1. import requests
  2. from bs4 import BeautifulSoup
  4. def strip_form_metadata(url, max_length=200, max_words=10):
  5. """
  6. Strips metadata from web forms on a given URL, limiting length and word count.
  8. Args:
  9. url (str): The URL of the webpage containing the form.
  10. max_length (int): Maximum character length of the stripped text.
  11. max_words (int): Maximum number of words in the stripped text.
  13. Returns:
  14. str: The stripped form text. Returns None if an error occurs.
  15. """
  16. try:
  17. response = requests.get(url)
  18. response.raise_for_status() # Raise HTTPError for bad responses (4xx or 5xx)
  20. soup = BeautifulSoup(response.content, 'html.parser')
  21. forms = soup.find_all('form')
  23. stripped_text = ""
  24. for form in forms:
  25. #Extract text from form elements
  26. form_text = form.get_text()
  28. #Strip metadata - remove leading/trailing whitespace and newlines
  29. form_text = form_text.strip()
  31. # Limit the length of the stripped text
  32. if len(form_text) > max_length:
  33. form_text = form_text[:max_length] + "..."
  35. # Limit the number of words
  36. words = form_text.split()
  37. if len(words) > max_words:
  38. form_text = " ".join(words[:max_words]) + "..."
  40. stripped_text += form_text + "\n" # Add newline between forms
  42. return stripped_text.strip() #remove trailing newline
  43. except requests.exceptions.RequestException as e:
  44. print(f"Error fetching URL: {e}")
  45. return None
  46. except Exception as e:
  47. print(f"An error occurred: {e}")
  48. return None
  52. if __name__ == '__main__':
  53. # Example Usage
  54. url = "https://www.example.com/form" # Replace with your target URL
  55. stripped_form = strip_form_metadata(url)
  57. if stripped_form:
  58. print(stripped_form)

Add your comment