app.py

import os
import requests
import pandas as pd
import matplotlib as mpl
import matplotlib.font_manager as fm
import matplotlib.pyplot as plt
import streamlit as st
import json
import time

# Set up Streamlit app title
st.title("🐣MOMO 🆚 PCHOME 商品搜索和價格分析👁️‍🗨️")

# Get user input
search_keyword = st.text_input("請輸入要搜索的關鍵字: ", "筆電")
page_number = st.number_input("請輸入要搜索的頁數: ", min_value=1, max_value=100, value=1, step=1)

# Create a button to start the scraping process
if st.button("開始搜索"):
    start_time = time.time()
    
    # MOMO scraping
    momo_url = "https://apisearch.momoshop.com.tw/momoSearchCloud/moec/textSearch"
    momo_headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36"
    }
    momo_payload = {
        "host": "momoshop",
        "flag": "searchEngine",
        "data": {
            "searchValue": search_keyword,
            "curPage": str(page_number),
            "priceS": "0",
            "priceE": "9999999",
            "searchType": "1"
        }
    }
    momo_response = requests.post(momo_url, headers=momo_headers, json=momo_payload)
    
    if momo_response.status_code == 200:
        momo_data = momo_response.json().get('rtnSearchData', {}).get('goodsInfoList', [])
        momo_product_list = []
        for product in momo_data:
            name = product.get('goodsName', '')
            price = product.get('goodsPrice', '')
            price_str = str(price).split('(')[0].replace(',', '').replace('$', '')
            try:
                product_price = float(price_str)
            except ValueError:
                product_price = 0
            momo_product_list.append({'title': name, 'price': product_price, 'platform': 'MOMO'})
        
        momo_df = pd.DataFrame(momo_product_list)
        st.write("MOMO 商品數據:", momo_df)
        
        # MOMO data analysis
        momo_avg_price = momo_df['price'].mean()
        st.write(f"MOMO 平均價格: {momo_avg_price:.2f}")
        st.write(f"MOMO 最高價格: {momo_df['price'].max():.2f}")
        st.write(f"MOMO 最低價格: {momo_df['price'].min():.2f}")
        
        # MOMO visualization - Unified with PCHOME
        font_url = "https://drive.google.com/uc?id=1eGAsTN1HBpJAkeVM57_C7ccp7hbgSz3_&export=download"
        font_response = requests.get(font_url)
        with open("TaipeiSansTCBeta-Regular.ttf", "wb") as font_file:
            font_file.write(font_response.content)
        fm.fontManager.addfont("TaipeiSansTCBeta-Regular.ttf")
        mpl.rc('font', family='Taipei Sans TC Beta')
        
        fig, ax = plt.subplots(figsize=(15, 8))
        ax.plot(momo_df.index[:70], momo_df['price'][:70], 'o', color='skyblue', markersize=8)
        ax.set_title(f'MOMO 電商網站上 "{search_keyword}" 的銷售價格', fontsize=20, fontweight='bold')
        ax.axhline(y=momo_avg_price, color='red', linestyle='--', linewidth=2, label=f'參考價格: {momo_avg_price:.2f}')
        ax.set_xlabel('商品索引', fontsize=14)
        ax.set_ylabel('價格', fontsize=14)
        ax.tick_params(axis='x', rotation=45, labelsize=12)
        ax.tick_params(axis='y', labelsize=12)
        ax.legend(fontsize=12, loc='upper left')
        ax.grid(axis='y', linestyle='--', alpha=0.7)
        plt.tight_layout()
        st.pyplot(fig)
    else:
        st.error(f"MOMO 請求失敗，狀態碼: {momo_response.status_code}")
    
    # PCHOME scraping
    pchome_base_url = 'https://ecshweb.pchome.com.tw/search/v3.3/all/results?q='
    pchome_data = pd.DataFrame()
    
    for i in range(1, page_number + 1):
        pchome_url = f'{pchome_base_url}{search_keyword}&page={i}&sort=sale/dc'
        pchome_response = requests.get(pchome_url)
        if pchome_response.status_code == 200:
            pchome_json_data = json.loads(pchome_response.content)
            pchome_df = pd.DataFrame(pchome_json_data['prods'])
            
            # Safely select only available columns
            available_columns = ['name', 'describe', 'price', 'orig']
            selected_columns = [col for col in available_columns if col in pchome_df.columns]
            pchome_df = pchome_df[selected_columns]
            if 'orig' in pchome_df.columns:
                pchome_df = pchome_df.rename(columns={'orig': 'original_price'})
            pchome_df['platform'] = 'PCHOME'  # Add platform identifier
            pchome_data = pd.concat([pchome_data, pchome_df])
            time.sleep(1)
        else:
            st.error(f"PCHOME 請求失敗，狀態碼: {pchome_response.status_code}")
    
    if not pchome_data.empty:
        st.write("PCHOME 商品數據:", pchome_data)
        
        # PCHOME data analysis
        pchome_avg_price = pchome_data['price'].mean()
        st.write(f"PCHOME 平均價格: {pchome_avg_price:.2f}")
        st.write(f"PCHOME 最高價格: {pchome_data['price'].max():.2f}")
        st.write(f"PCHOME 最低價格: {pchome_data['price'].min():.2f}")
        
        # PCHOME visualization
        fig, ax = plt.subplots(figsize=(15, 8))
        ax.plot(pchome_data.index[:70], pchome_data['price'][:70], 'o', color='skyblue', markersize=8)
        ax.set_title(f'PCHOME 電商網站上 "{search_keyword}" 的銷售價格', fontsize=20, fontweight='bold')
        ax.axhline(y=pchome_avg_price, color='red', linestyle='--', linewidth=2, label=f'參考價格: {pchome_avg_price:.2f}')
        ax.set_xlabel('商品索引', fontsize=14)
        ax.set_ylabel('價格', fontsize=14)
        ax.tick_params(axis='x', rotation=45, labelsize=12)
        ax.tick_params(axis='y', labelsize=12)
        ax.legend(fontsize=12, loc='upper left')
        ax.grid(axis='y', linestyle='--', alpha=0.7)
        plt.tight_layout()
        st.pyplot(fig)
    
    # Combine MOMO and PCHOME data
    combined_data = pd.concat([momo_df, pchome_data], ignore_index=True)
    
    # Add a button to download the combined data as CSV
    csv = combined_data.to_csv(index=False, encoding='utf-8-sig').encode('utf-8-sig')
    st.download_button(
        label="下載CSV檔案",
        data=csv,
        file_name=f'{search_keyword}_combined_data.csv',
        mime='text/csv'
    )
    
    end_time = time.time()
    st.write(f"Execution time: {end_time - start_time:.2f} seconds")