Update app.py

app.py

@@ -4,6 +4,8 @@ from bs4 import BeautifulSoup
 import pandas as pd
 from google.oauth2.service_account import Credentials
 import gspread
+import plotly.express as px
+import plotly.graph_objects as go
 
 # Google Sheets credentials
 SCOPE = ['https://www.googleapis.com/auth/spreadsheets']
@@ -13,22 +15,23 @@ SPREADSHEET_URL = "https://docs.google.com/spreadsheets/d/1tIsXCbB8P6ZxdnZNnv7S7
 # Streamlit app
 st.title("Booking.com 台南飯店資料爬取與分析")
 st.sidebar.header("功能選擇")
-mode = st.sidebar.selectbox("選擇模式", ["資料爬取", "上傳至 Google Sheet"])
+mode = st.sidebar.selectbox("選擇模式", ["資料爬取", "資料視覺化", "上傳至 Google Sheet"])
 
 @st.cache_data
-def scrape_booking_hotel(location, checkin_date, checkout_date):
+def scrape_booking_hotel():
     url = "https://www.booking.com/searchresults.zh-tw.html"
     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',
         'Accept-Language': 'zh-TW,zh;q=0.9,en-US;q=0.8,en;q=0.7',
     }
     params = {
-        'ss': location,
-        'checkin': checkin_date,
-        'checkout': checkout_date,
+        'ss': '台南',
+        'checkin': '2024-11-16',
+        'checkout': '2024-11-17',
         'group_adults': '2',
         'no_rooms': '1',
         'group_children': '0',
+        'dest_id': '-2637868',
         'dest_type': 'city'
     }
     try:
@@ -45,7 +48,7 @@ def scrape_booking_hotel(location, checkin_date, checkout_date):
                 price_elem = hotel.find('span', {'data-testid': 'price-and-discounted-price'})
                 price = price_elem.text.strip() if price_elem else "無資料"
                 
-                # Clean price data
+                # 清洗價格資料
                 price = (
                     price.replace('TWD', '')
                     .replace(' ', '')
@@ -86,6 +89,47 @@ def scrape_booking_hotel(location, checkin_date, checkout_date):
     except requests.RequestException:
         return pd.DataFrame()
 
+def clean_rating(x):
+    if pd.isna(x) or x == '無評分':
+        return 0
+    return float(str(x).replace('分數', '').replace('分', ''))
+
+def create_price_rating_scatter(df):
+    if df.empty:
+        st.warning("數據為空，無法生成圖表。")
+        return None
+    fig = px.scatter(
+        df,
+        x='價格',
+        y='評分',
+        text='飯店名稱',
+        size='價格',  # 點大小基於價格
+        color='評分',
+        title='台南飯店價格與評分關係圖',
+        labels={'價格': '房價 (TWD)', '評分': '評分 (0-10)'}
+    )
+    fig.update_layout(height=600, title_x=0.5)
+    return fig
+
+def create_price_distribution(df):
+    if df.empty:
+        st.warning("數據為空，無法生成圖表。")
+        return None
+    fig = go.Figure()
+    fig.add_trace(go.Histogram(
+        x=df['價格'],
+        name='價格分布',
+        nbinsx=10,
+        marker_color='rgb(55, 83, 109)'
+    ))
+    fig.add_trace(go.Box(
+        x=df['價格'],
+        name='價格箱型圖',
+        marker_color='rgb(26, 118, 255)'
+    ))
+    fig.update_layout(title_text='台南飯店價格分布', title_x=0.5, height=500)
+    return fig
+
 def upload_to_google_sheets(df):
     creds = Credentials.from_service_account_file(SERVICE_ACCOUNT_FILE, scopes=SCOPE)
     gs = gspread.authorize(creds)
@@ -97,25 +141,41 @@ def upload_to_google_sheets(df):
 
 # Streamlit app implementation
 if mode == "資料爬取":
-    st.header("爬取飯店資料")
-    location = st.text_input("輸入查詢地點", "台南")
-    checkin_date = st.date_input("選擇入住日期")
-    checkout_date = st.date_input("選擇退房日期")
-
+    st.header("爬取台南飯店資料")
     if st.button("開始爬取"):
-        df = scrape_booking_hotel(location, checkin_date.strftime('%Y-%m-%d'), checkout_date.strftime('%Y-%m-%d'))
+        df = scrape_booking_hotel()
         if not df.empty:
             st.dataframe(df)
-            df.to_csv('booking_hotels.csv', index=False, encoding='utf-8-sig')
-            st.success("資料爬取成功，已儲存至 booking_hotels.csv")
+            df.to_csv('booking_hotels_tainan.csv', index=False, encoding='utf-8-sig')
+            st.success("資料爬取成功，已儲存至 booking_hotels_tainan.csv")
         else:
             st.error("未能成功爬取資料")
 
+elif mode == "資料視覺化":
+    st.header("分析與視覺化")
+    try:
+        df = pd.read_csv('booking_hotels_tainan.csv', encoding='utf-8-sig')
+        df['價格'] = pd.to_numeric(df['價格'], errors='coerce')
+        df['評分'] = df['評分'].apply(clean_rating)
+        df = df.dropna(subset=['價格'])
+
+        st.write(f"有效數據行數：{len(df)}")
+        st.write(f"價格缺失值數量：{df['價格'].isna().sum()}")
+
+        scatter_fig = create_price_rating_scatter(df)
+        if scatter_fig:
+            st.plotly_chart(scatter_fig)
+        dist_fig = create_price_distribution(df)
+        if dist_fig:
+            st.plotly_chart(dist_fig)
+    except Exception as e:
+        st.error(f"讀取或分析資料時發生錯誤：{e}")
+
 elif mode == "上傳至 Google Sheet":
     st.header("上傳資料至 Google Sheet")
     try:
-        df = pd.read_csv('booking_hotels.csv', encoding='utf-8-sig')
+        df = pd.read_csv('booking_hotels_tainan.csv', encoding='utf-8-sig')
         result = upload_to_google_sheets(df)
         st.success(result)
     except Exception as e:
-        st.error(f"上傳資料時發生錯誤：{e}")
+        st.error(f"上傳資料時發生錯誤：{e}")