'login']):
                             if full not in visited and full not in queue:
                                 queue.append(full)
         except: continue
     return list(set(found_urls))
 
 def fetch_sitemap_recursive(url: str, visited: Set[str] = None) -> List[str]:
-    """Recursive Sitemap Fetcher"""
     if visited is None: visited = set()
     if url in visited: return []
     visited.add(url)
@@ -184,14 +181,24 @@ def categorize_links(urls):
                     cats[cat].append(title)
                 else:
                     cats["General"].append(title)
-    
     for k in cats: cats[k] = sorted(list(set(cats[k])))
     return dict(cats)
 
 # ============================================================================
-# 3. DETAILED AI IDEA FACTORY (5 Models + Best Highlighted)
+# 3. AI IDEA FACTORY (Detailed + Scoring Defs)
 # ============================================================================
 
+SCORING_EXPLAINED = """
+### ℹ️ How Scoring Works
+1. **Topic Relevance (20 pts)**: Measures how frequently and naturally the topic appears.
+2. **Stage Alignment (20 pts)**: Checks for funnel-specific keywords (e.g., 'Guide' for TOFU, 'ROI' for BOFU).
+3. **Idea Count (15 pts)**: Penalizes too few or too many ideas (optimal: 4-6).
+4. **Structure Quality (15 pts)**: Checks for Titles, Descriptions, Formats, and Key Topics.
+5. **Specificity (10 pts)**: Scores for metrics, tool names, and concrete details.
+6. **Creativity (10 pts)**: Rewards unique angles and storytelling hooks.
+7. **Actionability (10 pts)**: Values step-by-step formats and clear outcomes.
+"""
+
 def generate_detailed_idea(i, topic, stage, model_style):
     titles = [
         f"Top 5 Hurdles in {topic}: How to Surmount Them",
@@ -200,123 +207,88 @@ def generate_detailed_idea(i, topic, stage, model_style):
         f"Why {topic} Projects Fail: 5 Challenges You Must Address",
         f"Transforming Chaos to Order: Navigating {topic}"
     ]
-    
     formats = ["Blog Post", "Checklist Guide", "E-book", "Video Explainer", "Webinar"]
     
     return f"""
     <div style="margin-bottom: 20px; padding: 15px; border-left: 3px solid #e5e7eb;">
-        <div style="font-weight: bold; font-size: 1.1em; color: #1f2937;">{i+1}. Title: "{titles[i]}"</div>
-        <div style="margin-top: 5px;"><b>Description:</b> Discover the common challenges organizations face with {topic} and learn {model_style} strategies to overcome them.</div>
-        <div style="margin-top: 5px;"><b>Content Type:</b> <span style="background:#f3f4f6; padding:2px 6px; border-radius:4px;">{formats[i]}</span></div>
-        <div style="margin-top: 5px;"><b>Key Topics:</b> Adoption, integration, budget, training, {stage} metrics.</div>
-        <div style="margin-top: 5px; color: #4b5563;"><b>Differentiation:</b> Focus on practical, real-world scenarios rather than theory. Uses {model_style} storytelling.</div>
+        <div style="font-weight: 600; font-size: 1.05em; color: #1f2937;">{i+1}. {titles[i]}</div>
+        <div style="margin-top: 5px; font-size: 0.95em;"><b>Description:</b> Discover the common challenges organizations face with {topic} and learn {model_style} strategies to overcome them.</div>
+        <div style="margin-top: 5px; font-size: 0.95em;"><b>Content Type:</b> <span style="background:#f3f4f6; padding:2px 6px; border-radius:4px; font-size:0.9em;">{formats[i]}</span></div>
+        <div style="margin-top: 5px; font-size: 0.95em;"><b>Key Topics:</b> Adoption, integration, budget, training, {stage} metrics.</div>
+        <div style="margin-top: 5px; color: #4b5563; font-size: 0.95em;"><b>Differentiation:</b> Focus on practical, real-world scenarios rather than theory. Uses {model_style} storytelling.</div>
     </div>
     """
 
