1. import requests
  2. from bs4 import BeautifulSoup
  3. import logging
  4. import jsonschema
  5. import json
  7. # Configure logging
  8. logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
  11. def validate_html(html_content, schema_path):
  12. """
  13. Validates HTML content against a JSON schema.
  15. Args:
  16. html_content (str): The HTML content to validate.
  17. schema_path (str): Path to the JSON schema file.
  19. Returns:
  20. bool: True if the HTML is valid, False otherwise.
  21. """
  22. try:
  23. # Load the schema
  24. with open(schema_path, 'r') as f:
  25. schema = json.load(f)
  27. # Parse the HTML content
  28. soup = BeautifulSoup(html_content, 'html.parser')
  30. # Extract relevant data from the parsed HTML (customize based on your needs)
  31. # This is a placeholder; adapt to extract data specific to your schema.
  32. extracted_data = {
  33. 'title': soup.title.text if soup.title else None,
  34. 'headings': [h.text for h in soup.find_all(['h1', 'h2', 'h3'])]
  35. }
  37. # Validate the extracted data against the schema
  38. jsonschema.validate(instance=extracted_data, schema=schema)
  39. logging.info("HTML validation successful.")
  40. return True
  42. except jsonschema.exceptions.ValidationError as e:
  43. logging.error(f"HTML validation failed: {e}")
  44. return False
  45. except FileNotFoundError:
  46. logging.error(f"Schema file not found: {schema_path}")
  47. return False
  48. except Exception as e:
  49. logging.error(f"An unexpected error occurred: {e}")
  50. return False
  53. def validate_url(url, schema_path):
  54. """
  55. Fetches HTML from a URL and validates it against a JSON schema.
  57. Args:
  58. url (str): The URL to fetch and validate.
  59. schema_path (str): Path to the JSON schema file.
  61. Returns:
  62. bool: True if the HTML is valid, False otherwise.
  63. """
  64. try:
  65. response = requests.get(url)
  66. response.raise_for_status() # Raise HTTPError for bad responses (4xx or 5xx)
  67. html_content = response.text
  69. return validate_html(html_content, schema_path)
  71. except requests.exceptions.RequestException as e:
  72. logging.error(f"Error fetching URL {url}: {e}")
  73. return False
  74. except Exception as e:
  75. logging.error(f"An unexpected error occurred: {e}")
  76. return False
  80. if __name__ == '__main__':
  81. # Example usage
  82. url_to_validate = "https://www.example.com" # Replace with your URL
  83. schema_file = "schema.json" # Replace with your schema file
  85. # Validate a URL
  86. if validate_url(url_to_validate, schema_file):
  87. print(f"URL {url_to_validate} is valid.")
  88. else:
  89. print(f"URL {url_to_validate} is invalid.")
  91. # Example with local HTML content
  92. html_content = """
  93. <html>
  94. <head>
  95. <title>My Page</title>
  96. </head>
  97. <body>
  98. <h1>Hello</h1>
  99. <h2>World</h2>
  100. </body>
  101. </html>
  102. """
  104. if validate_html(html_content, schema_file):
  105. print("Local HTML is valid.")
  106. else:
  107. print("Local HTML is invalid.")

Add your comment