import streamlit as st import requests from bs4 import BeautifulSoup import pandas as pd import plotly.express as px import plotly.graph_objects as go from datetime import datetime import time st.set_page_config(page_title="Market Price Monitor", layout="wide") # ==================== WEB SCRAPING FUNCTIONS ==================== def scrape_coinmarketcap(): """Scrape cryptocurrency prices từ CoinMarketCap""" url = "https://coinmarketcap.com/" headers = {"User-Agent": "Mozilla/5.0"} try: response = requests.get(url, headers=headers, timeout=10) if response.status_code != 200: return pd.DataFrame(), "Error fetching data" soup = BeautifulSoup(response.content, "html.parser") rows = soup.select("tbody tr")[:15] data = [] for row in rows: cols = row.find_all("td") if len(cols) >= 7: name = cols[2].find("p", class_=True).text.strip() if cols[2].find("p") else "N/A" symbol = cols[2].find("p", class_="coin-item-symbol").text.strip() if cols[2].find("p", class_="coin-item-symbol") else "N/A" price = cols[3].text.strip() if len(cols) > 3 else "N/A" change_24h = cols[4].text.strip() if len(cols) > 4 else "N/A" market_cap = cols[6].text.strip() if len(cols) > 6 else "N/A" data.append({ "Name": name, "Symbol": symbol, "Price": price, "24h Change": change_24h, "Market Cap": market_cap }) df = pd.DataFrame(data) return df, None except Exception as e: return pd.DataFrame(), str(e) def scrape_product_prices(product_urls): """Scrape giá sản phẩm từ nhiều website (tùy chỉnh)""" data = [] for url in product_urls: try: headers = {"User-Agent": "Mozilla/5.0"} response = requests.get(url, headers=headers, timeout=10) soup = BeautifulSoup(response.content, "html.parser") # Tùy chỉnh selector theo website (ví dụ: Amazon, Shopee) title = soup.find("span", class_="a-size-medium") or soup.find("h1") price = soup.find("span", class_="a-price-whole") or soup.find("div", class_="price") data.append({ "URL": url, "Product": title.text.strip() if title else "Unknown", "Price": price.text.strip() if price else "N/A", "Scraped At": datetime.now().strftime("%Y-%m-%d %H:%M") }) except Exception as e: data.append({ "URL": url, "Product": "Error", "Price": f"Error: {str(e)}", "Scraped At": datetime.now().strftime("%Y-%m-%d %H:%M") }) return pd.DataFrame(data) # ==================== STREAMLIT DASHBOARD ==================== st.title("📊 Market Price Monitor Dashboard") st.markdown("Theo dõi giá thị trường thời gian thực - Web Scraping tự động") # Sidebar st.sidebar.header("⚙️ Cài đặt") # Chọn loại thị trường market_type = st.sidebar.radio( "Chọn thị trường:", ["Cryptocurrency", "Sản phẩm E-commerce", "Cả hai"] ) auto_refresh = st.sidebar.checkbox("Tự động làm mới (30s)", value=False) refresh_interval = st.sidebar.slider("Tần suất (giây)", 10, 120, 30) # ==================== CRYPTOCURRENCY SECTION ==================== if market_type in ["Cryptocurrency", "Cả hai"]: st.header("🪙 Cryptocurrency Prices") col1, col2, col3 = st.columns(3) if market_type == "Cryptocurrency": df_crypto, error = scrape_coinmarketcap() if error: st.error(f"❌ Lỗi: {error}") else: # Metrics with col1: st.metric("Total Cryptos", len(df_crypto)) with col2: avg_price = df_crypto["Price"].astype(str).str.replace(r"[^\d.]", "", regex=True).mean() st.metric("Avg Price", f"${avg_price:.2f}" if avg_price else "N/A") with col3: top_gainer = df_crypto.loc[df_crypto["24h Change"].str.contains("+", na=False)].head(1) if not top_gainer.empty: st.metric("Top Gainer", f"{top_gainer['Name'].values[0]} ({top_gainer['24h Change'].values[0]})") else: st.metric("Top Gainer", "N/A") # Data table st.subheader("📋 Dữ liệu chi tiết") st.dataframe( df_crypto, use_container_width=True, hide_index=True ) # Charts col1, col2 = st.columns(2) with col1: st.subheader("📈 Top 10 by Price") df_crypto_clean = df_crypto.copy() df_crypto_clean["Price"].replace({r"[^\d.]": ""}, regex=True, inplace=True) df_crypto_clean["Price"] = pd.to_numeric(df_crypto_clean["Price"], errors="coerce") df_top10 = df_crypto_clean.nlargest(10, "Price") fig_bar = px.bar(df_top10, x="Symbol", y="Price", color="Name", title="Top 10 Crypto Prices", labels={"Price": "Price (USD)"}) st.plotly_chart(fig_bar, use_container_width=True) with col2: st.subheader("🥧 Market Cap Distribution") fig_pie = px.pie(df_crypto.head(10), names="Name", values="Market Cap", title="Top 10 Market Cap") st.plotly_chart(fig_pie, use_container_width=True) # 24h Change chart st.subheader("📊 24h Change (%)") df_crypto_clean["24h Change"].replace({r"[^\d.-]": ""}, regex=True, inplace=True) df_crypto_clean["24h Change"] = pd.to_numeric(df_crypto_clean["24h Change"], errors="coerce") fig_change = px.bar(df_crypto_clean.head(15), x="Name", y="24h Change", color="24h Change", color_continuous_scale="RdYlGn", title="24h Price Change (%)") st.plotly_chart(fig_change, use_container_width=True) # ==================== E-COMMERCE SECTION ==================== if market_type in ["Sản phẩm E-commerce", "Cả hai"]: st.header("🛒 E-commerce Product Prices") # Input URLs st.subheader("🔗 Thêm URL sản phẩm") url_input = st.text_area( "Nhập URLs (mỗi dòng 1 URL):", placeholder="https://amazon.com/product1\nhttps://shopee.vn/product2", height=150 ) if st.button("🔍 Scrape Prices", type="primary"): if url_input.strip(): urls = [url.strip() for url in url_input.split("\n") if url.strip()] with st.spinner("Đang scrape dữ liệu..."): df_products = scrape_product_prices(urls) st.subheader("📋 Kết quả") st.dataframe(df_products, use_container_width=True, hide_index=True) # Download CSV csv = df_products.to_csv(index=False).encode("utf-8") st.download_button( "📥 Download CSV", csv, "market_prices.csv", "text/csv" ) else: st.warning("⚠️ Vui lòng nhập ít nhất 1 URL") # ==================== FOOTER ==================== st.markdown("---") st.markdown( f"""
🔄 Cập nhật: {datetime.now().strftime("%Y-%m-%d %H:%M:%S")} | Data scraped từ CoinMarketCap & E-commerce sites
""", unsafe_allow_html=True ) # Auto-refresh if auto_refresh: time.sleep(refresh_interval) st.rerun()