Update example URLs to use https instead of http.

These sites all redirect http requests to the corresponding https equivalent, so to make test and examples work better, update the URLs used to request https in the first place:

http://www.ics.uci.edu
http://www.cnn.com
http://www.wikipedia.org

README.md

@@ -92,14 +92,14 @@ public class MyCrawler extends WebCrawler {
      * the given url should be crawled or not (based on your crawling logic).
      * In this example, we are instructing the crawler to ignore urls that
      * have css, js, git, ... extensions and to only accept urls that start
-     * with "http://www.ics.uci.edu/". In this case, we didn't need the
+     * with "https://www.ics.uci.edu/". In this case, we didn't need the
      * referringPage parameter to make the decision.
      */
      @Override
      public boolean shouldVisit(Page referringPage, WebURL url) {
          String href = url.getURL().toLowerCase();
          return !FILTERS.matcher(href).matches()
-                && href.startsWith("http://www.ics.uci.edu/");
+                && href.startsWith("https://www.ics.uci.edu/");
      }
 
      /**
@@ -158,9 +158,9 @@ public class Controller {
          * URLs that are fetched and then the crawler starts following links
          * which are found in these pages
          */
-        controller.addSeed("http://www.ics.uci.edu/~lopes/");
-        controller.addSeed("http://www.ics.uci.edu/~welling/");
-    	controller.addSeed("http://www.ics.uci.edu/");
+        controller.addSeed("https://www.ics.uci.edu/~lopes/");
+        controller.addSeed("https://www.ics.uci.edu/~welling/");
+    	controller.addSeed("https://www.ics.uci.edu/");
 
         /*
          * Start the crawl. This is a blocking operation, meaning that your code

crawler4j-examples/crawler4j-examples-base/src/test/java/edu/uci/ics/crawler4j/examples/basic/BasicCrawlController.java

@@ -111,9 +111,9 @@ public static void main(String[] args) throws Exception {
      * URLs that are fetched and then the crawler starts following links
      * which are found in these pages
      */
-        controller.addSeed("http://www.ics.uci.edu/");
-        controller.addSeed("http://www.ics.uci.edu/~lopes/");
-        controller.addSeed("http://www.ics.uci.edu/~welling/");
+        controller.addSeed("https://www.ics.uci.edu/");
+        controller.addSeed("https://www.ics.uci.edu/~lopes/");
+        controller.addSeed("https://www.ics.uci.edu/~welling/");
 
     /*
      * Start the crawl. This is a blocking operation, meaning that your code

crawler4j-examples/crawler4j-examples-base/src/test/java/edu/uci/ics/crawler4j/examples/basic/BasicCrawler.java

@@ -47,7 +47,7 @@ public boolean shouldVisit(Page referringPage, WebURL url) {
         }
 
         // Only accept the url if it is in the "www.ics.uci.edu" domain and protocol is "http".
-        return href.startsWith("http://www.ics.uci.edu/");
+        return href.startsWith("https://www.ics.uci.edu/");
     }
 
     /**

crawler4j-examples/crawler4j-examples-base/src/test/java/edu/uci/ics/crawler4j/examples/localdata/LocalDataCollectorController.java

@@ -53,7 +53,7 @@ public static void main(String[] args) throws Exception {
         RobotstxtServer robotstxtServer = new RobotstxtServer(robotstxtConfig, pageFetcher);
         CrawlController controller = new CrawlController(config, pageFetcher, robotstxtServer);
 
-        controller.addSeed("http://www.ics.uci.edu/");
+        controller.addSeed("https://www.ics.uci.edu/");
         controller.start(LocalDataCollectorCrawler.class, numberOfCrawlers);
 
         List<Object> crawlersLocalData = controller.getCrawlersLocalData();

crawler4j-examples/crawler4j-examples-base/src/test/java/edu/uci/ics/crawler4j/examples/localdata/LocalDataCollectorCrawler.java

@@ -45,7 +45,7 @@ public LocalDataCollectorCrawler() {
     @Override
     public boolean shouldVisit(Page referringPage, WebURL url) {
         String href = url.getURL().toLowerCase();
-        return !FILTERS.matcher(href).matches() && href.startsWith("http://www.ics.uci.edu/");
+        return !FILTERS.matcher(href).matches() && href.startsWith("https://www.ics.uci.edu/");
     }
 
     @Override

crawler4j-examples/crawler4j-examples-base/src/test/java/edu/uci/ics/crawler4j/examples/multiple/MultipleCrawlerController.java

@@ -77,20 +77,20 @@ public static void main(String[] args) throws Exception {
         CrawlController controller1 = new CrawlController(config1, pageFetcher1, robotstxtServer);
         CrawlController controller2 = new CrawlController(config2, pageFetcher2, robotstxtServer);
 
