Update app2.py

app2.py

@@ -2,6 +2,9 @@ import streamlit as st
 import pandas as pd
 import plotly.express as px
 import requests
+from googleapiclient.discovery import build
+from googleapiclient.errors import HttpError
+from requests.exceptions import RequestException, ConnectionError, Timeout
 from ai71 import AI71
 import PyPDF2
 import io
@@ -18,7 +21,6 @@ import matplotlib.pyplot as plt
 from bs4 import BeautifulSoup, NavigableString, Tag
 from io import StringIO
 import wikipedia
-from googleapiclient.discovery import build
 from typing import List, Optional
 from httpx_sse import SSEError
 from difflib import SequenceMatcher
@@ -447,43 +449,59 @@ def safe_find(element, selector, class_=None, attr=None):
         return found.get(attr) if attr else found.text.strip()
     return "Not available"
 
-def search_web_duckduckgo(query: str, num_results: int = 3) -> List[Dict[str, str]]:
+def search_web_duckduckgo(query: str, num_results: int = 3, max_retries: int = 3) -> List[Dict[str, str]]:
     """
-    Performs a web search using the DuckDuckGo search engine.
+    Performs a web search using the Google Custom Search API.
     Returns a list of dictionaries containing search result title, link, and snippet.
     """
-    base_url = "https://html.duckduckgo.com/html/"
-    params = {
-        'q': query,
-        's': '0',
-        'dc': '20',
-        'o': 'json',
-        'api': '/d.js'
-    }
-    headers = {
-        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
-    }
+    api_key = "AIzaSyD-1OMuZ0CxGAek0PaXrzHOmcDWFvZQtm8"
+    cse_id = "877170db56f5c4629"
 
-    try:
-        response = requests.get(base_url, params=params, headers=headers, timeout=10)
-        response.raise_for_status()
-        soup = BeautifulSoup(response.content, 'html.parser')
-        
-        results = []
-        for result in soup.find_all('div', class_='result')[:num_results]:
-            title = result.find('a', class_='result__a').text.strip()
-            link = result.find('a', class_='result__a')['href']
-            snippet = result.find('a', class_='result__snippet').text.strip()
-            results.append({
-                'title': title,
-                'link': link,
-                'snippet': snippet
-            })
-        
-        return results
-    except requests.RequestException as e:
-        print(f"Error fetching web search results: {e}")
-        return []
+    user_agents = [
+        'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
+        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.0 Safari/605.1.15',
+        'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.101 Safari/537.36'
+    ]
+
+    for attempt in range(max_retries):
+        try:
+            headers = {'User-Agent': random.choice(user_agents)}
+            
+            service = build("customsearch", "v1", developerKey=api_key)
+
+            # Execute the search request
+            res = service.cse().list(q=query, cx=cse_id, num=num_results).execute()
+
+            results = []
+            if "items" in res:
+                for item in res["items"]:
+                    result = {
+                        "title": item["title"],
+                        "link": item["link"],
+                        "snippet": item.get("snippet", "")
+                    }
+                    results.append(result)
+                    if len(results) == num_results:
+                        break
+
+            return results
+
+        except HttpError as e:
+            print(f"HTTP error occurred: {e}. Attempt {attempt + 1} of {max_retries}")
+        except ConnectionError as e:
+            print(f"Connection error occurred: {e}. Attempt {attempt + 1} of {max_retries}")
+        except Timeout as e:
+            print(f"Timeout error occurred: {e}. Attempt {attempt + 1} of {max_retries}")
+        except RequestException as e:
+            print(f"An error occurred during the request: {e}. Attempt {attempt + 1} of {max_retries}")
+        except Exception as e:
+            print(f"An unexpected error occurred: {e}. Attempt {attempt + 1} of {max_retries}")
+
+        # Exponential backoff
+        time.sleep(2 ** attempt)
+
+    print("Max retries reached. No results found.")
+    return []
 
 def estimate_legal_costs(case_type: str, complexity: str, state: str) -> Dict[str, Any]:
     """