Create app.py

app.py

@@ -0,0 +1,72 @@
+import os
+import requests
+from bs4 import BeautifulSoup
+from urllib.parse import urljoin, urlparse
+from zipfile import ZipFile
+from io import BytesIO
+
+def download_file(url, session):
+    """Download a file and return its content."""
+    response = session.get(url)
+    response.raise_for_status()
+    return response.content
+
+def save_webpage_as_zip(url, output_zip):
+    """Save a webpage and its assets as a ZIP file."""
+    session = requests.Session()
+    response = session.get(url)
+    response.raise_for_status()
+
+    soup = BeautifulSoup(response.content, 'html.parser')
+
+    # Create a temporary directory to store downloaded files
+    temp_dir = 'temp_webpage'
+    if not os.path.exists(temp_dir):
+        os.makedirs(temp_dir)
+
+    # Download and save the main HTML file
+    main_html_path = os.path.join(temp_dir, 'index.html')
+    with open(main_html_path, 'wb') as f:
+        f.write(response.content)
+
+    # Prepare a list of all assets to download
+    assets = []
+    for tag in soup.find_all(['img', 'link', 'script']):
+        if tag.name == 'img' and tag.get('src'):
+            assets.append(tag['src'])
+        elif tag.name == 'link' and tag.get('href'):
+            assets.append(tag['href'])
+        elif tag.name == 'script' and tag.get('src'):
+            assets.append(tag['src'])
+
+    # Download and save all assets
+    for asset in assets:
+        asset_url = urljoin(url, asset)
+        asset_path = urlparse(asset_url).path.lstrip('/')
+        asset_full_path = os.path.join(temp_dir, asset_path)
+
+        # Create directories if they don't exist
+        os.makedirs(os.path.dirname(asset_full_path), exist_ok=True)
+
+        # Download and save the asset
+        content = download_file(asset_url, session)
+        with open(asset_full_path, 'wb') as f:
+            f.write(content)
+
+    # Create a ZIP file
+    with ZipFile(output_zip, 'w') as zipf:
+        for root, _, files in os.walk(temp_dir):
+            for file in files:
+                file_path = os.path.join(root, file)
+                zipf.write(file_path, os.path.relpath(file_path, temp_dir))
+
+    # Clean up temporary directory
+    for root, _, files in os.walk(temp_dir, topdown=False):
+        for file in files:
+            os.remove(os.path.join(root, file))
+        os.rmdir(root)
+
+# Example usage
+url = 'http://example.com'
+output_zip = 'webpage.zip'
+save_webpage_as_zip(url, output_zip)