Package org.apache.nutch.protocol

Examples of org.apache.nutch.protocol.Protocol

75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
  protected void tearDown() {}

  public void testIt() throws ProtocolException, ParseException {
    String urlString;
    Protocol protocol;
    Content content;
    Parse parse;
    Configuration conf = NutchConfiguration.create();

    for (int i = 0; i < sampleFiles.length; i++) {
      urlString = "file:" + sampleDir + fileSeparator + sampleFiles[i];

      protocol = new ProtocolFactory(conf).getProtocol(urlString);
      content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum()).getContent();

      parse = new ParseUtil(conf).parse(content).get(content.getUrl());

      String text = parse.getText().replaceAll("[ \t\r\n]+", " ").trim();
      assertTrue(sampleTexts[i].equals(text));
View Full Code Here
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
          try {
            LOG.info("fetching " + fit.url + " (queue crawl delay=" +
                      fetchQueues.getFetchItemQueue(fit.queueID).crawlDelay + "ms)");

            // fetch the page
            final Protocol protocol = this.protocolFactory.getProtocol(fit.url);
            final BaseRobotRules rules = protocol.getRobotRules(fit.url, fit.page);
            if (!rules.isAllowed(fit.u.toString())) {
              // unblock
              fetchQueues.finishFetchItem(fit, true);
              if (LOG.isDebugEnabled()) {
                LOG.debug("Denied by robots.txt: " + fit.url);
              }
              output(fit, null, ProtocolStatusUtils.STATUS_ROBOTS_DENIED,
                  CrawlStatus.STATUS_GONE);
              continue;
            }
            if (rules.getCrawlDelay() > 0) {
              if (rules.getCrawlDelay() > maxCrawlDelay && maxCrawlDelay >= 0) {
                // unblock
                fetchQueues.finishFetchItem(fit, true);
                LOG.debug("Crawl-Delay for " + fit.url + " too long (" + rules.getCrawlDelay() + "), skipping");
                output(fit, null, ProtocolStatusUtils.STATUS_ROBOTS_DENIED, CrawlStatus.STATUS_GONE);
                continue;
              } else {
                final FetchItemQueue fiq = fetchQueues.getFetchItemQueue(fit.queueID);
                fiq.crawlDelay = rules.getCrawlDelay();
                if (LOG.isDebugEnabled()) {
                  LOG.info("Crawl delay for queue: " + fit.queueID + " is set to " + fiq.crawlDelay + " as per robots.txt. url: " + fit.url);
                }
              }
            }
            final ProtocolOutput output = protocol.getProtocolOutput(fit.url, fit.page);
            final ProtocolStatus status = output.getStatus();
            final Content content = output.getContent();
            // unblock queue
            fetchQueues.finishFetchItem(fit);
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
86
   */
  public void setContentType(String testTextFile) throws ProtocolNotFound {
    String urlString = "file:" + sampleDir + fileSeparator + testTextFile;
    assertNotNull(urlString);
    WebPage datum = new WebPage();
    Protocol protocol = new ProtocolFactory(conf).getProtocol(urlString);
    ProtocolOutput output = protocol.getProtocolOutput(urlString,datum);
    assertNotNull(output);

    assertEquals("Status code: [" + output.getStatus().getCode()
        + "], not equal to: [" + ProtocolStatusCodes.SUCCESS + "]: args: ["
        + output.getStatus().getArgs() + "]", ProtocolStatusCodes.SUCCESS, output
View Full Code Here
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
   *           If the {@link Parser}Layer cannot be loaded.
   */
  @Test
  public void testParseFetchChannel() throws ProtocolNotFound, ParseException {
    String urlString;
    Protocol protocol;
    Content content;
    ParseResult parseResult;

    Configuration conf = NutchConfiguration.create();
    for (int i = 0; i < sampleFiles.length; i++) {
      urlString = "file:" + sampleDir + fileSeparator + sampleFiles[i];
      urlString = urlString.replace('\\', '/');

      protocol = new ProtocolFactory(conf).getProtocol(urlString);
      content = protocol.getProtocolOutput(new Text(urlString),
          new CrawlDatum()).getContent();

      parseResult = new ParseUtil(conf).parseByExtensionId("feed", content);

      assertEquals(3, parseResult.size());
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
    }

    IndexingFilters indexers = new IndexingFilters(conf);

