Update app.py

app.py

@@ -9,8 +9,9 @@ from streamlit_folium import st_folium
 from geopy.geocoders import Nominatim
 from geopy.exc import GeocoderTimedOut, GeocoderServiceError
 import time
+from folium.plugins import MarkerCluster  # 新增此行用於標記聚合
 
-# Function to set background image
+# 設定背景圖片的函數
 def set_background(png_file):
     with open(png_file, "rb") as f:
         data = f.read()
@@ -27,28 +28,30 @@ def set_background(png_file):
         unsafe_allow_html=True
     )
 
-# Set the background image
+# 設定背景圖片
 set_background('CAT.png')
 
-# Title of the app
+# App 的標題
 st.title("寵物醫院評分查詢")
 
-# User input for minimum rating
+# 用戶輸入的最低評分
 min_rating = st.slider("請輸入想查詢的最低評分:", 1.0, 5.0, 3.5)
 
-# List of URLs to scrape
+# 要爬取的 URL 列表
 urls = [
-    # (List of URLs)
+    "https://www.tw-animal.com/pet/171211/c000196.html",
+    "https://www.tw-animal.com/pet/171211/c000186.html",
+    # ... 其他 URL ...
 ]
 
-# Create an empty list to store the extracted data
+# 存放提取數據的空列表
 data_list = []
 
-# Initialize the geolocator
+# 初始化地理編碼器
 geolocator = Nominatim(user_agent="geoapiExercises")
-geocode_cache = {}  # Simple in-memory cache
+geocode_cache = {}  # 簡單的內存緩存
 
-# Function to geocode an address with retry logic and caching
+# 用於地理編碼地址的函數，帶有重試和緩存
 def geocode_address(address, retries=5, delay=5):
     if address in geocode_cache:
         return geocode_cache[address]
@@ -60,31 +63,28 @@ def geocode_address(address, retries=5, delay=5):
                 geocode_cache[address] = location
                 return location
         except (GeocoderTimedOut, GeocoderServiceError) as e:
-            st.warning(f"Geocoding error: {e}. Retrying...")
+            st.warning(f"地理編碼錯誤: {e}. 重試中...")
             time.sleep(delay)
-        except GeocoderServiceError as e:
-            st.error(f"Service error: {e}")
-            break
     
-    st.warning(f"Failed to geocode address: {address}")
+    st.warning(f"無法地理編碼地址: {address}")
     return None
 
-# Scrape data when the button is pressed
+# 當按下「開始爬取資料」按鈕時執行
 if st.button('開始爬取資料'):
     st.write("正在爬取資料，請稍候...")
     
-    # Loop through each URL and extract the data
+    # 迴圈遍歷每個 URL 並提取數據
     for url in urls:
         response = requests.get(url)
         soup = BeautifulSoup(response.content, 'html.parser')
 
-        # Extract data
+        # 提取數據
         title = soup.find('h1', class_='t-intro__title').get_text(strip=True)
         phone = soup.find('a', class_='t-font-large').get_text(strip=True)
         address = soup.find('a', class_='t-font-medium').get_text(strip=True)
         rating = float(soup.find('span', class_='t-intro__recommand').get_text(strip=True))
 
-        # Append the data to the list if rating meets the threshold
+        # 如果評分達到門檻，將數據添加到列表
         if rating >= min_rating:
             location = geocode_address(address)
             if location:
@@ -97,65 +97,50 @@ if st.button('開始爬取資料'):
                     "緯度": location.latitude
                 })
 
-    # If data was scraped successfully
+    # 如果成功爬取到數據
     if data_list:
         df1 = pd.DataFrame(data_list)
 
-        # Extract the region from the address (assuming region is part of the address)
+        # 從地址中提取區域（假設區域是地址的一部分）
         df1['區域'] = df1['地址'].apply(lambda x: x.split()[0])
 
-        # Group by region and merge hospitals in the same region
+        # 按區域分組，合併同區域的醫院
         grouped_df = df1.groupby('區域').agg({
             '標題': lambda x: ' | '.join(x),
             '手機': lambda x: ' | '.join(x),
             '地址': lambda x: ' | '.join(x),
-            '評分': 'mean'  # Aggregation for average rating
+            '評分': 'mean'  # 平均評分
         }).reset_index()
 
-        # Display the dataframe
+        # 顯示數據表格
         st.dataframe(df1)
 
-        # Display Plotly bar chart
+        # 顯示 Plotly 柱狀圖
         bar_fig = px.bar(grouped_df, x='區域', y='評分', title="各區域寵物醫院統計", labels={'評分':'平均評分', '區域':'區域'})
         st.plotly_chart(bar_fig)
 
-        # Display Plotly pie chart
+        # 顯示 Plotly 圓餅圖
         pie_fig = px.pie(grouped_df, names='區域', values='評分', title="各區域寵物醫院比例")
         st.plotly_chart(pie_fig)
 
-        # Display the map
+        # 顯示地圖
         if st.button('顯示地圖'):
-            # Create a folium map centered around the average location
+            # 創建一個 Folium 地圖，集中在平均位置
             map_center = [df1['緯度'].mean(), df1['經度'].mean()]
             pet_map = folium.Map(location=map_center, zoom_start=12)
 
-            # Add markers for each hospital
+            # 創建一個標記聚合器
+            marker_cluster = MarkerCluster().add_to(pet_map)
+
+            # 為每家醫院添加標記
             for index, row in df1.iterrows():
                 folium.Marker(
                     location=[row['緯度'], row['經度']],
                     popup=f"{row['標題']} (評分: {row['評分']})",
                     tooltip=row['標題']
-                ).add_to(pet_map)
+                ).add_to(marker_cluster)  # 添加到標記聚合器中
 
-            # Render the map using streamlit_folium
+            # 使用 streamlit_folium 渲染地圖
             st_folium(pet_map, width=700, height=500)
 
-        # Sending notification to LINE
-        if st.button('發送前五筆資料到Line'):
-            msg = df1[:5].to_string(index=False)
-
-            token = "E0yvdJqy8zwCCvBtMiR0j3CXNi9xZaXh8g1FrPBmv79"  # Replace with your LINE Notify token
-
-            # Send message to LINE
-            def send_line_notify(token, msg):
-                headers = {
-                    "Authorization": "Bearer " + token,
-                    "Content-Type": "application/x-www-form-urlencoded"
-                }
-                params = {"message": msg}
-                r = requests.post("https://notify-api.line.me/api/notify", headers=headers, params=params)
-
-            send_line_notify(token, msg)
-            st.success('資料已成功發送到 Line!')
-    else:
-        st.warning('沒有符合條件的資料。')
+