Update app.py

app.py

@@ -2,9 +2,12 @@ import json
 import streamlit as st
 from google.oauth2 import service_account
 from google.cloud import language_v1
+import urllib.parse
+import urllib.request
 import pandas as pd
 
-# Function to generate Google Search link for MID
+
+# Function to query Google's Knowledge Graph API
 def query_knowledge_graph(entity_id):
     try:
         google_search_link = f"https://www.google.com/search?kgmid={entity_id}"
@@ -12,28 +15,28 @@ def query_knowledge_graph(entity_id):
     except Exception as e:
         st.write(f"An error occurred: {e}")
 
-# Function to serialize metadata
+# Function to count entities with 'mid' that contains '/g/' or '/m/' in their metadata
+def count_entities(entities):
+    count = 0
+    for entity in entities:
+        metadata = entity.metadata
+        if 'mid' in metadata and ('/g/' in metadata['mid'] or '/m/' in metadata['mid']):
+            count += 1
+    return count
+
+# Function to serialize entity metadata
 def serialize_entity_metadata(metadata):
     return {k: str(v) for k, v in metadata.items()}
 
-# Count Google Entities (those with /g/ or /m/ mids)
-def count_google_entities(entities):
-    return sum(
-        1 for entity in entities
-        if 'mid' in entity.metadata and ('/g/' in entity.metadata['mid'] or '/m/' in entity.metadata['mid'])
-    )
-
-# Export all entities, regardless of mid
+# Function to export all entities, including those without metadata
 def export_entities(entities):
     entity_list = []
     for entity in entities:
         metadata = serialize_entity_metadata(entity.metadata) if entity.metadata else {}
-        mid = metadata.get('mid', '')
         entity_info = {
             "Name": entity.name,
             "Type": language_v1.Entity.Type(entity.type_).name,
             "Salience Score": entity.salience,
-            "MID": mid,
             "Metadata": metadata,
             "Mentions": [mention.text.content for mention in entity.mentions]
         }
@@ -44,27 +47,33 @@ def export_entities(entities):
         return
 
     df = pd.DataFrame(entity_list)
-    st.download_button(label="Export Entities as CSV", data=df.to_csv(index=False), file_name="entities.csv", mime="text/csv")
 
+    # Export as CSV
+    csv = df.to_csv(index=False)
+    st.download_button(label="Export Entities as CSV", data=csv, file_name="entities.csv", mime="text/csv")
+
+    # Export as JSON
     json_data = json.dumps(entity_list, indent=2)
     st.download_button(label="Export Entities as JSON", data=json_data, file_name="entities.json", mime="application/json")
 
-# Sidebar
+# Sidebar content
 st.sidebar.title("About This Tool")
-st.sidebar.markdown("This tool uses Google Cloud Natural Language API to identify entities.")
-st.sidebar.markdown("### How to Use")
+st.sidebar.markdown("This tool leverages Google's NLP technology for entity analysis.")
+st.sidebar.markdown("### Step-by-Step Guide")
 st.sidebar.markdown("""
-1. **Enter text** in the box below.
-2. **Click Analyze** to detect entities.
-3. **Export** results to CSV or JSON.
+1. **Open the Tool**: Navigate to the URL where the tool is hosted.
+2. **User Input**: Enter the text you want to analyze.
+3. **Analyze**: Click the 'Analyze' button.
+4. **View Results**: See the identified entities and their details.
+5. **Export Entities**: Export the entities as JSON or CSV.
 """)
 
-# Header
+# Header and intro
 st.title("Google Cloud NLP Entity Analyzer")
-st.write("Analyze text and extract all entities, including those without Google metadata (MID).")
+st.write("This tool analyzes text to identify entities such as people, locations, organizations, and events.")
+st.write("Entity salience scores are always relative to the analyzed text.")
 
-# NLP Analysis Logic
-def analyze_entities(text_content):
+def sample_analyze_entities(text_content):
     service_account_info = json.loads(st.secrets["google_nlp"])
     credentials = service_account.Credentials.from_service_account_info(
         service_account_info, scopes=["https://www.googleapis.com/auth/cloud-platform"]
@@ -75,46 +84,50 @@ def analyze_entities(text_content):
     encoding_type = language_v1.EncodingType.UTF8
 
     response = client.analyze_entities(request={"document": document, "encoding_type": encoding_type})
-    entities = response.entities
-
-    total_entities = len(entities)
-    google_entities = count_google_entities(entities)
+    
+    # Count the entities with 'mid' and either '/g/' or '/m/' in their metadata
+    entity_count = count_entities(response.entities)
 
-    if google_entities == 0:
-        st.markdown(f"### Found {total_entities} entities — no Google-linked (MID) entities found.")
+    if entity_count == 0:
+        st.markdown(f"# We found {len(response.entities)} entities - but found no Google Entities")
+        st.write("---")
+    elif entity_count == 1:
+        st.markdown(f"# We found {len(response.entities)} entities - and found 1 Google Entity")
+        st.write("---")
     else:
-        st.markdown(f"### Found {total_entities} entities — {google_entities} Google-linked entities with MID.")
+        st.markdown(f"# We found {len(response.entities)} entities - and found {entity_count} Google Entities")
+        st.write("---")
 
-    st.write("---")
 
-    for i, entity in enumerate(entities):
-        st.write(f"**Entity {i+1} of {total_entities}**")
-        st.write(f"**Name:** {entity.name}")
-        st.write(f"**Type:** {language_v1.Entity.Type(entity.type_).name}")
-        st.write(f"**Salience Score:** {entity.salience:.4f}")
+    for i, entity in enumerate(response.entities):
+        st.write(f"Entity {i+1} of {len(response.entities)}")
+        st.write(f"Name: {entity.name}")
+        st.write(f"Type: {language_v1.Entity.Type(entity.type_).name}")
+        st.write(f"Salience Score: {entity.salience}")
 
         if entity.metadata:
-            st.write("**Metadata:**")
-            st.json(entity.metadata)
-
+            st.write("Metadata:")
+            st.write(entity.metadata)
+            
             if 'mid' in entity.metadata and ('/g/' in entity.metadata['mid'] or '/m/' in entity.metadata['mid']):
-                query_knowledge_graph(entity.metadata['mid'])
-        else:
-            st.write("_No metadata available_")
+                entity_id = entity.metadata['mid']
+                query_knowledge_graph(entity_id)
 
         if entity.mentions:
-            st.write(f"**Mentions ({len(entity.mentions)}):**")
-            st.write([mention.text.content for mention in entity.mentions])
+            mention_count = len(entity.mentions)
+            plural = "s" if mention_count > 1 else ""
+            st.write(f"Mentions: {mention_count} mention{plural}")
+            st.write("Raw Array:")
+            st.write(entity.mentions)
 
         st.write("---")
 
-    export_entities(entities)
+    # Add the export functionality
+    export_entities(response.entities)
 
-# Text Input
+# User input for text analysis
 user_input = st.text_area("Enter text to analyze")
 
 if st.button("Analyze"):
-    if user_input.strip():
-        analyze_entities(user_input)
-    else:
-        st.warning("Please enter some text before clicking Analyze.")
+    if user_input:
+        sample_analyze_entities(user_input)