Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,11 +1,12 @@
 """
 Review Validator - Advanced Edition
-With explainability graphs + PDF report download
+With explainability graphs + PDF report download + Google Reverse Image Search
 """
 
 import os
 import io
 import time
+import base64
 import numpy as np
 import streamlit as st
 from transformers import pipeline, logging as hf_logging
@@ -82,7 +83,26 @@ def get_token():
 
     return None
 
+def get_serpapi_key():
+    """
+    Safely retrieves SERPAPI_KEY.
+    Priority 1: Env var
+    Priority 2: Streamlit Secrets
+    """
+    key = os.environ.get("SERPAPI_KEY")
+    if key:
+        return key
+    
+    try:
+        if hasattr(st, "secrets") and "SERPAPI_KEY" in st.secrets:
+            return st.secrets["SERPAPI_KEY"]
+    except Exception:
+        pass
+
+    return None
+
 HF_TOKEN = get_token()
+SERPAPI_KEY = get_serpapi_key()
 
 # --- Custom CSS ---
 def inject_custom_css():
@@ -152,6 +172,26 @@ def inject_custom_css():
             margin-top: 8px;
         }
 
+        .reverse-search-box {
+            background: #f0fff4;
+            border-left: 5px solid #48bb78;
+            padding: 15px;
+            border-radius: 5px;
+            margin-top: 15px;
+        }
+
+        .result-item {
+            background: white;
+            padding: 12px;
+            border-radius: 8px;
+            margin: 8px 0;
+            border: 1px solid #e2e8f0;
+            transition: box-shadow 0.2s;
+        }
+        .result-item:hover {
+            box-shadow: 0 2px 8px rgba(0,0,0,0.1);
+        }
+
         .stButton>button {
             border-radius: 30px;
             font-weight: bold;
@@ -443,6 +483,75 @@ def get_image_from_url(url):
     except Exception:
         return None
 
+# --- GOOGLE REVERSE IMAGE SEARCH (SerpAPI) ---
+def reverse_image_search(image_obj):
+    """
+    Performs Google reverse image search using SerpAPI.
+    
+    Args:
+        image_obj: PIL Image object
+    
+    Returns:
+        dict with 'success', 'results', 'error' keys
+    """
+    if not SERPAPI_KEY:
+        return {
+            "success": False,
+            "error": "SERPAPI_KEY not configured. Add it to secrets or environment variables.",
+            "results": []
+        }
+    
+    try:
+        # Convert PIL Image to base64
+        buffered = io.BytesIO()
+        image_obj.save(buffered, format="JPEG")
+        img_str = base64.b64encode(buffered.getvalue()).decode()
+        
+        # SerpAPI endpoint for Google Lens (reverse image search)
+        url = "https://serpapi.com/search"
+        
+        params = {
+            "engine": "google_lens",
+            "api_key": SERPAPI_KEY,
+            "url": f"data:image/jpeg;base64,{img_str}"
+        }
+        
+        response = requests.get(url, params=params, timeout=15)
+        
+        if response.status_code != 200:
+            return {
+                "success": False,
+                "error": f"SerpAPI returned status code {response.status_code}",
+                "results": []
+            }
+        
+        data = response.json()
+        
+        # Extract visual matches
+        visual_matches = data.get("visual_matches", [])
+        
+        results = []
+        for match in visual_matches[:10]:  # Limit to top 10 results
+            results.append({
+                "title": match.get("title", "No title"),
+                "link": match.get("link", ""),
+                "source": match.get("source", "Unknown"),
+                "thumbnail": match.get("thumbnail", "")
+            })
+        
+        return {
+            "success": True,
+            "results": results,
+            "error": None
+        }
+        
+    except Exception as e:
+        return {
+            "success": False,
+            "error": f"Reverse search failed: {str(e)}",
+            "results": []
+        }
+
 # --- Plotting ---
 
 def breakdown_chart(stats):
@@ -498,10 +607,11 @@ def word_freq_chart(stats):
 
 # --- PDF REPORT GENERATION ---
 
-def generate_pdf_report(platform, review_text, text_res, text_stats, image_info):
+def generate_pdf_report(platform, review_text, text_res, text_stats, image_info, reverse_search_data=None):
     """
     Returns PDF bytes. Requires ReportLab.
     image_info: dict or None
+    reverse_search_data: dict with reverse search results or None
     """
     buffer = io.BytesIO()
     c = canvas.Canvas(buffer, pagesize=A4)
@@ -558,6 +668,21 @@ def generate_pdf_report(platform, review_text, text_res, text_stats, image_info)
         write_line(f"Caption (approx): {image_info['caption']}")
         y -= 10
 