-        String[] crawler1Domains = {"http://www.ics.uci.edu/", "http://www.cnn.com/"};
-        String[] crawler2Domains = {"http://en.wikipedia.org/"};
+        String[] crawler1Domains = {"https://www.ics.uci.edu/", "https://www.cnn.com/"};
+        String[] crawler2Domains = {"https://en.wikipedia.org/"};
 
         controller1.setCustomData(crawler1Domains);
         controller2.setCustomData(crawler2Domains);
 
-        controller1.addSeed("http://www.ics.uci.edu/");
-        controller1.addSeed("http://www.cnn.com/");
-        controller1.addSeed("http://www.ics.uci.edu/~lopes/");
-        controller1.addSeed("http://www.cnn.com/POLITICS/");
+        controller1.addSeed("https://www.ics.uci.edu/");
+        controller1.addSeed("https://www.cnn.com/");
+        controller1.addSeed("https://www.ics.uci.edu/~lopes/");
+        controller1.addSeed("https://www.cnn.com/POLITICS/");
 
-        controller2.addSeed("http://en.wikipedia.org/wiki/Main_Page");
-        controller2.addSeed("http://en.wikipedia.org/wiki/Obama");
-        controller2.addSeed("http://en.wikipedia.org/wiki/Bing");
+        controller2.addSeed("https://en.wikipedia.org/wiki/Main_Page");
+        controller2.addSeed("https://en.wikipedia.org/wiki/Obama");
+        controller2.addSeed("https://en.wikipedia.org/wiki/Bing");
 
     /*
      * The first crawler will have 5 concurrent threads and the second

crawler4j-examples/crawler4j-examples-base/src/test/java/edu/uci/ics/crawler4j/examples/shutdown/BasicCrawler.java

@@ -39,7 +39,7 @@ public class BasicCrawler extends WebCrawler {
         ".*(\\.(css|js|bmp|gif|jpe?g|png|tiff?|mid|mp2|mp3|mp4|wav|avi|mov|mpeg|ram|m4v|pdf" +
         "|rm|smil|wmv|swf|wma|zip|rar|gz))$");
 
-    private static final String DOMAIN = "http://www.ics.uci.edu/";
+    private static final String DOMAIN = "https://www.ics.uci.edu/";
 
     @Override
     public boolean shouldVisit(Page referringPage, WebURL url) {

crawler4j-examples/crawler4j-examples-base/src/test/java/edu/uci/ics/crawler4j/examples/shutdown/ControllerWithShutdown.java

@@ -75,9 +75,9 @@ public static void main(String[] args) throws Exception {
      * URLs that are fetched and then the crawler starts following links
      * which are found in these pages
      */
-        controller.addSeed("http://www.ics.uci.edu/~welling/");
-        controller.addSeed("http://www.ics.uci.edu/~lopes/");
-        controller.addSeed("http://www.ics.uci.edu/");
+        controller.addSeed("https://www.ics.uci.edu/~welling/");
+        controller.addSeed("https://www.ics.uci.edu/~lopes/");
+        controller.addSeed("https://www.ics.uci.edu/");
 
     /*
      * Start the crawl. This is a blocking operation, meaning that your code

crawler4j-examples/crawler4j-examples-base/src/test/java/edu/uci/ics/crawler4j/examples/statushandler/StatusHandlerCrawlController.java

@@ -106,9 +106,9 @@ public static void main(String[] args) throws Exception {
      * URLs that are fetched and then the crawler starts following links
      * which are found in these pages
      */
-        controller.addSeed("http://www.ics.uci.edu/~welling/");
-        controller.addSeed("http://www.ics.uci.edu/~lopes/");
-        controller.addSeed("http://www.ics.uci.edu/");
+        controller.addSeed("https://www.ics.uci.edu/~welling/");
+        controller.addSeed("https://www.ics.uci.edu/~lopes/");
+        controller.addSeed("https://www.ics.uci.edu/");
 
     /*
      * Start the crawl. This is a blocking operation, meaning that your code

crawler4j-examples/crawler4j-examples-base/src/test/java/edu/uci/ics/crawler4j/examples/statushandler/StatusHandlerCrawler.java

@@ -45,7 +45,7 @@ public class StatusHandlerCrawler extends WebCrawler {
     @Override
     public boolean shouldVisit(Page referringPage, WebURL url) {
         String href = url.getURL().toLowerCase();
-        return !FILTERS.matcher(href).matches() && href.startsWith("http://www.ics.uci.edu/");
+        return !FILTERS.matcher(href).matches() && href.startsWith("https://www.ics.uci.edu/");
     }
 
     /**