Update app.py

app.py

@@ -3,6 +3,7 @@ from bs4 import BeautifulSoup
 import pandas as pd
 import plotly.graph_objects as go
 import streamlit as st
+from geopy.geocoders import Nominatim  # New import for geocoding
 
 # 設定應用標題
 st.title("餐廳資料抓取與分析")
@@ -17,32 +18,41 @@ urls = urls_df['網址'].tolist()
 # 初始化一個空的 DataFrame 列表來儲存所有資料
 df_list = []
 
+# 初始化地理定位器
+geolocator = Nominatim(user_agent="restaurant_locator")  # Initialize geolocator
+
 # 迭代每個網址並抓取資料
 for url in urls:
-    try:
-        response = requests.get(url)
-        response.raise_for_status()  # Raises an HTTPError for bad responses
-        soup = BeautifulSoup(response.content, 'html.parser')
-
-        # 解析並抓取所需資料
-        title_tag = soup.find('h1', class_='restaurant-details__heading--title')
-        title = title_tag.text.strip() if title_tag else 'N/A'
-        
-        address_tag = soup.find('li', class_='restaurant-details__heading--address')
-        address = address_tag.text.strip() if address_tag else 'N/A'
-        
-        phone_tag = soup.find('a', {'data-event': 'CTA_tel'})
-        phone = phone_tag['href'].replace('tel:', '') if phone_tag else 'N/A'
-        
-        description_tag = soup.find('div', class_='restaurant-details__description--text')
-        description = description_tag.text.strip() if description_tag else 'N/A'
-
-        # 將抓取的資料新增到列表中
-        df_list.append({'Title': title, 'Address': address, 'Phone': phone, 'Description': description})
-
-    except requests.exceptions.HTTPError as e:
-        print(f"HTTP error occurred for URL {url}: {e}")
-        continue  # Skip to the next URL if there's an error
+    response = requests.get(url)
+    soup = BeautifulSoup(response.content, 'html.parser')
+
+    # 解析並抓取所需資料
+    title_tag = soup.find('h1', class_='restaurant-details__heading--title')
+    title = title_tag.text.strip() if title_tag else 'N/A'
+    
+    address_tag = soup.find('li', class_='restaurant-details__heading--address')
+    address = address_tag.text.strip() if address_tag else 'N/A'
+    
+    phone_tag = soup.find('a', {'data-event': 'CTA_tel'})
+    phone = phone_tag['href'].replace('tel:', '') if phone_tag else 'N/A'
+    
+    description_tag = soup.find('div', class_='restaurant-details__description--text')
+    description = description_tag.text.strip() if description_tag else 'N/A'
+
+    # Geocode address to get latitude and longitude
+    location = geolocator.geocode(address) if address != 'N/A' else None
+    lat = location.latitude if location else None
+    lon = location.longitude if location else None
+
+    # 將抓取的資料新增到列表中
+    df_list.append({
+        'Title': title,
+        'Address': address,
+        'Phone': phone,
+        'Description': description,
+        'Latitude': lat,
+        'Longitude': lon
+    })
 
 # 使用 pd.DataFrame() 將所有資料合併成一個 DataFrame
 df = pd.DataFrame(df_list)
@@ -69,3 +79,11 @@ fig_pie.update_layout(title='每個區的商家數量比例')
 # 按鈕來顯示圓餅圖
 if st.button('顯示每個區的商家數量比例圓餅圖'):
     st.plotly_chart(fig_pie)
+
+# 顯示地圖
+st.subheader("餐廳地圖")
+# Drop rows with missing coordinates
+df_map = df.dropna(subset=['Latitude', 'Longitude'])
+
+# 顯示地圖
+st.map(df_map[['Latitude', 'Longitude']])