app.py

import time
import pandas as pd
import requests
import json
import matplotlib.pyplot as plt
import seaborn as sns
import matplotlib.font_manager as fm
import streamlit as st
from pathlib import Path

# 使用者輸入
st.title("PChome 網站爬蟲分析")
keyword = st.text_input("請輸入想搜尋的關鍵字", value="平板")
pages = st.number_input("請輸入要抓取的頁數", min_value=1, max_value=10, value=1)

# 按鈕
if st.button('開始抓取資料'):
    # 記錄開始時間
    start_time = time.time()

    # 下載字型檔案
    font_url = "https://drive.google.com/uc?id=1eGAsTN1HBpJAkeVM57_C7ccp7hbgSz3_&export=download"
    font_path = "TaipeiSansTCBeta-Regular.ttf"

    if not Path(font_path).is_file():
        with open(font_path, "wb") as f:
            f.write(requests.get(font_url).content)

    fm.fontManager.addfont(font_path)
    plt.rcParams['font.family'] = 'Taipei Sans TC Beta'

    # 爬取PChome資料
    alldata = pd.DataFrame()
    for i in range(1, pages + 1):
        url = f'https://ecshweb.pchome.com.tw/search/v3.3/all/results?q={keyword}&page={i}&sort=sale/dc'
        list_req = requests.get(url)
        getdata = json.loads(list_req.content)
        todataFrame = pd.DataFrame(getdata['prods'])
        alldata = pd.concat([alldata, todataFrame])
        time.sleep(10)

    # 資料處理
    df = alldata[["name", "price"]]
    df01 = df

    # 計算統計數據
    mean_price = df01['price'].mean()
    max_name = df01.loc[df01['price'].idxmax()]['name']
    min_price = df01['price'].min()

    st.write(f"平均價格: {mean_price}")
    st.write(f"最高價商品名稱: {max_name}")
    st.write(f"最低價格: {min_price}")

    # 畫圖設定
    st.subheader('價格分佈圖')
    plt.figure(figsize=(12, 6))
    sns.histplot(df01['price'], bins=30, kde=True)
    plt.title('商品價格分佈', fontsize=16)
    plt.xlabel('價格', fontsize=12)
    plt.ylabel('計數', fontsize=12)
    st.pyplot(plt)

    # 畫價格走勢圖
    st.subheader('前70個商品價格趨勢')
    df01['price'][:70].plot(subplots=False, figsize=(15, 8), color='skyblue', linewidth=2, marker='o', markersize=8)
    plt.title('PCHOME 電商網站上平板售價', fontsize=20, fontweight='bold')
    plt.axhline(y=10016, color='red', linestyle='--', linewidth=2, label='價格門檻: 10016')
    plt.xlabel('商品編號', fontsize=14)
    plt.ylabel('價格', fontsize=14)
    plt.xticks(rotation=45, ha='right', fontsize=12)
    plt.yticks(fontsize=12)
    plt.legend(fontsize=12, loc='upper left')
    plt.grid(axis='y', linestyle='--', alpha=0.7)
    plt.tight_layout()
    st.pyplot(plt)

    # 計算執行時間
    end_time = time.time()
    execution_time = end_time - start_time
    st.write(f"執行時間：{execution_time:.2f} 秒")