    ProtocolFactory factory = new ProtocolFactory(conf);
    Protocol protocol = factory.getProtocol(url);

    WebPage page = new WebPage();
    page.setBaseUrl(new org.apache.avro.util.Utf8(url));
    ProtocolOutput protocolOutput = protocol.getProtocolOutput(url, page);
    page.setProtocolStatus(protocolOutput.getStatus());
    if (protocolOutput.getStatus().getCode() == ProtocolStatusCodes.SUCCESS) {
      page.setStatus(CrawlStatus.STATUS_FETCHED);
      page.setFetchTime(System.currentTimeMillis());
    } else {
View Full Code Here
104
105
106
107
108
109
110
111
112
113
114
115
116
117
    if (LOG.isInfoEnabled()) {
      LOG.info("fetching: " + url);
    }

    ProtocolFactory factory = new ProtocolFactory(conf);
    Protocol protocol = factory.getProtocol(url);
    WebPage page = new WebPage();
   
    ProtocolOutput protocolOutput = protocol.getProtocolOutput(url, page);
   
    if(!protocolOutput.getStatus().isSuccess()) {
      LOG.error("Fetch failed with protocol status: "
          + ProtocolStatusUtils.getName(protocolOutput.getStatus().getCode())
          + ": " + ProtocolStatusUtils.getMessage(protocolOutput.getStatus()));
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
  protected void tearDown() {}

  @Test
  public void testIt() throws ProtocolException, ParseException {
    String urlString;
    Protocol protocol;
    Content content;
    Parse parse;
    Configuration conf = NutchConfiguration.create();

    for (int i = 0; i < sampleFiles.length; i++) {
      urlString = "file:" + sampleDir + fileSeparator + sampleFiles[i];

      protocol = new ProtocolFactory(conf).getProtocol(urlString);
      content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum()).getContent();

      parse = new ParseUtil(conf).parse(content).get(content.getUrl());

      String text = parse.getText().replaceAll("[ \t\r\n]+", " ").trim();
      assertTrue(sampleTexts[i].equals(text));
View Full Code Here
79
80
81
82
83
84
85
86
87
    FileOutputStream fos = new FileOutputStream(tempFile);
    fos.write(expectedText.getBytes());
    fos.close();

    // get nutch content
    Protocol protocol = new ProtocolFactory(NutchConfiguration.create()).getProtocol(urlString);
    content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum()).getContent();
    protocol = null;
  }
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
  protected void tearDown() {}

  @Test
  public void testIt() throws ProtocolException, ParseException {
    String urlString;
    Protocol protocol;
    Content content;
    Parse parse;

    Configuration conf = NutchConfiguration.create();
    for (int i = 0; i < sampleFiles.length; i++) {
      urlString = "file:" + sampleDir + fileSeparator + sampleFiles[i];

      protocol = new ProtocolFactory(conf).getProtocol(urlString);
      content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum()).getContent();
      parse = new ParseUtil(conf).parseByExtensionId("parse-zip",content).get(content.getUrl());
      assertTrue(parse.getText().equals(expectedText));
    }
  }
View Full Code Here
127
128
129
130
131
132
133
134
135
136
137
138
139
        value = "";
      cd.getMetaData().put(new Text(key), new Text(value));
    }

    ProtocolFactory factory = new ProtocolFactory(conf);
    Protocol protocol = factory.getProtocol(url);
    Text turl = new Text(url);
    ProtocolOutput output = protocol.getProtocolOutput(turl, cd);
   
    if (!output.getStatus().isSuccess()) {
      System.err.println("Fetch failed with protocol status: " + output.getStatus());
      return (-1);
    }
View Full Code Here
TOP

Related Classes of org.apache.nutch.protocol.Protocol

  • org.apache.nutch.analysis.lang.LanguageIdentifier
  • org.apache.nutch.fetcher.FetcherReducer$FetcherThread
  • org.apache.nutch.indexer.IndexingFiltersChecker
  • org.apache.nutch.parse.ext.TestExtParser
  • org.apache.nutch.parse.feed.TestFeedParser
  • org.apache.nutch.parse.html.TestMetatagParser
  • org.apache.nutch.parse.metatags.TestMetatagParser
  • org.apache.nutch.parse.mp3.TestMP3Parser
  • org.apache.nutch.parse.msexcel.TestMSExcelParser
  • org.apache.nutch.parse.msword.TestMSWordParser
    • 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.