Update app.py

app.py

@@ -1,3 +1,4 @@
+import pandas as pd
 import streamlit as st
 import re
 import logging
@@ -122,20 +123,42 @@ 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
+
 # Streamlit app
 st.title("AI-Powered Activism Message Analyzer")
 
-st.write("Enter text or upload a DOCX file for analysis:")
+st.write("Enter text or upload a DOCX/Excel file for analysis:")
 
 # Text input
 input_text = st.text_area("Input Text", height=200)
 
-# File upload
-uploaded_file = st.file_uploader("Upload a DOCX file", type=["docx"])
+# File upload (DOCX)
+uploaded_docx = st.file_uploader("Upload a DOCX file", type=["docx"])
+
+# File upload (Excel)
+uploaded_excel = st.file_uploader("Upload an Excel file", type=["xlsx"])
 
 # Initialize output dictionary
 output_data = {}
 
+# Process Text Input
 if input_text:
     output_data["Manual Input"] = {
         "Full Caption": input_text,
@@ -146,8 +169,9 @@ if input_text:
     }
     st.success("Analysis completed for text input.")
 
-if uploaded_file:
-    captions = extract_captions_from_docx(uploaded_file)
+# Process DOCX file
+if uploaded_docx:
+    captions = extract_captions_from_docx(uploaded_docx)
     for caption, text in captions.items():
         output_data[caption] = {
             "Full Caption": text,
@@ -156,7 +180,16 @@ if uploaded_file:
             "Hashtags": extract_hashtags(text),
             "Frames": extract_frames(text),
         }
-    st.success(f"Analysis completed for {len(captions)} posts.")
+    st.success(f"Analysis completed for {len(captions)} posts from DOCX.")
+
+# Process Excel file
+if uploaded_excel:
+    excel_metadata = extract_metadata_from_excel(uploaded_excel)
+    st.success(f"Excel metadata extracted with {len(excel_metadata)} posts.")
+
+# Merge and display final data
+if uploaded_excel:
+    output_data = merge_metadata_with_generated_data(output_data, excel_metadata)
 
 # Display results
 if output_data: