Update app2.py

app2.py

@@ -1556,6 +1556,222 @@ def automated_legal_brief_generation_ui():
             file_name="legal_brief.txt",
             mime="text/plain"
         )
+
+STATES = [
+    "Alabama", "Alaska", "Arizona", "Arkansas", "California", "Colorado", "Connecticut", "Delaware", "Florida", "Georgia",
+    "Hawaii", "Idaho", "Illinois", "Indiana", "Iowa", "Kansas", "Kentucky", "Louisiana", "Maine", "Maryland",
+    "Massachusetts", "Michigan", "Minnesota", "Mississippi", "Missouri", "Montana", "Nebraska", "Nevada", "New Hampshire", "New Jersey",
+    "New Mexico", "New York", "North Carolina", "North Dakota", "Ohio", "Oklahoma", "Oregon", "Pennsylvania", "Rhode Island", "South Carolina",
+    "South Dakota", "Tennessee", "Texas", "Utah", "Vermont", "Virginia", "Washington", "West Virginia", "Wisconsin", "Wyoming"
+]
+
+CITIES_BY_STATE = {
+    "Alabama": ["Birmingham", "Montgomery", "Mobile", "Huntsville"],
+    "Alaska": ["Anchorage", "Fairbanks", "Juneau"],
+    "Arizona": ["Phoenix", "Tucson", "Mesa", "Chandler"],
+    "Arkansas": ["Little Rock", "Fort Smith", "Fayetteville"],
+    "California": ["Los Angeles", "San Francisco", "San Diego", "San Jose"],
+    "Colorado": ["Denver", "Colorado Springs", "Aurora", "Fort Collins"],
+    "Connecticut": ["Bridgeport", "New Haven", "Hartford", "Stamford"],
+    "Delaware": ["Wilmington", "Dover", "Newark"],
+    "Florida": ["Miami", "Orlando", "Jacksonville", "Tampa"],
+    "Georgia": ["Atlanta", "Augusta", "Columbus", "Savannah"],
+    "Hawaii": ["Honolulu", "Hilo", "Kailua"],
+    "Idaho": ["Boise", "Nampa", "Meridian"],
+    "Illinois": ["Chicago", "Aurora", "Rockford", "Joliet"],
+    "Indiana": ["Indianapolis", "Fort Wayne", "Evansville"],
+    "Iowa": ["Des Moines", "Cedar Rapids", "Davenport"],
+    "Kansas": ["Wichita", "Overland Park", "Kansas City"],
+    "Kentucky": ["Louisville", "Lexington", "Bowling Green"],
+    "Louisiana": ["New Orleans", "Baton Rouge", "Shreveport"],
+    "Maine": ["Portland", "Lewiston", "Bangor"],
+    "Maryland": ["Baltimore", "Columbia", "Annapolis"],
+    "Massachusetts": ["Boston", "Worcester", "Springfield"],
+    "Michigan": ["Detroit", "Grand Rapids", "Ann Arbor"],
+    "Minnesota": ["Minneapolis", "St. Paul", "Rochester"],
+    "Mississippi": ["Jackson", "Gulfport", "Southaven"],
+    "Missouri": ["Kansas City", "St. Louis", "Springfield"],
+    "Montana": ["Billings", "Missoula", "Great Falls"],
+    "Nebraska": ["Omaha", "Lincoln", "Bellevue"],
+    "Nevada": ["Las Vegas", "Reno", "Henderson"],
+    "New Hampshire": ["Manchester", "Nashua", "Concord"],
+    "New Jersey": ["Newark", "Jersey City", "Paterson"],
+    "New Mexico": ["Albuquerque", "Las Cruces", "Santa Fe"],
+    "New York": ["New York City", "Buffalo", "Rochester", "Syracuse"],
+    "North Carolina": ["Charlotte", "Raleigh", "Greensboro"],
+    "North Dakota": ["Fargo", "Bismarck", "Grand Forks"],
+    "Ohio": ["Columbus", "Cleveland", "Cincinnati"],
+    "Oklahoma": ["Oklahoma City", "Tulsa", "Norman"],
+    "Oregon": ["Portland", "Eugene", "Salem"],
+    "Pennsylvania": ["Philadelphia", "Pittsburgh", "Allentown"],
+    "Rhode Island": ["Providence", "Warwick", "Cranston"],
+    "South Carolina": ["Charleston", "Columbia", "North Charleston"],
+    "South Dakota": ["Sioux Falls", "Rapid City", "Aberdeen"],
+    "Tennessee": ["Nashville", "Memphis", "Knoxville"],
+    "Texas": ["Houston", "Dallas", "Austin", "San Antonio"],
+    "Utah": ["Salt Lake City", "West Valley City", "Provo"],
+    "Vermont": ["Burlington", "South Burlington", "Rutland"],
+    "Virginia": ["Virginia Beach", "Norfolk", "Chesapeake"],
+    "Washington": ["Seattle", "Spokane", "Tacoma"],
+    "West Virginia": ["Charleston", "Huntington", "Morgantown"],
+    "Wisconsin": ["Milwaukee", "Madison", "Green Bay"],
+    "Wyoming": ["Cheyenne", "Casper", "Laramie"]
+}
+
+def find_lawyers(state, city, pages=1):
+    base_url = "https://www.justia.com/lawyers/"
+    url = f"{base_url}{state.lower()}/{city.lower().replace(' ', '-')}"
+    
+    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'
+    }
+    
+    names = []
+    short_bios = []
+    specializations = []
+    universities = []
+    addresses = []
+    phones = []
+    email_links = []
+    site_links = []
+    
+    try:
+        for page in range(1, pages + 1):
+            page_url = f"{url}?page={page}"
+            response = requests.get(page_url, headers=headers)
+            response.raise_for_status()
+            
+            soup = BeautifulSoup(response.content, 'html.parser')
+            results = soup.find_all('div', {'data-vars-action': 'OrganicListing'})
+            
+            for result in results:
+                # Name
+                try:
+                    names.append(result.find('strong', {'class': 'lawyer-name'}).get_text().strip())
+                except:
+                    names.append('')
+                
+                # Short Bio
+                try:
+                    short_bios.append(result.find('div', {'class': 'lawyer-expl'}).get_text().strip())
+                except:
+                    short_bios.append('')
+                
+                # Specialization
+                try:
+                    specializations.append(result.find('span', {'class': '-practices'}).get_text().strip())
+                except:
+                    specializations.append('')
