1. import time
  2. from bs4 import BeautifulSoup
  3. import requests
  4. import logging
  6. # Configure logging
  7. logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
  9. def wrap_html_task(html_content, task_function, timeout=10, retries=3):
  10. """
  11. Wraps an HTML document processing task with timeout and retry logic.
  13. Args:
  14. html_content (str): The HTML content to process.
  15. task_function (callable): The function to apply to the HTML content.
  16. Should accept the HTML content as input.
  17. timeout (int): Timeout in seconds for the task.
  18. retries (int): Number of retries if the task fails.
  20. Returns:
  21. The result of the task_function if successful, None otherwise.
  22. """
  23. for attempt in range(retries):
  24. try:
  25. # Start timer
  26. start_time = time.time()
  28. # Execute the task
  29. result = task_function(html_content)
  31. # Check if the task completed within the timeout
  32. if time.time() - start_time > timeout:
  33. logging.error(f"Task timed out after {timeout} seconds. Attempt: {attempt + 1}")
  34. continue # Retry
  36. return result # Return result if successful
  38. except Exception as e:
  39. logging.error(f"Task failed on attempt {attempt + 1}: {e}")
  40. if attempt < retries - 1:
  41. logging.warning(f"Retrying... Attempt: {attempt + 1}")
  42. time.sleep(2) # Wait before retrying
  43. else:
  44. logging.error("Task failed after all retries.")
  45. return None # Return None if all retries fail
  47. def example_task(html):
  48. """
  49. Example task function to extract title from HTML.
  50. Simulates a potentially slow task.
  51. """
  52. try:
  53. soup = BeautifulSoup(html, 'html.parser')
  54. title = soup.title.string if soup.title else "No Title"
  55. return title
  56. except Exception as e:
  57. logging.error(f"Error extracting title: {e}")
  58. return None
  61. if __name__ == '__main__':
  62. # Example Usage
  63. html_example = """
  64. <html>
  65. <head>
  66. <title>My Webpage</title>
  67. </head>
  68. <body>
  69. <h1>Hello World</h1>
  70. </body>
  71. </html>
  72. """
  74. title = wrap_html_task(html_example, example_task)
  76. if title:
  77. print(f"Extracted Title: {title}")
  78. else:
  79. print("Failed to extract title.")
  81. # Example with a failing task (simulated)
  82. def failing_task(html):
  83. raise ValueError("Simulated error in task")
  85. result = wrap_html_task(html_example, failing_task)
  87. if result:
  88. print(f"Task Result: {result}")
  89. else:
  90. print("Task failed.")

Add your comment