+    # Reverse search results
+    if reverse_search_data and reverse_search_data.get('success'):
+        write_line("=== Reverse Image Search Results ===", font="Helvetica-Bold", size=12)
+        results = reverse_search_data.get('results', [])
+        if results:
+            write_line(f"Found {len(results)} matches online:")
+            for i, result in enumerate(results[:5], 1):
+                write_line(f"{i}. {result['title']}")
+                write_line(f"   Source: {result['source']}")
+                write_line(f"   Link: {result['link']}")
+                y -= 5
+        else:
+            write_line("No matches found.")
+        y -= 10
+
     c.showPage()
     c.save()
     pdf_bytes = buffer.getvalue()
@@ -571,7 +696,7 @@ def landing_page():
     <div class="hero-box">
         <div class="hero-title">🛡️ Review Validator</div>
         <div class="hero-subtitle">
-            Advanced AI-powered review and image analysis with graphs, explainability, and exportable reports.
+            Advanced AI-powered review and image analysis with graphs, explainability, reverse image search, and exportable reports.
         </div>
     </div>
     """, unsafe_allow_html=True)
@@ -596,9 +721,9 @@ def landing_page():
     with c3:
         st.markdown("""
         <div class="feature-card">
-            <span class="emoji-icon">📊</span>
-            <h3>Explainable Reports</h3>
-            <p>Graphs, breakdowns, explanations, and PDF report downloads for sharing.</p>
+            <span class="emoji-icon">🔍</span>
+            <h3>Reverse Image Search</h3>
+            <p>Find where the image appears online using Google reverse image search.</p>
         </div>
         """, unsafe_allow_html=True)
 
