app.py

import requests
from bs4 import BeautifulSoup
import pandas as pd
import folium
from folium.plugins import MarkerCluster, HeatMap
import plotly.graph_objects as go
from geopy.geocoders import Nominatim
import re
import streamlit as st

# Streamlit title and description
st.title("Restaurant Data Extractor")
st.write("Extracting restaurant data and displaying it on a map.")

# Read data from Google Sheets
sheet_id = "1xUfnD1WCF5ldqECI8YXIko1gCpaDDCwTztL17kjI42U"
df1 = pd.read_csv(f"https://docs.google.com/spreadsheets/d/{sheet_id}/export?format=csv")

# Convert "網址" column to a Python list
urls = df1["網址"].tolist()

# Create a DataFrame to store all restaurant data
df = pd.DataFrame(columns=["Store Name", "Address", "Latitude", "Longitude", "Region"])

# Initialize Nominatim geocoder
geolocator = Nominatim(user_agent="my_app")

# Function to extract region (區域) from the address using regex
def extract_region(address):
    match = re.search(r'(.*?)區|縣|市', address)
    if match:
        return match.group(0)
    else:
        return "Unknown"

# Progress bar in Streamlit
progress_bar = st.progress(0)
total_urls = len(urls)

# Iterate through each URL
for idx, url in enumerate(urls):
    response = requests.get(url)
    soup = BeautifulSoup(response.content, "html.parser")

    try:
        store_name = soup.find("h2", class_="restaurant-details__heading--title").text.strip()
    except AttributeError:
        store_name = None

    try:
        address = soup.find("li", class_="restaurant-details__heading--address").text.strip()
        region = extract_region(address)
    except AttributeError:
        address = None
        region = "Unknown"

    try:
        location = geolocator.geocode(address)
        if location:
            latitude = location.latitude
            longitude = location.longitude
        else:
            latitude = None
            longitude = None
    except:
        latitude = None
        longitude = None

    new_row = pd.DataFrame({
        "Store Name": [store_name],
        "Address": [address],
        "Latitude": [latitude],
        "Longitude": [longitude],
        "Region": [region]
    })

    df = pd.concat([df, new_row], ignore_index=True)

    # Update progress bar
    progress_bar.progress((idx + 1) / total_urls)

# Save the DataFrame to CSV with UTF-8 encoding
csv_file = "restaurants_data.csv"
df.to_csv(csv_file, encoding="utf-8-sig", index=False)

# Display a download button for the CSV file
st.write(f"Data saved to {csv_file}")
st.download_button(
    label="Download restaurant data as CSV",
    data=open(csv_file, "rb").read(),
    file_name=csv_file,
    mime="text/csv"
)

# Display a map using Folium in Streamlit
st.subheader("Restaurant Locations Map")

# Create map centered around Tainan
m = folium.Map(location=[23.0, 120.2], zoom_start=12)

# Add marker cluster to the map
marker_cluster = MarkerCluster().add_to(m)
for index, row in df.iterrows():
    if pd.notnull(row["Latitude"]) and pd.notnull(row["Longitude"]):
        folium.Marker(
            location=[row["Latitude"], row["Longitude"]],
            popup=row["Store Name"],
            tooltip=row["Address"]
        ).add_to(marker_cluster)

# Display the map in Streamlit
st.components.v1.html(m._repr_html_(), height=600)

# Optional: Display the DataFrame as a table
st.subheader("Restaurant Data")
st.dataframe(df)