Update app.py

app.py

@@ -23,6 +23,8 @@ import json
 import pandas as pd
 import numpy as np
 import altair as alt
+from GoogleNews import GoogleNews
+from newspaper import Article
 
 st.set_page_config(layout="wide")
 
@@ -420,6 +422,51 @@ elif activities=="News Sentiment":
     }}
 
     """
+
+    def get_google_news_documents(query: str, max_articles: int = 10):
+        """
+        Fetches news articles from Google News and returns a list of LangChain Document objects.
+    
+        Args:
+            query (str): Search query for Google News.
+            max_articles (int): Maximum number of articles to fetch and parse.
+    
+        Returns:
+            List[Document]: List of LangChain Document objects containing article content and metadata.
+        """
+        logging.info(f"Fetching articles for query: '{query}'")
+        googlenews = GoogleNews(lang="en")
+        googlenews.search(query)
+        articles = googlenews.result()
+    
+        documents = []
+        for article in articles[:max_articles]:
+            url = article.get("link")
+            try:
+                news_article = Article(url)
+                news_article.download()
+                news_article.parse()
+                content = news_article.text.strip()
+    
+                if content:
+                    doc = Document(
+                        page_content=content,
+                        metadata={
+                            "source": "Google News",
+                            "title": article.get("title", ""),
+                            "published": article.get("date", ""),
+                            "link": url,
+                        }
+                    )
+                    documents.append(doc)
+    
+            except Exception as e:
+                st.write(f"Failed to process article: {url} — Error: {e}")
+    
+        return documents
+
+    google_docs = get_google_news_documents("Indian Stock market news NSE, Stocks in Action, Stocks in News", max_articles=10)
+    docs.extend(google_docs)
     llm_prompt = PromptTemplate.from_template(llm_prompt_template)
 
     llm_chain = LLMChain(llm=llm,prompt=llm_prompt)