@@ -693,190 +818,4 @@ def detector_page(squad, warnings_text=None):
                 color = "red" if bot_score > 50 else "green"
                 k1.markdown(
                     f"""<div class="stat-box">
-                        <div class="stat-num" style="color:{color}">{bot_score:.0f}%</div>
-                        <div class="stat-txt">AI-Likeness</div>
-                    </div>""",
-                    unsafe_allow_html=True
-                )
-                k2.markdown(
-                    f"""<div class="stat-box">
-                        <div class="stat-num">{grammar_score:.0f}%</div>
-                        <div class="stat-txt">Grammar Quality</div>
-                    </div>""",
-                    unsafe_allow_html=True
-                )
-                k3.markdown(
-                    f"""<div class="stat-box">
-                        <div class="stat-num">{mood_label}</div>
-                        <div class="stat-txt">Sentiment</div>
-                    </div>""",
-                    unsafe_allow_html=True
-                )
-
-                st.write("")
-                g1, g2, g3 = st.columns(3)
-                with g1:
-                    st.markdown("#### 📊 Scores")
-                    fig = breakdown_chart(res)
-                    st.pyplot(fig, use_container_width=True)
-                with g2:
-                    st.markdown("#### 📏 Sentence Lengths")
-                    fig2 = sentence_length_chart(stats)
-                    st.pyplot(fig2, use_container_width=True)
-                with g3:
-                    st.markdown("#### 🔤 Top Words")
-                    fig3 = word_freq_chart(stats)
-                    st.pyplot(fig3, use_container_width=True)
-
-                st.markdown("#### 💡 Verdict & Explanation")
-                if verdict_type == "error":
-                    st.error(verdict_text)
-                elif verdict_type == "warning":
-                    st.warning(verdict_text)
-                else:
-                    st.success(verdict_text)
-
-                reasons = explain_text(res, stats, strict_mode_saved)
-                for r in reasons:
-                    st.markdown(f"- {r}")
-
-                st.markdown(
-                    "<small>Note: These scores and explanations are signals, not absolute proof. "
-                    "Always combine them with your own judgement.</small>",
-                    unsafe_allow_html=True
-                )
-
-                # PDF report button
-                st.write("")
-                if HAVE_REPORTLAB:
-                    img_info_for_pdf = st.session_state.get("img_res_for_pdf", None)
-                    pdf_bytes = generate_pdf_report(
-                        platform_saved,
-                        review_text_saved,
-                        res,
-                        stats,
-                        img_info_for_pdf
-                    )
-                    st.download_button(
-                        "📄 Download PDF Report",
-                        data=pdf_bytes,
-                        file_name="review_validator_report.pdf",
-                        mime="application/pdf",
-                    )
-                else:
-                    st.info("PDF report requires reportlab. Add `reportlab` to requirements.txt to enable export.")
-
-    # --- IMAGE TAB ---
-    with tab2:
-        col_in, col_view = st.columns([1, 1])
-
-        with col_in:
-            st.markdown("#### Step 1: Provide Image")
-            method = st.radio(
-                "Input Method",
-                ["Paste URL", "Upload File"],
-                horizontal=True,
-                label_visibility="collapsed"
-            )
-
-            with st.form("image_form"):
-                img_file = None
-                img_url = None
-
-                if method == "Paste URL":
-                    img_url = st.text_input("Paste Image Link:")
-                else:
-                    img_file = st.file_uploader("Upload Image", type=['jpg', 'jpeg', 'png'])
-
-                strict_img = st.checkbox("Use Strict AI Mode for Images", value=True)
-                submitted = st.form_submit_button("Scan Image", type="primary")
-
-                if submitted:
-                    target_img = None
-                    if method == "Paste URL" and img_url:
-                        target_img = get_image_from_url(img_url)
-                    elif method == "Upload File" and img_file:
-                        try:
-                            target_img = Image.open(img_file).convert("RGB")
-                        except Exception:
-                            target_img = None
-
-                    if target_img is None:
-                        st.error("Could not read image. Try another link or file.")
-                    else:
-                        with st.spinner("Scanning image..."):
-                            data = check_image(target_img, squad)
-                            st.session_state['img_res'] = (data, strict_img)
-                            st.session_state['current_img'] = target_img
-                            # store a simplified version for PDF report
-                            st.session_state['img_res_for_pdf'] = data
-
-        with col_view:
-            if 'current_img' in st.session_state:
-                st.image(
-                    st.session_state['current_img'],
-                    use_column_width=True,
-                    caption="Analyzed Image"
-                )
-
-            if 'img_res' in st.session_state:
-                data, strict_img = st.session_state['img_res']
-                ai_score = data['ai_chance']
-                caption = data['caption']
-
-                st.markdown("#### Step 2: Analysis Results")
-
-                st.markdown(f"""
-                <div class="analysis-box">
-                    <strong>👁️ Visual Caption (approx):</strong><br>
-                    <em>{caption}</em>
-                </div>
-                """, unsafe_allow_html=True)
-
-                st.write("")
-
-                if strict_img:
-                    t_high = 90
-                    t_mid = 70
-                else:
-                    t_high = 80
-                    t_mid = 60
-
-                if ai_score >= t_high:
-                    st.error(f"🤖 Very likely AI-generated ({ai_score:.0f}% AI score)")
-                elif ai_score >= t_mid:
-                    st.warning(f"🤔 Suspicious / possibly AI ({ai_score:.0f}% AI score)")
-                else:
-                    st.success(f"📸 Likely real photo ({100 - ai_score:.0f}% real score)")
-
-                st.markdown("**Detector Details:**")
-                st.progress(ai_score / 100.0, text=f"AI probability: {ai_score:.1f}%")
-
-                with st.expander("See raw detector scores"):
-                    st.write(f"Image AI Score (model): {ai_score:.1f}%")
-
-# --- MAIN CONTROLLER ---
-def main():
-    inject_custom_css()
-
-    if 'page' not in st.session_state:
-        st.session_state['page'] = 'landing'
-
-    with st.spinner("Loading AI models (first run can take some time)..."):
-        squad, err = load_ai_squad()
-
-    if squad is None:
-        st.error(err or "Failed to load models.")
-        st.stop()
-
-    warnings_text = None
-    if err:
-        warnings_text = "Some features may be limited:<br>" + err.replace("\n", "<br>")
-
-    if st.session_state['page'] == 'landing':
-        landing_page()
-    else:
-        detector_page(squad, warnings_text=warnings_text)
-
-if __name__ == "__main__":
-    main()
+                        <div class="stat-num" style="color:{color}">{bot_score:.0f}%