Package com.crawljax.core.configuration

Examples of com.crawljax.core.configuration.CrawljaxConfiguration$CrawljaxConfigurationBuilder

23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
    CrawlSpecification spec = new CrawlSpecification(Utils.URL);
    spec.setMaximumStates(5);
    spec.clickDefaultElements();

    CrawljaxConfiguration config = new CrawljaxConfiguration();
    config.setBrowser(BrowserType.firefox);
    config.setCrawlSpecification(spec);

    SaveCrawlSession saveCrawlSessionPlugin = new SaveCrawlSession(Utils.SESSION_XML);
    saveCrawlSessionPlugin.setOutputFolder(Utils.OUTPUTFOLDER);
    config.addPlugin(saveCrawlSessionPlugin);

    try {
      CrawljaxController controller = new CrawljaxController(config);
      controller.run();
    } catch (ConfigurationException e) {
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
  private MetricRegistry registry;

  @Before
  public void setup() {
    registry = new MetricRegistry();
    CrawljaxConfiguration config = CrawljaxConfiguration.builderFor("http://localhost")
            .addPlugin(domChange, browserCreatedPlugin,
                    fireEventFailedPlugin, invariantViolationPlugin, newStatePlugin,
                    onRevisitStatePlugin,
                    urlLoadPlugin, postCrawlingPlugin, prestatePlugin).build();
    plugins = new Plugins(config, registry);
View Full Code Here
112
113
114
115
116
117
118
119
120
121
122
123
    when(formHandlerFactory.newFormHandler(browser)).thenReturn(formHandler);
    url = new URL("http://example.com");
    when(browser.getCurrentUrl()).thenReturn(url.toExternalForm());
    when(sessionProvider.get()).thenReturn(session);

    CrawljaxConfiguration config = Mockito.spy(CrawljaxConfiguration.builderFor(url).build());
    stateComparator = new StateComparator(config.getCrawlRules());

    when(extractor.extract(target)).thenReturn(ImmutableList.of(action));
    when(graphProvider.get()).thenReturn(graph);

    context =
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
  public void testIframeExclusions() throws CrawljaxException {
    CrawljaxConfigurationBuilder builder = setupConfig();
    builder.crawlRules().dontCrawlFrame("frame1");
    builder.crawlRules().dontCrawlFrame("sub");
    builder.crawlRules().dontCrawlFrame("frame0");
    CrawljaxConfiguration config = builder.build();
    crawljax = new CrawljaxRunner(config);
    CrawlSession session = crawljax.call();
    assertThat(session.getStateFlowGraph(), hasEdges(3));
    assertThat(session.getStateFlowGraph(), hasStates(4));
  }
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
  public void testExtract() throws InterruptedException, CrawljaxException {
    CrawljaxConfigurationBuilder builder =
            CrawljaxConfiguration.builderFor(DEMO_SITE_SERVER.getSiteUrl().toExternalForm());
    builder.crawlRules().click("a");
    builder.crawlRules().clickOnce(true);
    CrawljaxConfiguration config = builder.build();

    CandidateElementExtractor extractor = newElementExtractor(config);
    browser.goToUrl(DEMO_SITE_SERVER.getSiteUrl());
    List<CandidateElement> candidates = extractor.extract(DUMMY_STATE);
View Full Code Here
94
95
96
97
98
99
100
101
102
103
104
    CrawljaxConfigurationBuilder builder =
            CrawljaxConfiguration.builderFor(DEMO_SITE_SERVER.getSiteUrl().toExternalForm());
    builder.crawlRules().click("a");
    builder.crawlRules().dontClick("div").withAttribute("id", "menubar");
    builder.crawlRules().clickOnce(true);
    CrawljaxConfiguration config = builder.build();

    CandidateElementExtractor extractor = newElementExtractor(config);
    browser.goToUrl(DEMO_SITE_SERVER.getSiteUrl());

    List<CandidateElement> candidates = extractor.extract(DUMMY_STATE);
View Full Code Here
114
115
116
117
118
119
120
121
122
123
124
    server.before();
    CrawljaxConfigurationBuilder builder =
            CrawljaxConfiguration
                    .builderFor(server.getSiteUrl().toExternalForm() + "iframe/");
    builder.crawlRules().click("a");
    CrawljaxConfiguration config = builder.build();

    CandidateElementExtractor extractor = newElementExtractor(config);
    browser.goToUrl(new URL(server.getSiteUrl().toExternalForm() + "iframe/"));
    List<CandidateElement> candidates = extractor.extract(DUMMY_STATE);
View Full Code Here
242
243
244
245
246
247
248
249
250
251
252
   * Make sure On new State Plugin executed.
   */
  @Test
  public void testOnNewStatePlugin() {
    hit = false;
    CrawljaxConfiguration config = CrawljaxConfiguration.builderFor(
            "http://localhost").addPlugin(new OnNewStatePlugin() {

      @Override
      public void onNewState(CrawlerContext context, StateVertex state) {
        hit = true;
View Full Code Here
15
16
17
18
19
20
21
22
23
24
25
26
27
28
  public static void main(String[] args) {

    try {
      // configure the crawling engine
      CrawljaxConfiguration config = getConfig();

      // add your plugin
      config.addPlugin(new SamplePlugin());

      // initilize and run Crawljax
      CrawljaxController crawljax = new CrawljaxController(config);
      crawljax.run();
View Full Code Here
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
  /**
   * Configure Crawljax to crawl Google.
   */
  private static CrawljaxConfiguration getConfig() {
    CrawljaxConfiguration config = new CrawljaxConfiguration();
    config.setBrowser(BrowserType.firefox);

    CrawlSpecification crawler = new CrawlSpecification("http://www.google.com");
    crawler.setWaitTimeAfterEvent(500);
    crawler.setWaitTimeAfterReloadUrl(500);

    // click on all anchor tags
    crawler.click("a");
    // and all input tags with "submit"
    crawler.click("input").withAttribute("type", "submit");

    // exclude these
    crawler.dontClick("a").underXPath("//DIV[@id='guser']");
    crawler.dontClick("a").withText("Language Tools");

    InputSpecification inputSpec = new InputSpecification();
    inputSpec.field("q").setValue("Crawljax");
    crawler.setInputSpecification(inputSpec);

    // Constrain the crawl to Google (no other web sites)
    crawler.addCrawlCondition("Only crawl Google", new UrlCondition("google"));

    // limit the crawling scope
    crawler.setMaximumStates(6);
    crawler.setDepth(2);

    config.setCrawlSpecification(crawler);

    return config;
  }
View Full Code Here
TOP

Related Classes of com.crawljax.core.configuration.CrawljaxConfiguration$CrawljaxConfigurationBuilder

  • $.CrawljaxRunner
  • com.crawljax.condition.eventablecondition.EventableCondition
  • com.crawljax.core.CandidateElementExtractorTest
  • com.crawljax.core.CrawlControllerTest
  • com.crawljax.core.CrawlerTest
  • com.crawljax.core.IFrameTest
  • com.crawljax.core.plugin.Plugins
  • com.crawljax.core.plugin.PluginsTest
  • com.crawljax.core.state.StateMachineTest
  • com.crawljax.crawljax_plugins_plugin.SampleCrawler
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.