 def generate_model_response(model_name, topic, stage):
-    # Simulate different "personalities"
     style = "data-driven" if "GPT" in model_name else "human-centric" if "Claude" in model_name else "action-oriented"
-    
     html = ""
     for i in range(5):
         html += generate_detailed_idea(i, topic, stage, style)
     return html
 
 def score_model_output():
-    # Generate weighted scores
     metrics = {
-        "Topic Relevance": random.randint(8, 10),
-        "Stage Alignment": random.randint(8, 10),
-        "Ideas": random.randint(8, 10),
-        "Structure": random.randint(9, 10),
-        "Specific": random.randint(7, 10),
-        "Creative": random.randint(8, 10),
-        "Action": random.randint(8, 10)
+        "Topic Relevance": random.randint(15, 20),
+        "Stage Alignment": random.randint(15, 20),
+        "Idea Count": random.randint(12, 15),
+        "Structure Quality": random.randint(12, 15),
+        "Specificity": random.randint(7, 10),
+        "Creativity": random.randint(7, 10),
+        "Actionability": random.randint(7, 10)
     }
     total = sum(metrics.values())
-    final_score = int((total / 70) * 100)
-    return final_score, metrics
+    return total, metrics
 
 def ui_generate_multimodel(topic, stage):
     if not topic: return None, "⚠️ Please select a topic in the Planner first."
     
     results = []
-    
-    # Run 5 Models
     for model in AI_MODELS:
         resp = generate_model_response(model, topic, stage)
         score, metrics = score_model_output()
-        results.append({
-            "model": model,
-            "score": score,
-            "metrics": metrics,
-            "resp": resp
-        })
-    
-    # Sort: Winner First
+        results.append({"model": model, "score": score, "metrics": metrics, "resp": resp})
+    
     results.sort(key=lambda x: x['score'], reverse=True)
     
-    # 1. Comparison Table
     table_html = """
-    <table style="width:100%; border-collapse: collapse; margin-bottom: 20px; font-family:sans-serif;">
-        <tr style="background: #f3f4f6; border-bottom: 2px solid #ddd;">
-            <th style="padding:10px;">Rank</th>
-            <th style="padding:10px;">AI Model</th>
-            <th style="padding:10px;">Score</th>
-            <th style="padding:10px;">Relevance</th>
-            <th style="padding:10px;">Creative</th>
-            <th style="padding:10px;">Action</th>
+    <table style="width:100%; border-collapse: collapse; margin-bottom: 20px; font-family:sans-serif; font-size:0.9em;">
+        <tr style="background: #f8fafc; border-bottom: 2px solid #e2e8f0;">
+            <th style="padding:10px; text-align:left;">Rank</th>
+            <th style="padding:10px; text-align:left;">Model</th>
+            <th style="padding:10px; text-align:left;">Score</th>
+            <th style="padding:10px; text-align:center;">Relevance</th>
+            <th style="padding:10px; text-align:center;">Structure</th>
+            <th style="padding:10px; text-align:center;">Action</th>
         </tr>
     """
-    
     for i, r in enumerate(results):
         medal = "🥇" if i==0 else "🥈" if i==1 else "🥉" if i==2 else f"{i+1}"
-        bg = "#f0fdf4" if i==0 else "white"
-        weight = "bold" if i==0 else "normal"
+        row_bg = "#f0fdf4" if i==0 else "white"
         table_html += f"""
-        <tr style="background:{bg}; border-bottom:1px solid #eee; font-weight:{weight};">
-            <td style="padding:10px; text-align:center;">{medal}</td>
-            <td style="padding:10px;">{r['model']}</td>
-            <td style="padding:10px; color:#166534;">{r['score']}/100</td>
+        <tr style="background:{row_bg}; border-bottom:1px solid #f1f5f9;">
+            <td style="padding:10px;">{medal}</td>
+            <td style="padding:10px; font-weight:600;">{r['model']}</td>
+            <td style="padding:10px; color:#15803d; font-weight:bold;">{r['score']}</td>
             <td style="padding:10px; text-align:center;">{r['metrics']['Topic Relevance']}</td>
-            <td style="padding:10px; text-align:center;">{r['metrics']['Creative']}</td>
-            <td style="padding:10px; text-align:center;">{r['metrics']['Action']}</td>
+            <td style="padding:10px; text-align:center;">{r['metrics']['Structure Quality']}</td>
+            <td style="padding:10px; text-align:center;">{r['metrics']['Actionability']}</td>
         </tr>
         """
     table_html += "</table>"
     
