Update app.py

app.py

@@ -118,6 +118,63 @@ def scrape_shopee(nama_barang, num_items):
             driver.quit()
     
     return products
+
+@st.cache_data
+def scrape_tokped(nama_barang, num_items):
+  products = []
+  page = 1
+  query = quote(nama_barang)
+
+  while len(data) < num_items :
+    url = f'https://www.tokopedia.com/search?navsource=&page={page}&q={query}&srp_component_id=02.01.00.00&srp_page_id=&srp_page_title=&st='
+
+    headers = {
+        'User-Agent' : "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36",
+        'Accept-Language' : 'en-US, en;q-0.5',
+        'Accept-Encoding' : 'grip, deflate, bt',
+        'Connection': 'keep-alive'
+    }
+    timeout = 10
+    try :
+      response = requests.get(url, headers = headers, timeout = timeout)
+      response.raise_for_status()
+
+      soup = BeautifulSoup(response.text, 'html.parser')
+      product_container_list = soup.find_all('a', class_="pcv3__info-content css-gwkf0u", href = True)
+
+      for product_info in product_container_list:
+        link = product_info['href']
+        title = product_info.find('div', class_="prd_link-product-name css-3um8ox" ).text.strip()
+        harga = product_info.find('div', class_="prd_link-product-price css-h66vau").text.strip()
+        #Dapatkan terjual
+        terjual_element = product_info.find('span', class_="prd_label-integrity css-1sgek4h").text.strip()
+        terjual = terjual_element if terjual_element else None
+        # Dapatkan rating
+        rating_element = product_info.find('span', class_='prd_rating-average-text css-t70v7i')
+        rating = rating_element.text if rating_element else None
+
+        toko = product_info.find('span', class_="prd_link-shop-name css-1kdc32b flip").text.strip()
+        asal_product = product_info.find('span', class_="prd_link-shop-loc css-1kdc32b flip"  ).text.strip()
+
+        products.append({
+            'link': link,
+            'produk' : title,
+            'harga' : harga,
+            'terjual' : terjual,
+            'rating' : rating,
+            'toko' : toko,
+            'asal_product' : asal_product,
+        })
+        if len(products) >= num_items:
+            products = products[:num_items]
+            break
+
+    except requests.exceptions.RequestException as e:
+      st.error("Terjadi kesalahan")
+    except requests.exceptions.HTTPError as e:
+      st.error("HTTP Error :", str(e))
+    page += 1
+  return products
 #---------------------------------------------------User Interface----------------------------------------------------------------------
 
 # Streamlit UI
@@ -125,7 +182,7 @@ st.title("Scraping E-Commerce")
 
 with st.expander("Settings :"):
     # Pilihan untuk memilih situs web
-    selected_site = st.selectbox("Pilih Situs Web :", ["klikindomaret.com", "shopee.co.id"])
+    selected_site = st.selectbox("Pilih Situs Web :", ["klikindomaret.com", "shopee.co.id", "tokopedia.com"])
     
     nama_barang = st.text_input("Masukkan Nama Barang :")
     num_items = st.number_input("Masukkan Estimasi Banyak Data :", min_value = 1, step = 1, placeholder="Type a number...")
@@ -156,7 +213,16 @@ if selected_site == "shopee.co.id":
             scraped_products = scrape_shopee(nama_barang, num_items)
             hidden_data = scraped_products  # Simpan data ke dalam variabel tersembunyi
             scraping_done = True  # Set scraping_done menjadi True
-
+            
+if selected_site == "tokopedia.com":
+    #st.error("Sedang dalam pengembangan. Silahkan pilih situs yang lain")
+    if st.button("Mulai Scraping"):
+        if not nama_barang:
+            st.error("Mohon isi Nama Barang.")
+        else:
+            scraped_products = scrape_tokped(nama_barang, num_items)
+            hidden_data = scraped_products  # Simpan data ke dalam variabel tersembunyi
+            scraping_done = True  # Set scraping_done menjadi True
 
 # Simpan DataFrame ke dalam file
 output_file = f"scraped_{selected_site}_{nama_barang}.xlsx"