1. import argparse
  2. from bs4 import BeautifulSoup
  3. import requests
  5. def check_sandbox(url, sandbox_attributes=None):
  6. """
  7. Checks an HTML document for the presence of the 'sandbox' attribute.
  9. Args:
  10. url (str): The URL of the HTML document to check.
  11. sandbox_attributes (list, optional): A list of sandbox attributes to search for.
  12. Defaults to None (checks for the general 'sandbox' attribute).
  14. Returns:
  15. bool: True if a sandbox attribute is found, False otherwise. Returns None on error.
  16. """
  17. try:
  18. response = requests.get(url)
  19. response.raise_for_status() # Raise HTTPError for bad responses (4xx or 5xx)
  20. soup = BeautifulSoup(response.content, 'html.parser')
  22. if sandbox_attributes is None:
  23. # Check for the general 'sandbox' attribute
  24. for tag in soup.find_all():
  25. if 'sandbox' in tag.attrs:
  26. return True
  27. else:
  28. # Check for specified sandbox attributes
  29. for tag in soup.find_all():
  30. if 'sandbox' in tag.attrs and any(attr in tag.attrs['sandbox'] for attr in sandbox_attributes):
  31. return True
  32. return False
  33. except requests.exceptions.RequestException as e:
  34. print(f"Error fetching URL: {e}")
  35. return None # Indicate an error
  36. except Exception as e:
  37. print(f"Error parsing HTML: {e}")
  38. return None #Indicate an error
  42. if __name__ == '__main__':
  43. parser = argparse.ArgumentParser(description='Check HTML documents for sandbox usage.')
  44. parser.add_argument('url', help='The URL of the HTML document.')
  45. parser.add_argument('--sandbox', nargs='+', help='Specific sandbox attributes to search for (e.g., allow-scripts allow-forms).')
  46. args = parser.parse_args()
  48. result = check_sandbox(args.url, args.sandbox)
  50. if result is not None:
  51. if result:
  52. print("Sandbox attribute found.")
  53. else:
  54. print("No sandbox attribute found.")

Add your comment