Update app.py

app.py

@@ -68,10 +68,8 @@ def detect_language(text):
 # Extract tone using Groq API (or fallback method)
 def extract_tone(text):
     try:
-        response = llm.chat([
-            {"role": "system", "content": "Analyze the tone of the following text and provide descriptive tone labels."},
-            {"role": "user", "content": text}
-        ])
+        response = llm.chat([{"role": "system", "content": "Analyze the tone of the following text and provide descriptive tone labels."},
+                             {"role": "user", "content": text}])
         return response["choices"][0]["message"]["content"].split(", ")
     except Exception as e:
         logging.error(f"Groq API error: {e}")
@@ -93,23 +91,34 @@ def extract_hashtags(text):
 # Extract frames using Groq API (or fallback)
 def extract_frames(text):
     try:
-        response = llm.chat([
-            {"role": "system", "content": "Classify the following text into relevant activism frames and assign Major, Significant, or Minor focus."},
-            {"role": "user", "content": text}
-        ])
-        return response["choices"][0]["message"]["content"]
+        response = llm.chat([{"role": "system", "content": "Classify the following text into relevant activism frames and assign Major, Significant, or Minor focus."},
+                             {"role": "user", "content": text}])
+        return categorize_frame_focus(response["choices"][0]["message"]["content"])
     except Exception as e:
         logging.error(f"Groq API error: {e}")
         return extract_frames_fallback(text)
 
+# Categorize frame focus: Major, Significant, Minor
+def categorize_frame_focus(frames_text):
+    frame_data = {}
+    frames = frames_text.split(", ")
+    for frame in frames:
+        if "Major" in frame:
+            frame_data[frame] = "Major Focus"
+        elif "Significant" in frame:
+            frame_data[frame] = "Significant Focus"
+        else:
+            frame_data[frame] = "Minor Mention"
+    return frame_data
+
 # Fallback method for frame extraction
 def extract_frames_fallback(text):
-    detected_frames = set()
+    detected_frames = {}
     text_lower = text.lower()
     for category, keywords in frame_categories.items():
         if any(word in text_lower for word in keywords):
-            detected_frames.add(category)
-    return list(detected_frames)
+            detected_frames[category] = "Minor Mention"
+    return detected_frames
 
 # Extract captions from DOCX
 def extract_captions_from_docx(docx_file):
@@ -125,23 +134,15 @@ def extract_captions_from_docx(docx_file):
             captions[current_post].append(text)
     return {post: " ".join(lines) for post, lines in captions.items() if lines}
 
-# Extract metadata from Excel file
-def extract_metadata_from_excel(excel_file):
-    try:
-        df = pd.read_excel(excel_file)
-        # Assuming the Excel sheet has columns: 'Post Number', 'Likes', 'Comments', 'Media Type'
-        metadata = df.set_index("Post Number").to_dict(orient="index")
-        return metadata
-    except Exception as e:
-        logging.error(f"Error reading Excel file: {e}")
-        return {}
-
-# Merge metadata from Excel with the generated data
-def merge_metadata_with_generated_data(generated_data, excel_metadata):
-    for post, metadata in excel_metadata.items():
-        if post in generated_data:
-            generated_data[post].update(metadata)
-    return generated_data
+# Generate DOCX file for download
+def generate_docx(data):
+    doc = Document()
+    for post, content in data.items():
+        doc.add_heading(post, level=1)
+        for key, value in content.items():
+            doc.add_paragraph(f"{key}: {value}")
+        doc.add_paragraph()  # Add space between posts
+    return doc
 
 # Streamlit app
 st.title("AI-Powered Activism Message Analyzer")
@@ -196,3 +197,16 @@ if uploaded_excel:
 # Display results
 if output_data:
     st.write(output_data)
+
+    # Generate DOCX for download
+    doc = generate_docx(output_data)
+    doc_io = io.BytesIO()
+    doc.save(doc_io)
+    doc_io.seek(0)
+
+    st.download_button(
+        label="Download Extracted Data",
+        data=doc_io,
+        file_name="extracted_data.docx",
+        mime="application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+    )