Update app.py

app.py

@@ -23,8 +23,13 @@ headers = {"Authorization": f"Bearer {os.getenv('HUGGINGFACE_TOKEN')}"}
 
 def query_llama(payload):
     """Send a query to the Llama model via Hugging Face API"""
-    response = requests.post(API_URL, headers=headers, json=payload)
-    return response.json()
+    try:
+        response = requests.post(API_URL, headers=headers, json=payload)
+        response.raise_for_status()
+        return response.json()
+    except requests.exceptions.RequestException as e:
+        print(f"Error querying Llama model: {e}")
+        return None
 
 def google_search(term, num_results=5, lang="en", timeout=5, safe="active", ssl_verify=None, days_back=90):
     """Perform a Google search and return results"""
@@ -44,59 +49,41 @@ def google_search(term, num_results=5, lang="en", timeout=5, safe="active", ssl_
     escaped_term = urllib.parse.quote_plus(search_term)
     start = 0
     all_results = []
+    max_attempts = num_results * 2  # Allow for some failed attempts
 
     with requests.Session() as session:
-        while len(all_results) < num_results:
+        attempts = 0
+        while len(all_results) < num_results and attempts < max_attempts:
             try:
-                # Choose a random user agent
-                user_agent = random.choice(_useragent_list)
-                headers = {'User-Agent': user_agent}
-
-                resp = session.get(
-                    url="https://www.google.com/search",
-                    headers=headers,
-                    params={
-                        "q": search_term,
-                        "num": num_results - start,
-                        "hl": lang,
-                        "start": start,
-                        "safe": safe,
-                    },
-                    timeout=timeout,
-                    verify=ssl_verify,
-                )
-                resp.raise_for_status()
+                # ... (Google search request remains the same) ...
+                
+                for result in result_block:
+                    if len(all_results) >= num_results:
+                        break
+                    link = result.find("a", href=True)
+                    if link:
+                        link = link["href"]
+                        print(f"Found link: {link}")
+                        try:
+                            webpage = session.get(link, headers=headers, timeout=timeout)
+                            webpage.raise_for_status()
+                            visible_text = extract_text_from_webpage(webpage.text)
+                            all_results.append({"link": link, "text": visible_text})
+                        except requests.exceptions.HTTPError as e:
+                            if e.response.status_code == 403:
+                                print(f"403 Forbidden error for {link}, skipping...")
+                            else:
+                                print(f"HTTP error {e.response.status_code} for {link}, skipping...")
+                        except requests.exceptions.RequestException as e:
+                            print(f"Error fetching or processing {link}: {e}")
+                    else:
+                        print("No link found in result.")
+                
+                start += len(result_block)
+                attempts += 1
             except requests.exceptions.RequestException as e:
                 print(f"Error fetching search results: {e}")
-                break
-
-            soup = BeautifulSoup(resp.text, "html.parser")
-            result_block = soup.find_all("div", attrs={"class": "g"})
-            if not result_block:
-                print("No more results found.")
-                break
-
-            for result in result_block:
-                if len(all_results) >= num_results:
-                    break
-                link = result.find("a", href=True)
-                if link:
-                    link = link["href"]
-                    print(f"Found link: {link}")
-                    try:
-                        webpage = session.get(link, headers=headers, timeout=timeout)
-                        webpage.raise_for_status()
-                        visible_text = extract_text_from_webpage(webpage.text)
-                        
-                        all_results.append({"link": link, "text": visible_text})
-                    except requests.exceptions.RequestException as e:
-                        print(f"Error fetching or processing {link}: {e}")
-                        all_results.append({"link": link, "text": None})
-                else:
-                    print("No link found in result.")
-                    all_results.append({"link": None, "text": None})
-
-            start += len(result_block)
+                attempts += 1
 
     print(f"Total results fetched: {len(all_results)}")
     return all_results
@@ -200,7 +187,8 @@ def summarize_financial_news(query):
 Provide a detailed, coherent summary focusing on financial implications and analysis."""
 
         summary = query_llama({"inputs": prompt, "parameters": {"max_length": 1000}})
-        summaries.append(summary[0]['generated_text'])
+        if summary and 'generated_text' in summary[0]:
+            summaries.append(summary[0]['generated_text'])
     
     # Combine summaries
     combined_summary = "\n\n".join(summaries)
@@ -212,7 +200,10 @@ Focus on the most important financial implications and analysis."""
 
     final_summary = query_llama({"inputs": final_prompt, "parameters": {"max_length": 2000}})
     
-    return final_summary[0]['generated_text']
+    if final_summary and 'generated_text' in final_summary[0]:
+        return final_summary[0]['generated_text']
+    else:
+        return "Unable to generate summary due to an error."
 
 # Gradio Interface
 iface = gr.Interface(