Hugging Face's logo

Spaces:
Roberta2024
/
PET_STREAMLIT
Sleeping

App Files Community
PET_STREAMLIT
File size: 4,862 Bytes 
f844013
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
 
import streamlit as st
import requests
from bs4 import BeautifulSoup
import pandas as pd
import plotly.express as px
import base64

# 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/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 = []

# 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:
            data_list.append({
                "標題": title,
                "手機": phone,
                "地址": address,
                "評分": rating
            })

    # 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)

        # 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。')