app.py

import streamlit as st
import requests
from bs4 import BeautifulSoup
import pandas as pd
import plotly.express as px
import base64
import folium
from streamlit_folium import st_folium
from geopy.geocoders import Nominatim

# Function to set background image
def set_background(png_file):
    with open(png_file, "rb") as f:
        data = f.read()
    encoded = base64.b64encode(data).decode()
    st.markdown(
        f"""
        <style>
        .stApp {{
            background: url(data:image/png;base64,{encoded});
            background-size: cover;
        }}
        </style>
        """,
        unsafe_allow_html=True
    )

# Set the background image
set_background('CAT.png')

# Title of the app
st.title("寵物醫院評分查詢")

# User input for minimum rating
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
urls = [
    "https://www.tw-animal.com/pet/171211/c000196.html",
    "https://www.tw-animal.com/pet/171211/c000186.html",
    "https://www.tw-animal.com/pet/171211/c000186.html",
    "https://www.tw-animal.com/pet/171211/c000081.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/c001138.html",
    "https://www.tw-animal.com/pet/171211/c000484.html",
    "https://www.tw-animal.com/pet/171211/c001089.html",
    "https://www.tw-animal.com/pet/171211/c001252.html"
]


# Create an empty list to store the extracted data
data_list = []

# Initialize the geolocator
geolocator = Nominatim(user_agent="geoapiExercises")

# Scrape data when the button is pressed
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
    for url in urls:
        response = requests.get(url)
        soup = BeautifulSoup(response.content, 'html.parser')

        # Extract data
        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
        if rating >= min_rating:
            try:
                # Geocode the address to get the latitude and longitude
                location = geolocator.geocode(address)
                if location:
                    data_list.append({
                        "標題": title,
                        "手機": phone,
                        "地址": address,
                        "評分": rating,
                        "經度": location.longitude,
                        "緯度": location.latitude
                    })
            except Exception as e:
                st.warning(f"無法獲取經緯度：{e}")

    # If data was scraped successfully
    if data_list:
        df1 = pd.DataFrame(data_list)

        # Extract the region from the address (assuming region is part of the address)
        df1['區域'] = df1['地址'].apply(lambda x: x.split()[0])

        # Group by region and merge hospitals in the same region
        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
        }).reset_index()

        # Display the dataframe
        st.dataframe(df1)

        # Display Plotly bar chart
        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
        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
        if st.button('顯示地圖'):
            # Create a folium map centered around the average location
            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
            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)

            # Render the map using streamlit_folium
            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 = "DzMHaXosskpjtGuIjuB7NIcQ5TIoptLz7l7VYzV3Wp4"  # 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。')