1. import java.io.BufferedReader;
  2. import java.io.IOException;
  3. import java.io.InputStreamReader;
  4. import java.net.URL;
  5. import java.net.URLConnection;
  6. import java.util.HashMap;
  7. import java.util.Map;
  8. import java.util.logging.Logger;
  10. public class HTMLResourceSync {
  12. private static final Logger logger = Logger.getLogger(HTMLResourceSync.class.getName());
  14. public static void main(String[] args) throws IOException {
  15. // Define the URLs to sync
  16. String url1 = "http://example.com/page1.html"; // Replace with your first URL
  17. String url2 = "http://example.com/page2.html"; // Replace with your second URL
  19. // Perform synchronization
  20. syncResources(url1, url2);
  21. }
  23. public static void syncResources(String url1, String url2) throws IOException {
  24. logger.info("Starting resource synchronization...");
  26. // Get resources from the first URL
  27. Map<String, String> resources1 = getResources(url1);
  28. logger.info("Resources retrieved from " + url1 + ": " + resources1.size());
  30. // Get resources from the second URL
  31. Map<String, String> resources2 = getResources(url2);
  32. logger.info("Resources retrieved from " + url2 + ": " + resources2.size());
  34. // Compare and update resources in the second URL based on the first
  35. updateResources(url2, resources1, resources2);
  36. logger.info("Synchronization completed.");
  37. }
  39. private static Map<String, String> getResources(String url) throws IOException {
  40. logger.info("Fetching resources from: " + url);
  41. URL urlObj = new URL(url);
  42. URLConnection connection = urlObj.openConnection();
  43. connection.setConnectTimeout(5000); // Set a timeout for connection
  44. connection.setReadTimeout(10000); // Set a timeout for reading
  46. try (BufferedReader reader = new BufferedReader(new InputStreamReader(connection.getInputStream()))) {
  47. StringBuilder html = new StringBuilder();
  48. String line;
  49. while ((line = reader.readLine()) != null) {
  50. html.append(line).append("\n");
  51. }
  52. } catch (IOException e) {
  53. logger.error("Error fetching resources from " + url + ": " + e.getMessage());
  54. return new HashMap<>(); // Return empty map on error
  55. }
  57. Map<String, String> resources = new HashMap<>();
  58. // Simple resource extraction (can be improved with regex)
  59. for (String line : html.toString().split("\\s+")) {
  60. if (line.startsWith("href=")) {
  61. String resource = line.substring(5).trim();
  62. resources.put(resource, "present"); // Indicate resource is present
  63. } else if (line.startsWith("src=")) {
  64. String resource = line.substring(5).trim();
  65. resources.put(resource, "present");
  66. }
  67. }
  68. return resources;
  69. }
  71. private static void updateResources(String url2, Map<String, String> resources1, Map<String, String> resources2) throws IOException {
  72. logger.info("Updating resources in: " + url2);
  73. // Iterate through resources from the first URL and update the second URL
  74. for (Map.Entry<String, String> entry : resources1.entrySet()) {
  75. String resource = entry.getKey();
  76. if (!resources2.containsKey(resource)) {
  77. // Resource is missing in the second URL, so add it
  78. logger.info("Adding resource: " + resource + " to " + url2);
  79. // In a real application, you would update the HTML content of url2 here
  80. // For this example, we just log the addition
  81. } else {
  82. // Resource exists in the second URL, check if content are different
  83. // In a real application, you would compare the content of the resource
  84. // and update it if necessary
  85. logger.info("Resource " + resource + " already exists in " + url2);
  87. }
  88. }
  89. }
  90. }

Add your comment