Update app.py

app.py

@@ -2,9 +2,9 @@ import streamlit as st
 import requests
 from bs4 import BeautifulSoup
 import pandas as pd
-import base64  # This is a built-in module, no need to install
+import base64
+import plotly.express as px
 
-# Function to set background image
 def set_background(image_file):
     with open(image_file, "rb") as image_file:
         encoded_string = base64.b64encode(image_file.read()).decode()
@@ -14,77 +14,99 @@ def set_background(image_file):
         .stApp {{
             background-image: url(data:image/png;base64,{encoded_string});
             background-size: cover;
+            background-position: center top;
+            padding-top: 100px;
         }}
         </style>
         """,
         unsafe_allow_html=True
     )
 
-# Set the background image
+# 設定背景圖片
 set_background('ddog.png')
 
-# Rest of the code remains the same
-# ...
-
-# Streamlit app title
+# Streamlit app 標題
 st.title('寵物診所資訊爬蟲')
 
 # 網址列表
 urls = [
     'https://www.tw-animal.com/pet/171211/c000196.html',
     'https://www.tw-animal.com/pet/171211/c000186.html',
-    # ... (rest of the URLs)
+    'https://www.tw-animal.com/pet/171211/c000081.html',
+    'https://www.tw-animal.com/pet/171211/c000848.html',
+    'https://www.tw-animal.com/pet/171211/c000045.html',
+    'https://www.tw-animal.com/pet/171211/c001166.html',
+    'https://www.tw-animal.com/pet/171211/c000773.html',
+    'https://www.tw-animal.com/pet/171211/c001038.html',
+    'https://www.tw-animal.com/pet/171211/c000741.html',
+    'https://www.tw-animal.com/pet/171211/c001451.html',
+    'https://www.tw-animal.com/pet/171211/c000102.html',
+    'https://www.tw-animal.com/pet/171211/c000757.html',
+    'https://www.tw-animal.com/pet/171211/c000703.html',
+    'https://www.tw-animal.com/pet/171211/c000481.html',
+    'https://www.tw-animal.com/pet/171211/c000971.html',
+    'https://www.tw-animal.com/pet/171211/c000187.html',
+    'https://www.tw-animal.com/pet/171211/c001357.html',
+    'https://www.tw-animal.com/pet/171211/c001065.html',
+    'https://www.tw-animal.com/pet/171211/c000165.html',
+    'https://www.tw-animal.com/pet/171211/c000217.html',
+    'https://www.tw-animal.com/pet/171211/c000802.html',
+    'https://www.tw-animal.com/pet/171211/c001034.html',
+    'https://www.tw-animal.com/pet/171211/c001453.html'
 ]
 
 # 讓使用者輸入評分門檻
 min_rating = st.slider("請選擇想篩選的最低評分", 0.0, 5.0, 4.5, 0.1)
 
+# 當使用者按下「開始爬蟲」按鈕時開始抓取資料
 if st.button('開始爬蟲'):
-    # 建立空的列表來儲存每一頁的資料
     all_data = []
-
-    # 顯示進度條
     progress_bar = st.progress(0)
     status_text = st.empty()
 
-    # 遍歷每個網址
+    # 遍歷每個網址並抓取資料
     for i, url in enumerate(urls):
-        # 更新進度條和狀態文字
         progress = int((i + 1) / len(urls) * 100)
         progress_bar.progress(progress)
         status_text.text(f'正在處理第 {i+1} 個網址，共 {len(urls)} 個')
 
-        # 發送HTTP請求獲取頁面內容
         response = requests.get(url)
         response.encoding = 'utf-8'
-
-        # 使用BeautifulSoup解析頁面
         soup = BeautifulSoup(response.text, 'html.parser')
 
-        # 抓取標題、手機、地址和評分
         title = soup.find('h1', class_='t-intro__title').get_text(strip=True)
         phone = soup.find('a', href=lambda href: href and href.startswith('tel:')).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))
+        
+        # 提取地址中的區名
+        district = address.split('區')[0] + '區' if '區' in address else '其他'
 
-        # 將評分大於或等於使用者輸入的資料存入列表
+        # 只將符合評分條件的資料加入列表
         if rating >= min_rating:
             all_data.append({
                 '標題': title,
                 '手機': phone,
                 '地址': address,
-                '評分': rating
+                '評分': rating,
+                '區': district
             })
 
-    # 將所有符合條件的資料轉換為DataFrame
+    # 轉換為 DataFrame
     df = pd.DataFrame(all_data)
 
-    # 檢查是否有符合條件的資料
+    # 如果有符合條件的資料，顯示並繪圖
     if not df.empty:
-        # 輸出篩選後的DataFrame
         st.dataframe(df)
-        
-        # 提供下載 CSV 檔案的選項
+
+        # 以每個區的診所數量繪製動態圖表
+        district_counts = df['區'].value_counts().reset_index()
+        district_counts.columns = ['區', '診所數量']
+
+        fig = px.bar(district_counts, x='區', y='診所數量', title='各區寵物診所數量')
+        st.plotly_chart(fig)
+
+        # 提供 CSV 下載功能
         csv = df.to_csv(index=False)
         st.download_button(
             label="下載 CSV 檔案",
@@ -95,19 +117,17 @@ if st.button('開始爬蟲'):
     else:
         st.write(f"沒有找到評分大於或等於 {min_rating} 的資料。")
 
-    # 清除進度條和狀態文字
+    # 清空進度條和狀態訊息
     progress_bar.empty()
     status_text.empty()
 
 # LINE Notify 部分
 st.header('傳送至 LINE Notify')
 token = st.text_input("請輸入 LINE Notify 權杖")
-
 if st.button('傳送至 LINE'):
     if 'df' in locals() and not df.empty:
         msg = df.to_string(index=False)
         
-        # 傳送 LINE Notify 訊息
         def send_line_notify(token, msg):
             headers = {
                 "Authorization": "Bearer " + token,
@@ -119,11 +139,10 @@ if st.button('傳送至 LINE'):
             r = requests.post("https://notify-api.line.me/api/notify", headers=headers, params=params)
             return r.status_code
 
-        # 呼叫傳送 LINE Notify 函數
         status_code = send_line_notify(token, msg)
         if status_code == 200:
             st.success('成功傳送至 LINE Notify!')
         else:
             st.error('傳送失敗，請檢查您的權杖是否正確。')
     else:
-        st.warning('沒有資料可以傳送，請先執行爬蟲。')
+        st.warning('沒有資料可以傳送，請先執行爬蟲。')