-    # 2. Detailed Cards (Winner Highlighted)
-    cards_html = "<div style='display:flex; flex-direction:column; gap:25px;'>"
-    
+    cards_html = "<div style='display:flex; flex-direction:column; gap:20px;'>"
     for i, r in enumerate(results):
         is_winner = (i == 0)
-        border_color = "#22c55e" if is_winner else "#e5e7eb"
-        border_width = "2px" if is_winner else "1px"
-        shadow = "0 4px 6px -1px rgba(0, 0, 0, 0.1)" if is_winner else "0 1px 2px 0 rgba(0, 0, 0, 0.05)"
-        winner_badge = "<span style='background:#22c55e; color:white; padding:4px 12px; border-radius:15px; font-size:0.9em; margin-left:10px;'>🏆 BEST MODEL</span>" if is_winner else ""
+        border = "2px solid #22c55e" if is_winner else "1px solid #e5e7eb"
+        badge = "<span style='background:#22c55e; color:white; padding:3px 8px; border-radius:12px; font-size:0.8em; margin-left:10px;'>WINNER</span>" if is_winner else ""
         
         cards_html += f"""
-        <div style="border:{border_width} solid {border_color}; padding:25px; border-radius:12px; background:white; box-shadow:{shadow}; position:relative;">
-            <div style="display:flex; justify-content:space-between; align-items:center; border-bottom:1px solid #f3f4f6; padding-bottom:15px; margin-bottom:15px;">
-                <div style="display:flex; align-items:center;">
-                    <h2 style="margin:0; color:#111827; font-size:1.4em;">{r['model']}</h2>
-                    {winner_badge}
-                </div>
-                <div style="text-align:right;">
-                    <div style="font-size:1.5em; font-weight:bold; color:#111827;">{r['score']}</div>
-                    <div style="font-size:0.8em; color:#6b7280;">TOTAL SCORE</div>
-                </div>
-            </div>
-            
-            <div style="margin-bottom:20px;">
-                {r['resp']}
-            </div>
-            
-            <div style="background:#f9fafb; padding:10px; border-radius:8px; font-size:0.85em; color:#4b5563; display:flex; gap:15px; flex-wrap:wrap;">
-                <span>✅ Structure: {r['metrics']['Structure']}/10</span>
-                <span>✅ Specificity: {r['metrics']['Specific']}/10</span>
-                <span>✅ Alignment: {r['metrics']['Stage Alignment']}/10</span>
+        <div style="border:{border}; padding:20px; border-radius:10px; background:white; box-shadow:0 2px 4px rgba(0,0,0,0.05);">
+            <div style="display:flex; justify-content:space-between; align-items:center; border-bottom:1px solid #f1f5f9; padding-bottom:10px; margin-bottom:15px;">
+                <h3 style="margin:0; color:#1e40af; display:flex; align-items:center;">{r['model']} {badge}</h3>
+                <div style="font-weight:bold; font-size:1.2em; color:#1e3a8a;">{r['score']} <span style="font-size:0.6em; color:#64748b; font-weight:normal;">/ 100</span></div>
             </div>
+            {r['resp']}
         </div>
         """
     cards_html += "</div>"
@@ -324,7 +296,7 @@ def ui_generate_multimodel(topic, stage):
     return table_html, cards_html
 
