This project has retired. For details please refer to its Attic page.
SiteCrawlerTest xref
View Javadoc
1   /*
2    * Licensed to the Apache Software Foundation (ASF) under one or more
3    * contributor license agreements.  See the NOTICE file distributed with
4    * this work for additional information regarding copyright ownership.
5    * The ASF licenses this file to You under the Apache License, Version 2.0
6    * (the "License"); you may not use this file except in compliance with
7    * the License.  You may obtain a copy of the License at
8    *
9    *  http://www.apache.org/licenses/LICENSE-2.0
10   *
11   * Unless required by applicable law or agreed to in writing, software
12   * distributed under the License is distributed on an "AS IS" BASIS,
13   * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14   * See the License for the specific language governing permissions and
15   * limitations under the License.
16   */
17  
18  package org.apache.any23.plugin.crawler;
19  
20  import edu.uci.ics.crawler4j.crawler.Page;
21  import org.apache.any23.Any23OnlineTestBase;
22  import org.junit.Assert;
23  import org.junit.Test;
24  import org.slf4j.Logger;
25  import org.slf4j.LoggerFactory;
26  
27  import java.io.File;
28  import java.net.URL;
29  import java.util.HashSet;
30  import java.util.Set;
31  import java.util.Iterator;
32  
33  /**
34   * Test case for {@link SiteCrawler}.
35   *
36   * @author Michele Mostarda (mostarda@fbk.eu)
37   */
38  public class SiteCrawlerTest extends Any23OnlineTestBase {
39  
40      public static final Logger logger = LoggerFactory.getLogger(SiteCrawlerTest.class);
41  
42      /**
43       * Tests the main crawler use case.
44       *
45       * @throws Exception if there is an error asserting test data
46       */
47      @Test
48      public void testSiteCrawling() throws Exception {
49          assumeOnlineAllowed();
50  
51          File tmpFile = File.createTempFile("site-crawler-test", ".storage");
52          tmpFile.delete();
53  
54          final SiteCrawler controller = new SiteCrawler(tmpFile);
55          controller.setMaxPages(100);
56          logger.info("Crawler4j: Setting max num of pages to: " + controller.getMaxPages());
57          controller.setPolitenessDelay(500);
58          logger.info("Crawler4j: Setting Politeness delay to: " + controller.getPolitenessDelay() + "ms");
59  
60          final Set<String> distinctPages = new HashSet<String>();
61          controller.addListener(new CrawlerListener() {
62              @Override
63              public void visitedPage(Page page) {
64                  distinctPages.add( page.getWebURL().getURL() );
65                  Iterator<String> it = distinctPages.iterator();
66                  while (it.hasNext()) {
67                      logger.info("Crawler4j: Fetching page - " + it.next());
68                  }
69              }
70          });
71  
72          controller.start( new URL("http://any23.apache.org/"), false);
73  
74          synchronized (this) {
75              this.wait(15 * 1000);
76          }
77          controller.stop();
78  
79          logger.info("Distinct pages: " + distinctPages.size());
80          Assert.assertTrue("Expected some page crawled.", distinctPages.size() > 0);
81      }
82  
83  }