Upload app.py with huggingface_hub

app.py

@@ -3,70 +3,35 @@
 import streamlit as st
 from bs4 import BeautifulSoup
 import requests
-from urllib.parse import urlsplit
-from urllib.parse import unquote
-import os
+from urllib.parse import urljoin
 
-def download_page(url):
-    try:
-        response = requests.get(url)
-        soup = BeautifulSoup(response.text, 'html.parser')
-        return soup
-    except requests.exceptions.RequestException as e:
-        return f"Error: {e}"
-
-def download_and_save(url):
-    try:
-        response = requests.get(url, allow_redirects=True)
-        soup = BeautifulSoup(response.text, 'html.parser')
-        filename = os.path.basename(unquote(urlsplit(response.url).path))
-        if not filename:
-            filename = 'index.html'
-        with open(filename, 'w', encoding='utf-8') as file:
-            file.write(soup.prettify())
-        return filename, soup
-    except requests.exceptions.RequestException as e:
-        return f"Error: {e}", None
-
-def get_first_link(query):
-    url = f"https://www.google.com/search?q={query}"
+def search_daraz(query):
+    url = f"https://www.daraz.com.np/catalog/?q={query}"
     response = requests.get(url)
     soup = BeautifulSoup(response.text, 'html.parser')
-    links = soup.find_all('a')
-    for link in links:
-        href = link.get('href')
-        if href and href.startswith('/url?q='):
-            return href.split('&sa=U&ved=')[0].replace('/url?q=', '')
+    product_links = soup.find_all('a', class_='c16H9d')
+    if product_links:
+        return urljoin("https://www.daraz.com.np", product_links[0]['href'])
+    else:
+        return None
+
+def download_content(url):
+    response = requests.get(url)
+    return response.text
+
+st.title("Daraz Search and Download")
 
-st.title("Webpage Downloader")
-st.write("Enter the query or URL of the webpage you want to download:")
+query = st.text_input("Enter your query (e.g. beds)")
+search_button = st.button("Search")
 
-query = st.text_input("Query or URL")
-if st.button("Download"):
-    if query:
-        if "http" not in query:
-            url = get_first_link(query)
-            st.write(f"Opening first link: {url}")
-        else:
-            url = query
-            if " from " in url:
-                url = url.split(" from ")[1]
-        try:
-            filename, soup = download_and_save(url)
-            if "Error:" in filename:
-                st.error(f"Failed to download webpage: {filename}")
-            else:
-                st.success(f"Webpage downloaded and saved as {filename}")
-                images = soup.find_all('img')
-                for i, img in enumerate(images):
-                    img_url = img.get('src')
-                    if img_url:
-                        st.image(img_url, caption=f"Image {i+1}")
-                titles = soup.find_all(['h1', 'h2', 'h3', 'h4', 'h5', 'h6'])
-                for title in titles:
-                    st.write(title.text)
-        except Exception as e:
-            st.error(f"Failed to download webpage: {e}")
+if search_button:
+    link = search_daraz(query)
+    if link:
+        st.write(f"First result: {link}")
+        download_button = st.button("Download Content")
+        if download_button:
+            content = download_content(link)
+            st.download_button("Download", content, file_name="content.html")
     else:
-        st.error("Please enter a query or URL")
+        st.write("No results found")