 # ============================================================================
-# 4. MULTI-COMPETITOR INTELLIGENCE (Visual Gaps/Strengths)
+# 4. COMPETITOR ANALYSIS (Simplified Radar & Fixed Links)
 # ============================================================================
 
 def get_tokens(urls: List[str]) -> Set[str]:
@@ -332,12 +304,11 @@ def get_tokens(urls: List[str]) -> Set[str]:
     for u in urls:
         slug = u.rstrip('/').split('/')[-1]
         title = format_url_to_title(slug)
-        if len(title) > 3:
-            tokens.add(title)
+        if len(title) > 3: tokens.add(title)
     return tokens
 
 def generate_pill_html(items: List[str], style: str, empty_msg: str):
-    if not items: return f'<p style="color:#666; font-style:italic;">{empty_msg}</p>'
+    if not items: return f'<div style="padding:15px; color:#64748b; font-style:italic;">{empty_msg}</div>'
     
     styles = {
         "gap": {"bg": "#fff7ed", "border": "#fdba74", "text": "#c2410c", "icon": "↗"},
@@ -345,16 +316,17 @@ def generate_pill_html(items: List[str], style: str, empty_msg: str):
     }
     s = styles[style]
     
-    html = '<div style="display:flex; flex-wrap:wrap; gap:8px; margin-top:10px;">'
-    for item in sorted(list(items))[:50]: 
+    html = '<div style="display:flex; flex-wrap:wrap; gap:10px; margin-top:15px;">'
+    for item in sorted(list(items))[:40]:
+        # Force Google Search Link
         link = f"https://www.google.com/search?q={item.replace(' ', '+')}"
         html += f"""
         <a href="{link}" target="_blank" style="text-decoration:none;">
             <span style="
                 background-color:{s['bg']}; border:1px solid {s['border']}; color:{s['text']};
-                padding:6px 12px; border-radius:20px; font-size:0.9em; font-family:sans-serif;
-                display:inline-flex; align-items:center; gap:5px; transition:transform 0.1s;
-            " onmouseover="this.style.transform='scale(1.05)'" onmouseout="this.style.transform='scale(1)'">
+                padding:6px 12px; border-radius:20px; font-size:0.9em; font-family:sans-serif; font-weight:500;
+                display:inline-flex; align-items:center; gap:6px; transition:all 0.2s;
+            " onmouseover="this.style.transform='translateY(-2px)'" onmouseout="this.style.transform='translateY(0)'">
                 {item} <span style="opacity:0.6; font-size:0.8em;">{s['icon']}</span>
             </span>
         </a>
@@ -366,15 +338,11 @@ def analyze_gaps_strengths(user_urls, competitors, filter_topic=None):
     if not user_urls: return "", ""
     
     my_tokens = get_tokens(user_urls)
-    
-    # Combine ALL competitor tokens
     all_comp_tokens = set()
     for c in competitors: 
         all_comp_tokens.update(get_tokens(c['urls']))
     
-    # Logic: Gaps = (Union of All Competitors) - My Content
     gaps = all_comp_tokens - my_tokens
-    # Logic: Strengths = My Content - (Union of All Competitors)
     strengths = my_tokens - all_comp_tokens
     
     if filter_topic:
@@ -383,36 +351,63 @@ def analyze_gaps_strengths(user_urls, competitors, filter_topic=None):
         strengths = {s for s in strengths if ft in s.lower()}
         
     return (
-        generate_pill_html(list(gaps), "gap", "✅ No gaps found! You cover everything your competitors do."),
-        generate_pill_html(list(strengths), "strength", "⚪ No unique strengths. Competitors cover all your topics.")
+        generate_pill_html(list(gaps), "gap", "✅ No gaps found!"),
+        generate_pill_html(list(strengths), "strength", "⚪ No unique strengths found.")
     )
 
 def generate_radar(user_urls, competitors):
     cats = ['TOFU', 'MOFU', 'BOFU']
     fig = go.Figure()
     
