app.py

import requests
from bs4 import BeautifulSoup
import pandas as pd
from urllib.parse import quote
import streamlit as st
import json

@st.cache_data
def scrape_e_commerce(nama_barang, num_items):
    products = []
    page = 1
    query = quote(nama_barang)
    progress_text = "Scraping in progress. Please wait."
    my_bar = st.progress(len(data), text=progress_text)
    
    while len(products) < num_items:
        url = f"https://www.klikindomaret.com/search/?key={query}&categories=&productbrandid=&sortcol=&pagesize=54&page={page}&startprice=&endprice=&attributes=&ShowItem="
        response = requests.get(url)
        soup = BeautifulSoup(response.text, 'html.parser')

        product_list = soup.find_all('a', href=True)

        for product in product_list:
            product_href = product['href']
            if '/product/' in product_href:
                product_name = product.find('div', class_='title').text.strip()
                product_price = product.find('span', class_='normal price-value').text.strip()
                product_link = f"https://www.klikindomaret.com{product_href}"
                products.append({
                    'product': product_name,
                    'price': product_price,
                    'link': product_link
                })
                
        prop = min(len(products) / num_items, 1)
        my_bar.progress(prop, text=progress_text)
        if len (products) > num_items :
          products = products[:num_items]
          break
        page += 1
        
    time.sleep(1)   
    my_bar.empty()
    return products

#---------------------------------------------------User Interface----------------------------------------------------------------------

# Streamlit UI
st.title("Scraping E-Commerce")

with st.expander("Settings :"):
    # Pilihan untuk memilih situs web
    selected_site = st.selectbox("Pilih Situs Web :", ["klikindomaret.com"])
    
    nama_barang = st.text_input("Masukkan Nama Barang :")
    estimated_num_items = st.number_input("Masukkan Estimasi Banyak Data :", min_value = 1, step = 1, placeholder="Type a number...")
    
    download_format = st.selectbox("Pilih Format Unduhan :", ["XLSX", "CSV", "JSON"])
    st.info('Tekan "Mulai Scraping" kembali jika tampilan menghilang ', icon="ℹ️")

# Variabel tersembunyi untuk menyimpan hasil scraping
hidden_data = []

scraping_done = False  # Tambahkan variabel ini

if selected_site == "klikindomaret.com":
    if st.button("Mulai Scraping"):
        if not query:
            st.error("Mohon isi query.")
        else:
            data_df = scrape_e_commerce(nama_barang, estimated_num_items)
            hidden_data = data_df  # Simpan data ke dalam variabel tersembunyi
            scraping_done = True  # Set scraping_done menjadi True

scraped_products = scrape_e_commerce(nama_barang, estimated_num_items)



# Simpan DataFrame ke dalam file
output_file = f"scraped_{nama_barang}.xlsx"
output_file_csv = f"scraped_{nama_barang}.csv"
output_file_json = f"scraped_{nama_barang}.json"


#---------------------------------------------------Download File & Hasil Scraping----------------------------------------------------------------------

# Tampilkan hasil scraping
if scraping_done:
    if hidden_data:
        # Menampilkan hasil sentimen dalam kotak yang dapat diperluas
        with st.expander(f"Hasil Scraping {selected_site} :"):
            st.write(pd.DataFrame(scraped_products))
        if download_format == "XLSX":
            df = pd.DataFrame(scraped_products)
            df.to_excel(output_file, index=False)
            st.download_button(label=f"Unduh XLSX ({len(hidden_data)} data)", data=open(output_file, "rb").read(), key="xlsx_download", file_name=output_file)
        elif download_format == "CSV":
            df = pd.DataFrame(scraped_products)
            csv = df.to_csv(index=False)
            st.download_button(label=f"Unduh CSV ({len(hidden_data)} data)", data=csv, key="csv_download", file_name=output_file_csv)
        elif download_format == "JSON":
            json_data = pd.DataFrame(scraped_products).to_json(orient="records")
            st.download_button(label=f"Unduh JSON ({len(hidden_data)} data)", data=json_data, key="json_download", file_name=output_file_json)
if not scraping_done:
    st.write("Tidak ada data untuk diunduh.")

st.divider()
github_link = "https://github.com/naufalnashif/"
st.markdown(f"GitHub: [{github_link}]({github_link})")
instagram_link = "https://www.instagram.com/naufal.nashif/"
st.markdown(f"Instagram: [{instagram_link}]({instagram_link})")
st.write('Terima kasih telah mencoba demo ini!')