Package org.apache.nutch.crawl

Examples of org.apache.nutch.crawl.Inlinks

56
57
58
59
60
61
62
63
64
65
66
    assertNotNull(filter);
    NutchDocument doc = new NutchDocument();
    ParseImpl parse = new ParseImpl("foo bar", new ParseData());
   
    try{
        filter.filter(doc, parse, new Text("http://nutch.apache.org/index.html"), new CrawlDatum(), new Inlinks());
    }
    catch(Exception e){
        e.printStackTrace();
        fail(e.getMessage());
    }
View Full Code Here
78
79
80
81
82
83
84
85
86
    MoreIndexingFilter filter = new MoreIndexingFilter();
    filter.setConf(conf);

    NutchDocument doc = filter.filter(new NutchDocument(), new ParseImpl("text", new ParseData(
      new ParseStatus(), "title", new Outlink[0], metadata)), new Text(
        "http://www.example.com/"), new CrawlDatum(), new Inlinks());

    assertEquals("content-disposition not detected", "filename.ext", doc.getFieldValue("title"));
  }
View Full Code Here
97
98
99
100
101
102
103
104
    metadata.add(Response.CONTENT_TYPE, source);
    MoreIndexingFilter filter = new MoreIndexingFilter();
    filter.setConf(conf);
    NutchDocument doc = filter.filter(new NutchDocument(), new ParseImpl("text", new ParseData(
        new ParseStatus(), "title", new Outlink[0], metadata)), new Text(
        "http://www.example.com/"), new CrawlDatum(), new Inlinks());
    assertEquals("mime type not detected", expected, doc.getFieldValue("type"));
  }
View Full Code Here
161
162
163
164
165
166
167
168
169
170
171
  }

  public void reduce(Text key, Iterator<NutchWritable> values,
                     OutputCollector<Text, NutchIndexAction> output, Reporter reporter)
    throws IOException {
    Inlinks inlinks = null;
    CrawlDatum dbDatum = null;
    CrawlDatum fetchDatum = null;
    ParseData parseData = null;
    ParseText parseText = null;
View Full Code Here
131
132
133
134
135
136
137
138
139
140
141
    NutchDocument doc = new NutchDocument();
    doc.add("id", url);
    Text urlText = new Text(url);

    Inlinks inlinks = null;
    Parse parse = parseResult.get(urlText);
    if (parse == null) {
      LOG.error("Failed to get parse from parse result");
      LOG.error("Available parses in parse result (by URL key):");
      for (Map.Entry<Text, Parse> entry : parseResult) {
View Full Code Here
TOP

Related Classes of org.apache.nutch.crawl.Inlinks

  • org.apache.nutch.indexer.anchor.TestAnchorIndexingFilter
  • org.apache.nutch.indexer.basic.TestBasicIndexingFilter
  • org.apache.nutch.indexer.Indexer
  • org.apache.nutch.indexer.IndexerMapReduce
  • org.apache.nutch.indexer.IndexingFiltersChecker
  • org.apache.nutch.indexer.more.TestMoreIndexingFilter
  • org.apache.nutch.indexer.staticfield.TestStaticFieldIndexerTest
  • org.apache.nutch.indexer.TestIndexingFilters
  • org.archive.access.nutch.jobs.NutchwaxLinkDb
    • 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.