Package org.apache.nutch.indexer

Examples of org.apache.nutch.indexer.IndexingFilters

73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
   
    if (LOG.isInfoEnabled()) {
      LOG.info("fetching: " + url);
    }
       
    IndexingFilters indexers = new IndexingFilters(conf);
   
    ProtocolFactory factory = new ProtocolFactory(conf);
    Protocol protocol = factory.getProtocol(url);
    CrawlDatum datum = new CrawlDatum();
   
    Content content = protocol.getProtocolOutput(new Text(url), datum)
        .getContent();

    // store the guessed content type in the crawldatum
    if (content.getContentType() != null) datum.getMetaData().put(new Text(Metadata.CONTENT_TYPE), new Text(content.getContentType()));

    if (content == null) {
      System.out.println("No content for " + url);
      return 0;
    }
   
    contentType = content.getContentType();
   
    if (contentType == null) {
      return -1;
    }
   
    if (LOG.isInfoEnabled()) {
      LOG.info("parsing: " + url);
      LOG.info("contentType: " + contentType);
    }

    ParseResult parseResult = new ParseUtil(conf).parse(content);
   
    NutchDocument doc = new NutchDocument();
    Text urlText = new Text(url);

    Inlinks inlinks = null;
    Parse parse = parseResult.get(urlText);
    try {
      indexers.filter(doc, parse, urlText, datum, inlinks);
    } catch (IndexingException e) {
      e.printStackTrace();
    }

    for (String fname : doc.getFieldNames()) {
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
    if (LOG.isInfoEnabled()) {
      LOG.info("fetching: " + url);
    }

    IndexingFilters indexers = new IndexingFilters(conf);

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

    ProtocolOutput output = protocol.getProtocolOutput(new Text(url), datum);
   
    if (!output.getStatus().isSuccess()) {
      System.out.println("Fetch failed with protocol status: " + output.getStatus());
      return 0;
    }
        
    Content content = output.getContent();

    if (content == null) {
      System.out.println("No content for " + url);
      return 0;
    }

    contentType = content.getContentType();

    if (contentType == null) {
      return -1;
    }

    // store the guessed content type in the crawldatum
    datum.getMetaData().put(new Text(Metadata.CONTENT_TYPE), new Text(contentType));

    if (ParseSegment.isTruncated(content)) {
      LOG.warn("Content is truncated, parse may fail!");
    }

    if (LOG.isInfoEnabled()) {
      LOG.info("parsing: " + url);
      LOG.info("contentType: " + contentType);
    }

    ParseResult parseResult = new ParseUtil(conf).parse(content);

    NutchDocument doc = new NutchDocument();
    Text urlText = new Text(url);

    Inlinks inlinks = null;
    Parse parse = parseResult.get(urlText);
    try {
      doc = indexers.filter(doc, parse, urlText, datum, inlinks);
    } catch (IndexingException e) {
      e.printStackTrace();
    }

    if (doc == null) {
View Full Code Here
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
89
90
91
92
93
94
95
96
97
98
   
    if (LOG.isInfoEnabled()) {
      LOG.info("fetching: " + url);
    }
       
    IndexingFilters indexers = new IndexingFilters(conf);
   
    ProtocolFactory factory = new ProtocolFactory(conf);
    Protocol protocol = factory.getProtocol(url);
    CrawlDatum datum = new CrawlDatum();
   
    Content content = protocol.getProtocolOutput(new Text(url), datum)
        .getContent();
   
    if (content == null) {
      System.out.println("No content for " + url);
      return 0;
    }
   
    contentType = content.getContentType();
   
    if (contentType == null) {
      return -1;
    }
   
    if (LOG.isInfoEnabled()) {
      LOG.info("parsing: " + url);
      LOG.info("contentType: " + contentType);
    }
   
    ParseResult parseResult = new ParseUtil(conf).parse(content);
   
    NutchDocument doc = new NutchDocument();
    Text urlText = new Text(url);

    Inlinks inlinks = null;
    Parse parse = parseResult.get(urlText);
    try {
      indexers.filter(doc, parse, urlText, datum, inlinks);
    } catch (IndexingException e) {
      e.printStackTrace();
    }

    for (String fname : doc.getFieldNames()) {
View Full Code Here
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
    if (LOG.isInfoEnabled()) {
      LOG.info("fetching: " + url);
    }

    IndexingFilters indexers = new IndexingFilters(conf);

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

    Content content = protocol.getProtocolOutput(new Text(url), datum)
        .getContent();

    if (content == null) {
      System.out.println("No content for " + url);
      return 0;
    }

    contentType = content.getContentType();

    if (contentType == null) {
      return -1;
    }

    // store the guessed content type in the crawldatum
    datum.getMetaData().put(new Text(Metadata.CONTENT_TYPE), new Text(contentType));

    if (LOG.isInfoEnabled()) {
      LOG.info("parsing: " + url);
      LOG.info("contentType: " + contentType);
    }

    ParseResult parseResult = new ParseUtil(conf).parse(content);

    NutchDocument doc = new NutchDocument();
    Text urlText = new Text(url);

    Inlinks inlinks = null;
    Parse parse = parseResult.get(urlText);
    try {
      doc = indexers.filter(doc, parse, urlText, datum, inlinks);
    } catch (IndexingException e) {
      e.printStackTrace();
    }

    if (doc == null) {
View Full Code Here
TOP

Related Classes of org.apache.nutch.indexer.IndexingFilters

  • org.apache.nutch.indexer.IndexingFiltersChecker
  • org.apache.nutch.plugin.Extension
  • org.apache.nutch.plugin.ExtensionPoint
  • org.apache.nutch.util.ObjectCache
  • java.util.HashMap
    • 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.