Create 10_ETScrapper.py

pages/10_ETScrapper.py

@@ -0,0 +1,32 @@
+import streamlit as st
+import requests
+from bs4 import BeautifulSoup
+import io
+
+st.title('Web Scraper')
+
+url = st.text_input('Enter the URL of the site to scrape:', '')
+
+if st.button('Scrape'):
+    if url:
+        response = requests.get(url)
+        soup = BeautifulSoup(response.content, 'html.parser')
+
+        # Extract the content
+        content = soup.get_text()
+
+        # Display the content
+        st.text_area('Scraped Content', content, height=300)
+
+        # Provide a download link
+        buffer = io.StringIO()
+        buffer.write(content)
+        buffer.seek(0)
+        st.download_button(
+            label="Download Extracted Text",
+            data=buffer,
+            file_name='extracted_content.txt',
+            mime='text/plain'
+        )
+    else:
+        st.error('Please enter a valid URL.')