Examples of Extractor

Examples of barrysoft.web.Extractor

18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
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
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
public class ExtractionTest {
 
  @Test
  public void testExtract() {
   
    Extractor search = new Extractor();
   
    search.getParser().setName("ITSA Search");
   
    ParserRule inr = new ParserRule("(?i)(?s).*?<a href=\"([^<>]+)\">\\s[series]</a>.*?");
    inr.setQuickRule(" [series]<");
    inr.setGroupName("season link", 0);
    inr.addParam(new ParserRuleParam("series", "How I Met Your Mother"));
   
    search.getParser().addRule(inr);
    try {
      search.getDownloader().setUrl("http://www.italiansubs.net/index.php?option=com_remository");
    } catch (MalformedURLException e) {
      fail(e.getMessage());
    }
   
    Extractor season = new Extractor();
   
    season.getParser().setName("ITSA Season");
   
    ParserRule outr = new ParserRule("(?i)(?s).*?<a href=\"([^<>]+)\">\\s[season]</a>.*?");
    outr.setQuickRule(" [season]<");
    outr.setGroupName("episodes link", 0);
    //outr.addParam(new ParserRuleParam("season", "Stagione 2"));
   
    season.getParser().addRule(outr);
   
    Extractor episode = new Extractor();
   
    episode.getParser().setName("ITSA Episode");
   
    outr = new ParserRule("(?i)(?s).*?<a href=\"([^<>]+)\">[episode]</a>.*?");
    outr.setQuickRule("[episode]<");
    outr.setGroupName("subtitle link", 0);
    //outr.addParam(new ParserRuleParam("episode", "How I Met Your Mother 2x06"));
   
    episode.getParser().addRule(outr);
   
    ExtractionJob job = new ExtractionJob("Get ITSA subtitle link");
   
    ExtractionStep estep = new ExtractionStep("Get season's page", search, season);
    estep.connect("season link", ExtractionStep.URL_BINDING);
    job.addStep(estep);
   
    estep = new ExtractionStep("Get subtitle's page", season, episode);
    estep.connect("episodes link", ExtractionStep.URL_BINDING);
    job.addStep(estep);
   
    try {
      job.execute();
    } catch (IllegalStateException e) {
      fail(e.getMessage());
    } catch (MalformedURLException e) {
      fail(e.getMessage());
    } catch (IOException e) {
      fail(e.getMessage());
    }
   
    String[] link;
    try {
      link = episode.getParser().getRule(0).getResults("subtitle link");
      assertEquals(1, link.length);
      System.out.println(link[0]);
    } catch (IndexOutOfBoundsException e) {
      fail(e.getMessage());
    } catch (NoSuchElementException e) {
View Full Code Here

Examples of com.ontometrics.scraper.extraction.Extractor

80
81
82
83
84
85
86
  private URL baseUrl;

  private String sessionIDName;

  public Scraper() {
    this.extractor = new Extractor();
  }
View Full Code Here

Examples of de.jetwick.tw.Extractor

99
100
101
102
103
104
105
106
107
108
109
            int counter = 0;

            @Override
            public String getObject() {
                return new Extractor() {

                    @Override
                    public String createTagMarkup(String tag, String cleanTag) {
//                        String url = Helper.TSURL + cleanTag;
                        return "<a class=\"i-tw-link tw-tag\" "
View Full Code Here

Examples of de.jetwick.tw.Extractor

121
122
123
124
125
126
127
128
129
130
131
                        final JTweet tweet = (JTweet) item.getModelObject();
                        final Label label = new Label("tweet", new Model<String>() {

                            @Override
                            public String getObject() {
                                return new Extractor().setTweet(tweet).setText(tweet.getText()).run().toString();
//                                return tweet.getText();
                            }
                        });
                        label.setEscapeModelStrings(false);
                        item.add(label);
View Full Code Here

Examples of de.jetwick.tw.Extractor

43
44
45
46
47
48
49
50
51
52
53
                        tw.getFromUser().getScreenName()));

                item.add(new ExternalLink("statusLink",
                        Helper.toTwitterHref(tw.getFromUser().getScreenName(), tw.getTwitterId())));

                Label label = new Label("tweetText", new Extractor().setTweet(tw).run().toString());
                label.setEscapeModelStrings(false);
                item.add(label);
            }
        });
    }
View Full Code Here

Examples of de.jetwick.tw.Extractor

606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
    public Collection<JTweet> findRetweets(Map<Long, JTweet> tweets, final Map<String, JUser> userMap) {
        // 1. check if tweets contains originals which were retweeted -> only done for 'tweets'
        // 2. check if tweets contains retweets -> done for 'tweets' and for tweets in solr

        final Set<JTweet> updatedTweets = new LinkedHashSet<JTweet>();
        Extractor extractor = new Extractor() {

