Upload app.py with huggingface_hub
Browse files
app.py
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
# app.py
|
3 |
+
import streamlit as st
|
4 |
+
from googlesearch import search
|
5 |
+
import requests
|
6 |
+
from bs4 import BeautifulSoup
|
7 |
+
|
8 |
+
def get_first_link(query):
|
9 |
+
try:
|
10 |
+
for result in search(query, num=1, stop=1):
|
11 |
+
return result
|
12 |
+
except Exception as e:
|
13 |
+
st.error(f"Error fetching search results: {e}")
|
14 |
+
return None
|
15 |
+
|
16 |
+
def download_webpage_content(url):
|
17 |
+
try:
|
18 |
+
response = requests.get(url)
|
19 |
+
response.raise_for_status()
|
20 |
+
soup = BeautifulSoup(response.text, 'html.parser')
|
21 |
+
return soup.prettify()
|
22 |
+
except Exception as e:
|
23 |
+
st.error(f"Error fetching webpage content: {e}")
|
24 |
+
return None
|
25 |
+
|
26 |
+
st.title("Webpage Content Downloader")
|
27 |
+
|
28 |
+
query = st.text_input("Enter your search query:")
|
29 |
+
|
30 |
+
if st.button("Fetch First Link and Download Content"):
|
31 |
+
if query:
|
32 |
+
with st.spinner("Fetching the first link..."):
|
33 |
+
first_link = get_first_link(query)
|
34 |
+
if first_link:
|
35 |
+
st.success(f"First Link Found: {first_link}")
|
36 |
+
with st.spinner("Downloading webpage content..."):
|
37 |
+
webpage_content = download_webpage_content(first_link)
|
38 |
+
if webpage_content:
|
39 |
+
st.success("Content Downloaded!")
|
40 |
+
st.download_button(
|
41 |
+
label="Download Webpage Content",
|
42 |
+
data=webpage_content,
|
43 |
+
file_name="webpage_content.html",
|
44 |
+
mime="text/html"
|
45 |
+
)
|
46 |
+
else:
|
47 |
+
st.error("No links found for the query.")
|
48 |
+
else:
|
49 |
+
st.error("Please enter a query.")
|
50 |
+
|
51 |
+
|