Update app2.py

app2.py

@@ -318,50 +318,67 @@ def fetch_detailed_content(url: str) -> str:
 
 def query_public_case_law(query: str) -> List[Dict[str, Any]]:
     """
-    Query publicly available case law databases and perform a web search to find related cases.
+    Query publicly available case law databases (Justia and CourtListener)
+    and perform a web search to find related cases.
     """
-    # Perform a web search to find relevant case law
-    search_url = f"https://www.google.com/search?q={query}+case+law+site:law.justia.com"
-    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'}
-    
+    cases = []
+
+    # --- Justia Search (Using BeautifulSoup) ---
+    justia_url = f"https://law.justia.com/cases/?q={query}"
+    justia_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'
+    }
     try:
-        response = requests.get(search_url, headers=headers)
-        response.raise_for_status()
-        soup = BeautifulSoup(response.text, 'html.parser')
-        
-        search_results = soup.find_all('div', class_='g')
-        cases = []
-        
-        for result in search_results[:5]:  # Limit to top 5 results
-            title_elem = result.find('h3', class_='r')
-            link_elem = result.find('a')
-            snippet_elem = result.find('div', class_='s')
-            
-            if title_elem and link_elem and snippet_elem:
-                title = title_elem.text
-                link = link_elem['href']
-                snippet = snippet_elem.text
-                
-                # Extract case name and citation from the title
-                case_info = title.split(' - ')
-                if len(case_info) >= 2:
-                    case_name = case_info[0]
-                    citation = case_info[1]
-                else:
-                    case_name = title
-                    citation = "Citation not found"
-                
-                cases.append({
-                    "case_name": case_name,
-                    "citation": citation,
-                    "summary": snippet,
-                    "url": link
-                })
-        
-        return cases
+        justia_response = requests.get(justia_url, headers=justia_headers)
+        justia_response.raise_for_status()
+        justia_soup = BeautifulSoup(justia_response.text, 'html.parser')
+        justia_results = justia_soup.find_all('div', class_='case-listing')
+
+        for result in justia_results[:3]:  # Limit Justia results to 3
+            title = result.find('h6').text.strip()
+            citation = result.find('p', class_='citation').text.strip()
+            summary = result.find('p', class_='summary').text.strip()
+            url = result.find('a')['href']
+            cases.append({
+                "source": "Justia",
+                "case_name": title,
+                "citation": citation,
+                "summary": summary,
+                "url": url
+            })
     except requests.RequestException as e:
-        print(f"Error querying case law: {e}")
-        return []
+        print(f"Error querying Justia: {e}")
+
+    # --- CourtListener Search (Using API) ---
+    courtlistener_url = f"https://www.courtlistener.com/api/rest/v3/search/?q={query}&type=o&format=json"
+    for attempt in range(3):  # Retry up to 3 times
+        try:
+            courtlistener_response = requests.get(courtlistener_url)
+            courtlistener_response.raise_for_status()
+            courtlistener_data = courtlistener_response.json()
+            break
+        except (requests.RequestException, ValueError) as e:
+            print(f"Attempt {attempt + 1} failed: {e}")
+            if attempt == 2:
+                print(
+                    f"Failed to retrieve or parse data from CourtListener: {e}"
+                )
+                break
+            time.sleep(2)
+
+    if 'results' in courtlistener_data:
+        for result in courtlistener_data['results'][:3]:  # Limit to 3 results
+            case_url = f"https://www.courtlistener.com{result['absolute_url']}"
+            cases.append({
+                "source": "CourtListener",
+                "case_name": result['caseName'],
+                "date_filed": result['dateFiled'],
+                "docket_number": result.get('docketNumber', 'Not available'),
+                "court": result['court'],
+                "url": case_url
+            })
+
+    return cases
 
 def comprehensive_document_analysis(content: str) -> Dict[str, Any]:
     """Performs a comprehensive analysis of the document, including web and Wikipedia searches."""
@@ -1551,8 +1568,8 @@ elif feature == "Case Precedent Finder":
         
         st.write("### Related Cases from Public Databases")
         for i, case in enumerate(precedents["public_cases"], 1):
-            st.write(f"**{i}. {case['case_name']} - {case['citation']}**")
-            st.write(f"Summary: {case['summary']}")
+            st.write(f"**{i}. {case['case_name']} ({case['source']}) - {case.get('citation', '')}**") # Display the source 
+            st.write(f"Summary: {case.get('summary', 'Not available')}")
             st.write(f"[Read full case]({case['url']})")
             st.write("---")