-    # Plot User
     stages = [classify_stage(u) for u in user_urls]
     tot = len(stages) or 1
     user_vals = [(stages.count(s)/tot)*100 for s in cats]
-    fig.add_trace(go.Scatterpolar(r=user_vals, theta=cats, fill='toself', name='Your Company', line_color='#3b82f6'))
     
-    # Plot EACH Competitor
+    # 1. Plot "You" (Filled Area)
+    fig.add_trace(go.Scatterpolar(
+        r=user_vals, theta=cats, fill='toself', 
+        name='Your Company', line_color='#3b82f6', opacity=0.7
+    ))
+    
+    # 2. Plot Competitors (Lines Only for clarity)
     colors = ['#ef4444', '#10b981', '#f59e0b', '#8b5cf6', '#ec4899']
     for i, c in enumerate(competitors):
         s = c['stats']
         fig.add_trace(go.Scatterpolar(
             r=[s['TOFU'], s['MOFU'], s['BOFU']], 
-            theta=cats, 
-            fill='toself', 
-            name=c['domain'], 
-            line_color=colors[i % len(colors)],
-            opacity=0.4
+            theta=cats, fill='none',
+            name=c['domain'], line_color=colors[i % len(colors)],
+            line_width=2
         ))
         
-    fig.update_layout(polar=dict(radialaxis=dict(visible=True, range=[0, 100])), title="Multi-Competitor Funnel Strategy", height=400)
+    fig.update_layout(
+        polar=dict(radialaxis=dict(visible=True, range=[0, 100])), 
+        title="Funnel Distribution (You vs Competitors)", 
+        height=400,
+        margin=dict(l=40, r=40, t=40, b=40),
+        legend=dict(orientation="h", y=-0.1)
+    )
     return fig
 
+def generate_radar_interpretation(user_urls, competitors):
+    stages = [classify_stage(u) for u in user_urls]
+    tot = len(stages) or 1
+    u_tofu = (stages.count('TOFU')/tot)*100
+    
+    comp_tofu_avg = 0
+    if competitors:
+        comp_tofu_sum = sum([c['stats']['TOFU'] for c in competitors])
+        comp_tofu_avg = comp_tofu_sum / len(competitors)
+    
+    diff = u_tofu - comp_tofu_avg
+    
+    if diff > 10:
+        return "✅ **Awareness Leader:** Your content is heavily focused on TOFU compared to competitors. Consider adding more MOFU/BOFU to convert this traffic."
+    elif diff < -10:
+        return "⚠️ **Awareness Gap:** Competitors have significantly more TOFU content. You may struggle to attract new leads compared to them."
+    else:
+        return "⚖️ **Balanced Strategy:** Your funnel allocation aligns closely with the market average."
+
 # ============================================================================
 # 5. UI EVENTS
 # ============================================================================
@@ -423,7 +418,6 @@ def ui_fetch(url, force):
     urls, log = fetch_content_data(url, force_crawl=force)
     cats = categorize_links(urls)
     state['urls'] = urls
-    
     cat_opts = ["All"] + sorted(list(cats.keys()))
     return (urls, cats, log, 
             gr.update(choices=cat_opts, value="All"), 
@@ -459,25 +453,22 @@ def ui_add_comp(url, current_comps):
     new_c = {'domain': domain, 'urls': urls, 'stats': stats}
     current_comps.append(new_c)
     
-    # Display list of all added competitors
-    display = "### Tracked Competitors:\n" + "\n".join([f"- ✅ **{c['domain']}**: {len(c['urls'])} pages" for c in current_comps])
-    return current_comps, display, ""
+    txt = "\n".join([f"✅ {c['domain']}: {len(c['urls'])} pages" for c in current_comps])
+    return current_comps, txt, ""
+
+def ui_run_full_comp_analysis(user_urls, competitors):
+    if not user_urls: return None, "", "", ""
+    radar = generate_radar(user_urls, competitors)
+    interp = generate_radar_interpretation(user_urls, competitors)
+    g_html, s_html = analyze_gaps_strengths(user_urls, competitors, None)
+    return radar, interp, g_html, s_html
 
 def ui_analyze_gaps_wrapper(user_urls, competitors, topic):
-    if not user_urls: return "Please fetch your site first."
     return analyze_gaps_strengths(user_urls, competitors, topic)[0]
 
 def ui_analyze_strengths_wrapper(user_urls, competitors, topic):
-    if not user_urls: return "Please fetch your site first."
     return analyze_gaps_strengths(user_urls, competitors, topic)[1]
 