            @Override
            public boolean onNewUser(int index, String user) {
                boolean isRetweet = index >= 3 && text.substring(index - 3, index).equalsIgnoreCase("rt ");
                if (isRetweet) {
                    user = user.toLowerCase();
                    JUser existingUser = userMap.get(user);
                    JTweet resTw = null;

                    // check ifRetweetOf against local tweets
                    if (existingUser != null)
                        for (JTweet tmp : existingUser.getOwnTweets()) {
                            if (tmp.getCreatedAt().getTime() < tweet.getCreatedAt().getTime()
                                    && tweet.isRetweetOf(tmp)) {
                                if (addReplyNoTricks(tmp, tweet)) {
                                    resTw = tmp;
                                    break;
                                }
                            }
                        }

                    // check ifRetweetOf against tweets existing in index
                    if (resTw == null)
                        resTw = connectToOrigTweet(tweet, user);

                    if (resTw != null) {
                        updatedTweets.add(resTw);
                        return false;
                    }
                }

                // break loop of Extractor because we only need the first user!
                return true;
            }
        };

        for (JTweet tw : tweets.values()) {
            if (tw.isRetweet()) {
                extractor.setTweet(tw).run();
            }
        }
        return updatedTweets;
    }
View Full Code Here

Examples of edu.stanford.nlp.ie.machinereading.Extractor

32
33
34
35
36
37
38
39
40
41
42
  public RelationExtractorAnnotator(Properties props){
    verbose = Boolean.parseBoolean(props.getProperty("sup.relation.verbose", "false"));
    String relationModel = props.getProperty("sup.relation.model", DefaultPaths.DEFAULT_SUP_RELATION_EX_RELATION_MODEL);
    try {
      Extractor entityExtractor = new RothEntityExtractor();
      BasicRelationExtractor relationExtractor = BasicRelationExtractor.load(relationModel);
     
      System.err.println("Loading relation model from " + relationModel);
      mr = MachineReading.makeMachineReadingForAnnotation(new RothCONLL04Reader(), entityExtractor, relationExtractor, null, null,
          null, true, verbose);
View Full Code Here

Examples of net.sf.cannagrower.data.hardware.Extractor

53
54
55
56
57
58
59
60
61
62
63
      culture=new Culture(repository);

      culture.getHardwares().store(new Room());
      culture.getHardwares().store(new Lamp());
      culture.getHardwares().store(new Intractor());
      culture.getHardwares().store(new Extractor());
      culture.getHardwares().store(new MediumSoil());
     
      plantation=new Plantation(culture);
     
      event=new net.sf.cannagrower.data.event.PlantsAdd();
View Full Code Here

Examples of org.apache.any23.extractor.Extractor

45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
public class ExtractionExceptionTest {

    @Test
    public void testPrintStackTrace() throws ExtractionException, IOException {
        final String FAKE_EXTRACTOR_NAME = "fake-extractor-name";
        final Extractor extractor = mock(Extractor.class);
        final ExtractorDescription ed = mock(ExtractorDescription.class);
        when(ed.getExtractorName()).thenReturn(FAKE_EXTRACTOR_NAME);
        when(extractor.getDescription()).thenReturn(ed);

        final TripleHandler th = mock(TripleHandler.class);
        final ExtractionContext extractionContext = new ExtractionContext(
                extractor.getDescription().getExtractorName(),
                new URIImpl("http://fake.document.uri")
        );
        final ExtractionResult er = new ExtractionResultImpl(extractionContext, extractor, th);
        er.notifyIssue(IssueReport.IssueLevel.Fatal  , "Fake fatal error.", 1, 2);
        er.notifyIssue(IssueReport.IssueLevel.Error  , "Fake error."      , 3, 4);
View Full Code Here

Examples of org.apache.jmeter.extractor.Extractor

120
121
122
123
124
125
126
127
128
129
130
131
        }
    }

    private String process(String textToParse) {
        List<String> result = new ArrayList<String>();
        Extractor extractor = HtmlExtractor.getExtractorImpl(cssJqueryLabeledChoice.getText());
        final int nbFound = extractor.extract(
                cssJqueryField.getText(), attributeField.getText(), -1, textToParse, result, 0, null);

        // Construct a multi-line string with all matches
        StringBuilder sb = new StringBuilder();
        sb.append("Match count: ").append(nbFound).append("\n");
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.