updated

main.py

@@ -0,0 +1,80 @@
+import streamlit as st
+import requests
+
+BASE_URL = "https://jatin7237-news-app.hf.space"  # Replace with your API's public URL
+
+# App title and description
+st.title("Company Sentiment Analysis")
+st.write("Analyze company news articles for sentiment, topics, and summaries using the FastAPI app.")
+
+# Input company name
+company_name = st.text_input("Enter the company name:", placeholder="Example: Microsoft, Apple, Tesla")
+# Generate summary button
+if st.button("Generate Summary"):
+    if company_name:
+        try:
+            # Call the /generateSummary endpoint
+            summary_url = f"{BASE_URL}/generateSummary"
+            response = requests.post(summary_url, json={"company_name": company_name})
+            
+            if response.status_code == 200:
+                data = response.json()
+                
+                # Display the output
+                st.subheader("Company:")
+                st.write(data.get("Company", "Unknown"))
+
+                st.subheader("Articles:")
+                articles = data.get("Articles", [])
+                for i, article in enumerate(articles, start=1):
+                    st.write(f"**Article {i}:**")
+                    st.write(f"Title: {article['Title']}")
+                    st.write(f"Summary: {article['Summary']}")
+                    st.write(f"Sentiment: {article['Sentiment']}")
+                    st.write(f"Score: {article['Score']}")
+                    st.write(f"Topics: {', '.join(article['Topics'])}")
+
+                st.subheader("Comparative Sentiment Score:")
+                st.write(data.get("Comparative Sentiment Score", {}))
+
+                st.subheader("Final Sentiment Analysis:")
+                st.write(data.get("Final Sentiment Analysis", "No sentiment analysis available."))
+
+                st.subheader("Hindi Summary:")
+                st.write(data.get("Hindi Summary", "No Hindi summary available."))
+
+            else:
+                st.error(f"Error: {response.status_code}, {response.text}")
+
+        except Exception as e:
+            st.error(f"An error occurred: {e}")
+    else:
+        st.warning("Please enter a company name.")
+
+# Download JSON file
+if st.button("Download JSON File"):
+    json_url = f"{BASE_URL}/downloadJson"
+    try:
+        response = requests.get(json_url)
+        if response.status_code == 200:
+            with open("final_summary.json", "wb") as f:
+                f.write(response.content)
+            st.success("JSON file downloaded successfully!")
+        else:
+            st.error(f"Error: {response.status_code}, {response.text}")
+    except Exception as e:
+        st.error(f"An error occurred: {e}")
+
+# Download Hindi audio file
+if st.button("Download Hindi Audio"):
+    audio_url = f"{BASE_URL}/downloadHindiAudio"
+    try:
+        response = requests.get(audio_url)
+        if response.status_code == 200:
+            with open("hindi_summary.mp3", "wb") as f:
+                f.write(response.content)
+            st.success("Hindi audio file downloaded successfully!")
+        else:
+            st.error(f"Error: {response.status_code}, {response.text}")
+    except Exception as e:
+        st.error(f"An error occurred: {e}")

utils.py

@@ -76,25 +76,25 @@ def perform_sentiment_analysis(news_data):
     return news_data, sentiment_counts
 
 # def extract_topics_with_hf(news_data):
-    # structured_data = {
-    #     "Company": news_data.get("Company", "Unknown"),
-    #     "Articles": []
-    # }
-    # topic_pipe = pipeline("text-classification", model="valurank/distilroberta-topic-classification",device=1)
-    # articles = news_data.get("Articles", [])
-    # for article in articles:
-    #     content = f"{article['Title']} {article['Summary']}"
-    #     topics_result = topic_pipe(content, top_k=3)
-    #     topics = [topic["label"] for topic in topics_result] if topics_result else ["Unknown"]
-
-    #     structured_data["Articles"].append({
-    #         "Title": article["Title"],
-    #         "Summary": article["Summary"],
-    #         "Sentiment": article.get("Sentiment", "Unknown"),
-    #         "Score": article.get("Score", 0.0),
-    #         "Topics": topics
-    #     })
-    # return structured_data
+#     structured_data = {
+#         "Company": news_data.get("Company", "Unknown"),
+#         "Articles": []
+#     }
+#     topic_pipe = pipeline("text-classification", model="valurank/distilroberta-topic-classification",device=1)
+#     articles = news_data.get("Articles", [])
+#     for article in articles:
+#         content = f"{article['Title']} {article['Summary']}"
+#         topics_result = topic_pipe(content, top_k=3)
+#         topics = [topic["label"] for topic in topics_result] if topics_result else ["Unknown"]
+
+#         structured_data["Articles"].append({
+#             "Title": article["Title"],
+#             "Summary": article["Summary"],
+#             "Sentiment": article.get("Sentiment", "Unknown"),
+#             "Score": article.get("Score", 0.0),
+#             "Topics": topics
+#         })
+#     return structured_data
 
 def extract_topics_with_hf(news_data):
     structured_data = {