Update app.py

app.py

@@ -3,31 +3,17 @@ import requests
 from bs4 import BeautifulSoup
 import pandas as pd
 import plotly.graph_objects as go
-import plotly.io as pio
+import os
 
 app = Flask(__name__)
 
-@app.route('/')
-def home():
-    # 設定應用標題
-    title = "餐廳資料抓取與分析"
-
-    # 從 Google 試算表中讀取 URLs
-    sheet_id = "1W20lawjiQtEpljUKoEaMVPDlSdnhvJLPUy2jk5xao_w"
-    urls_df = pd.read_csv(f"https://docs.google.com/spreadsheets/d/{sheet_id}/export?format=csv")
-
-    # 將 URLs 轉換為列表
-    urls = urls_df['網址'].tolist()
-
-    # 初始化一個空的 DataFrame 列表來儲存所有資料
+# Function to scrape restaurant data from URLs
+def scrape_data(urls):
     df_list = []
-
-    # 迭代每個網址並抓取資料
     for url in urls:
         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'
         
@@ -40,11 +26,9 @@ def home():
         description_tag = soup.find('div', class_='restaurant-details__description--text')
         description = description_tag.text.strip() if description_tag else 'N/A'
 
-        # NOTE: Assuming latitude and longitude are not available from the current page content, you can omit them or fetch them if necessary
         lat = 'N/A'
         lon = 'N/A'
 
-        # 將抓取的資料新增到列表中
         df_list.append({
             'Title': title,
             'Address': address,
@@ -54,25 +38,33 @@ def home():
             'Longitude': lon
         })
 
-    # 使用 pd.DataFrame() 將所有資料合併成一個 DataFrame
-    df = pd.DataFrame(df_list)
+    return pd.DataFrame(df_list)
+
+@app.route('/')
+def home():
+    return render_template('index.html')
 
-    # 統計每個區的商家數量
-    df['Area'] = df['Address'].str.extract(r'(\w+區)')  # 正确关闭字符串
+@app.route('/scrape', methods=['POST'])
+def scrape():
+    sheet_id = request.form['sheet_id']
+    urls_df = pd.read_csv(f"https://docs.google.com/spreadsheets/d/{sheet_id}/export?format=csv")
+    urls = urls_df['網址'].tolist()
+    
+    df = scrape_data(urls)
 
-    # 生成柱狀圖
-    area_counts = df['Area'].value_counts()  # 統計各區的商家數量
+    # Generate bar chart
+    df['Area'] = df['Address'].str.extract(r'(\w+區)')
+    area_counts = df['Area'].value_counts()
     fig_bar = go.Figure(data=[go.Bar(x=area_counts.index, y=area_counts.values)])
     fig_bar.update_layout(title='每個區的商家數量', xaxis_title='區域', yaxis_title='商家數量')
-    bar_chart = pio.to_html(fig_bar, full_html=False)
+    bar_chart = fig_bar.to_html(full_html=False)
 
-    # 生成圓餅圖
+    # Generate pie chart
     fig_pie = go.Figure(data=[go.Pie(labels=area_counts.index, values=area_counts.values)])
     fig_pie.update_layout(title='每個區的商家數量比例')
-    pie_chart = pio.to_html(fig_pie, full_html=False)
+    pie_chart = fig_pie.to_html(full_html=False)
 
-    # 渲染模板，顯示結果
     return render_template('results.html', tables=[df.to_html(classes='data')], bar_chart=bar_chart, pie_chart=pie_chart)
 
 if __name__ == '__main__':
-    app.run(host='0.0.0.0', port=8080, debug=True)
+    app.run(host='0.0.0.0', port=int(os.environ.get('PORT', 8080)), debug=True)