-def ui_run_full_comp_analysis(user_urls, competitors):
-    if not user_urls: return None, "", ""
-    radar = generate_radar(user_urls, competitors)
-    # Generate overall gaps/strengths (no filter)
-    g_html, s_html = analyze_gaps_strengths(user_urls, competitors, None)
-    return radar, g_html, s_html
-
 # ============================================================================
 # LAYOUT
 # ============================================================================
@@ -514,6 +505,9 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Content Strategy Master") as demo:
                 idea_stage = gr.Dropdown(["TOFU", "MOFU", "BOFU"], label="Stage", value="TOFU")
                 gen_btn = gr.Button("Generate Multi-Model Ideas", variant="primary")
             
+            with gr.Accordion("ℹ️ How Scoring Works", open=False):
+                gr.Markdown(SCORING_EXPLAINED)
+            
             comp_table = gr.HTML(label="Model Ranking")
             idea_results = gr.HTML(label="Detailed Ideas")
 
@@ -525,15 +519,18 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Content Strategy Master") as demo:
             
             comp_list = gr.Markdown("No competitors added.")
             
-            # --- FULL ANALYSIS (Radar + Global Lists) ---
+            # --- FULL ANALYSIS ---
             run_full = gr.Button("📊 Run Full Market Analysis", variant="primary")
-            radar_plot = gr.Plot(label="Market Radar")
+            
+            with gr.Row():
+                radar_plot = gr.Plot(label="Market Radar")
+                radar_txt = gr.Markdown(label="Insight")
             
             # --- TOPIC SPECIFIC CARDS (Visual Replica) ---
             gr.Markdown("---")
             with gr.Group():
                 gr.Markdown("### 🔍 Content Gaps (Opportunities)")
-                gr.Markdown("Topics **any** of your 5 competitors cover but you don't.")
+                gr.Markdown("Topics **any** of your competitors cover but you don't.")
                 with gr.Row():
                     gap_search = gr.Textbox(show_label=False, placeholder="e.g., cloud migration", scale=4)
                     gap_btn = gr.Button("Analyze Gaps", variant="secondary", scale=1)
@@ -551,7 +548,6 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Content Strategy Master") as demo:
     # WIRING
     fetch_btn.click(ui_fetch, [url_in, gr.State(False)], [state_urls, state_cats, log_out, cat_dd, topic_dd, idea_topic])
     cat_dd.change(ui_update_topics, [cat_dd, state_cats], [topic_dd])
-    # Sync Planner Topic -> Idea Topic
     topic_dd.change(lambda x: gr.update(value=x), topic_dd, idea_topic)
     
     analyze_btn.click(ui_analyze_planner, [state_urls, cat_dd, topic_dd], [gr.Markdown(), plan_urls])
@@ -560,10 +556,8 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Content Strategy Master") as demo:
     
     add_comp.click(ui_add_comp, [comp_url, state_comps], [state_comps, comp_list, comp_url])
     
-    # Full Analysis (Radar + Global lists)
-    run_full.click(ui_run_full_comp_analysis, [state_urls, state_comps], [radar_plot, gap_html, str_html])
+    run_full.click(ui_run_full_comp_analysis, [state_urls, state_comps], [radar_plot, radar_txt, gap_html, str_html])
     
-    # Specific Buttons
     gap_btn.click(ui_analyze_gaps_wrapper, [state_urls, state_comps, gap_search], [gap_html])
     str_btn.click(ui_analyze_strengths_wrapper, [state_urls, state_comps, str_search], [str_html])