1. from bs4 import BeautifulSoup
  3. def split_html_data(html_string, split_by="div"):
  4. """
  5. Splits HTML data into a list of strings based on the specified tag.
  6. Returns a list of strings.
  7. """
  8. try:
  9. soup = BeautifulSoup(html_string, 'html.parser')
  11. if split_by == "div":
  12. # Split by <div> tags
  13. elements = soup.find_all('div')
  14. data_list = [str(element) for element in elements]
  15. elif split_by == "p":
  16. # Split by <p> tags
  17. elements = soup.find_all('p')
  18. data_list = [str(element) for element in elements]
  19. else:
  20. raise ValueError("Invalid split_by tag. Choose 'div' or 'p'.")
  22. return data_list
  23. except Exception as e:
  24. print(f"Error splitting HTML: {e}")
  25. return [] # Return an empty list on error
  29. if __name__ == '__main__':
  30. # Example Usage:
  31. html_data = """
  32. <div>
  33. <p>This is the first paragraph.</p>
  34. <p>This is the second paragraph.</p>
  35. </div>
  36. <div>
  37. <p>Another paragraph.</p>
  38. </div>
  39. """
  41. split_data = split_html_data(html_data, split_by="div")
  42. print(split_data)
  44. split_data = split_html_data(html_data, split_by="p")
  45. print(split_data)
  47. #Example with invalid split
  48. split_data = split_html_data(html_data, split_by="span")
  49. print(split_data)

Add your comment