Upload app.py with huggingface_hub

app.py

@@ -5,46 +5,28 @@ from bs4 import BeautifulSoup
 import requests
 from urllib.parse import urljoin, urlparse
 
-def is_valid(url):
-    parsed = urlparse(url)
-    return bool(parsed.netloc) and bool(parsed.scheme)
-
-def get_all_website_links(url, query):
-    urls = set()
-    domain_name = urlparse(url).netloc
-    soup = BeautifulSoup(requests.get(url + "?q=" + query).content, "html.parser")
-    for a_tag in soup.findAll("a"):
-        href = a_tag.attrs.get("href")
-        if href == "" or href is None:
-            continue
-        href = urljoin(url, href)
-        parsed_href = urlparse(href)
-        href = parsed_href.scheme + "://" + parsed_href.netloc + parsed_href.path
-        if not is_valid(href):
-            continue
-        if href in urls:
-            continue
-        if domain_name not in href:
-            continue
-        if href != url:
-            urls.add(href)
-    return urls
+def search(query, url):
+    if not url.startswith("http"):
+        url = "https://" + url
+    parsed_url = urlparse(url)
+    search_url = f"{parsed_url.scheme}://{parsed_url.netloc}/{query}/"
+    return search_url
 
 def download_content(url):
     response = requests.get(url)
     return response.text
 
 st.title("Search and Download")
+
 query = st.text_input("Enter your query (e.g. beds)")
 url = st.text_input("Enter the URL to search from (e.g. https://www.daraz.com.np/)")
-if st.button("Search"):
-    links = get_all_website_links(url, query)
-    if links:
-        first_link = list(links)[0]
-        st.write("First result:", first_link)
-        if st.button("Download content"):
-            content = download_content(first_link)
-            st.download_button("Download", content, file_name="content.html")
-    else:
-        st.write("No results found")
+search_button = st.button("Search")
+
+if search_button:
+    link = search(query, url)
+    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")