1. from bs4 import BeautifulSoup
  3. def extract_html_values(html_content, tags_to_extract=None):
  4. """
  5. Extracts text values from HTML content.
  7. Args:
  8. html_content (str): The HTML content as a string.
  9. tags_to_extract (list, optional): A list of HTML tags to extract values from.
  10. If None, extracts from all tags. Defaults to None.
  12. Returns:
  13. dict: A dictionary where keys are tag names and values are lists of extracted text.
  14. Returns an empty dictionary if html_content is empty or invalid.
  15. """
  16. if not html_content:
  17. return {}
  19. soup = BeautifulSoup(html_content, 'html.parser')
  20. extracted_data = {}
  22. if tags_to_extract is None:
  23. tags_to_extract = soup.find_all() # Extract from all tags if none specified
  25. for tag in tags_to_extract:
  26. tag_name = tag.name
  27. text = tag.get_text(strip=True) # Extract text, removing leading/trailing whitespace
  28. if text:
  29. if tag_name not in extracted_data:
  30. extracted_data[tag_name] = []
  31. extracted_data[tag_name].append(text)
  33. return extracted_data
  36. if __name__ == '__main__':
  37. # Example Usage
  38. html = """
  39. <html>
  40. <head>
  41. <title>My Webpage</title>
  42. </head>
  43. <body>
  44. <h1>Heading</h1>
  45. <p>This is a paragraph.</p>
  46. <a href="https://example.com">Link</a>
  47. <ul>
  48. <li>Item 1</li>
  49. <li>Item 2</li>
  50. </ul>
  51. </body>
  52. </html>
  53. """
  55. # Extract all values
  56. all_values = extract_html_values(html)
  57. print("All Values:", all_values)
  59. # Extract only paragraph and link values
  60. paragraph_link_values = extract_html_values(html, ['p', 'a'])
  61. print("\nParagraph and Link Values:", paragraph_link_values)

Add your comment