1. def html_hash(html_string):
  2. """
  3. Generates a simple hash of an HTML document string.
  4. For development purposes only. Not cryptographically secure.
  5. """
  6. hash_value = 0
  7. for char in html_string:
  8. hash_value = (hash_value * 31 + ord(char)) % (2**32) # Simple polynomial hash
  9. return hash_value
  11. if __name__ == '__main__':
  12. html_doc1 = """
  13. <!DOCTYPE html>
  14. <html>
  15. <head>
  16. <title>Example 1</title>
  17. </head>
  18. <body>
  19. <h1>Hello, world!</h1>
  20. </body>
  21. </html>
  22. """
  23. html_doc2 = """
  24. <!DOCTYPE html>
  25. <html>
  26. <head>
  27. <title>Example 2</title>
  28. </head>
  29. <body>
  30. <h1>Hello, world!</h1>
  31. </body>
  32. </html>
  33. """
  34. html_doc3 = """
  35. <!DOCTYPE html>
  36. <html>
  37. <head>
  38. <title>Example 3</title>
  39. </head>
  40. <body>
  41. <h2>Another heading</h2>
  42. </body>
  43. </html>
  44. """
  46. hash1 = html_hash(html_doc1)
  47. hash2 = html_hash(html_doc2)
  48. hash3 = html_hash(html_doc3)
  50. print(f"Hash of doc1: {hash1}")
  51. print(f"Hash of doc2: {hash2}")
  52. print(f"Hash of doc3: {hash3}")
  54. #Test case for empty string
  55. html_doc4 = ""
  56. hash4 = html_hash(html_doc4)
  57. print(f"Hash of doc4: {hash4}")

Add your comment