+                
+                # University
+                try:
+                    universities.append(result.find('span', {'class': '-law-schools'}).get_text().strip())
+                except:
+                    universities.append('')
+                
+                # Address
+                try:
+                    addresses.append(result.find('span', {'class': '-address'}).get_text().strip().replace("\t", '').replace('\n', ', '))
+                except:
+                    addresses.append('')
+                
+                # Phone
+                try:
+                    phones.append(result.find('strong', {'class': '-phone'}).get_text().strip())
+                except:
+                    phones.append('')
+                
+                # Email Link
+                try:
+                    email_links.append(result.find('a', {'class': '-email'}).get('href'))
+                except:
+                    email_links.append('')
+                
+                # Site Link
+                try:
+                    site_links.append(result.find('a', {'class': '-website'}).get('href'))
+                except:
+                    site_links.append('')
+        
+        df_lawyers = pd.DataFrame({
+            'lawyer_name': names,
+            'short_bio': short_bios,
+            'specialization': specializations,
+            'university': universities,
+            'address': addresses,
+            'phone': phones,
+            'email_link': email_links,
+            'site_link': site_links
+        })
+        
+        return df_lawyers
+    
+    except requests.RequestException as e:
+        st.error(f"An error occurred while fetching lawyer information: {str(e)}")
+        return pd.DataFrame()
+
+def lawyer_finder_ui():
+    st.title("Find Lawyers in Your Area")
+    
+    col1, col2 = st.columns(2)
+    with col1:
+        state = st.selectbox("Select a State:", STATES)
+    
+    with col2:
+        cities = CITIES_BY_STATE.get(state, [])
+        city = st.selectbox("Select a City:", cities)
+    
+    if not city:
+        st.warning("Please select a city to continue.")
+        return
+    
+    pages = st.slider("Number of pages to scrape", 1, 20, 1)
+    
+    if st.button("Find Lawyers", type="primary"):
+        with st.spinner("Searching for lawyers in your area..."):
+            df_lawyers = find_lawyers(state, city, pages)
+            
+            if not df_lawyers.empty:
+                st.success(f"Found {len(df_lawyers)} lawyers in {city}, {state}.")
+                
+                # Display results in a more visually appealing way
+                st.subheader("Lawyer Directory")
+                for i in range(0, len(df_lawyers), 3):
+                    cols = st.columns(3)
+                    for j in range(3):
+                        if i + j < len(df_lawyers):
+                            lawyer = df_lawyers.iloc[i + j]
+                            with cols[j]:
+                                st.markdown(f"**{lawyer['lawyer_name']}**")
+                                st.markdown(f"*{lawyer['specialization']}*")
+                                if lawyer['phone']:
+                                    st.markdown(f"📞 {lawyer['phone']}")
+                                if lawyer['email_link']:
+                                    st.markdown(f"📧 [Email]({lawyer['email_link']})")
+                                if lawyer['site_link']:
+                                    st.markdown(f"🌐 [Website]({lawyer['site_link']})")
+                                st.markdown("---")
+                
+                # Show CSV preview with vertical and horizontal scrolling
+                st.subheader("Data Preview")
+                st.dataframe(
+                    df_lawyers,
+                    height=400,
+                    width=600,
+                    use_container_width=True,
+                )
+                
+                # Provide CSV download option
+                csv = df_lawyers.to_csv(index=False)
+                st.download_button(
+                    label="Download complete data as CSV",
+                    data=csv,
+                    file_name="lawyers_data.csv",
+                    mime="text/csv",
+                )
+            else:
+                st.warning(f"No lawyers found in {city}, {state}. Try selecting a different city or state.")
+
 # --- Streamlit App ---
 st.markdown("""
 <style>
@@ -1608,7 +1824,7 @@ with st.sidebar:
     
     feature = st.selectbox(
         "Select a feature",
-        ["Legal Chatbot", "Document Analysis", "Case Precedent Finder", "Legal Cost Estimator", "Contract Analysis", "Case Trend Visualizer", "Case Information Retrieval", "Automated Legal Brief Generation"]
+        ["Legal Chatbot", "Document Analysis", "Case Precedent Finder", "Legal Cost Estimator", "Contract Analysis", "Case Trend Visualizer", "Case Information Retrieval", "Automated Legal Brief Generation", "Find the Lawyers"]
     )
 if feature == "Legal Chatbot":
     st.subheader("Legal Chatbot")
@@ -1770,6 +1986,9 @@ elif feature == "Case Information Retrieval":
 elif feature == "Automated Legal Brief Generation":
     automated_legal_brief_generation_ui()
 
+elif feature == "Find the Lawyers":
+    lawyer_finder_ui()
+
 st.markdown("---")
 st.markdown(
     """