Examples of HTMLMetaTags

Examples of org.apache.nutch.parse.HTMLMetaTags

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
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
      LOG.error("Error parsing "+content.getUrl(),e);
      return new ParseStatus(ParseStatus.FAILED, e.getMessage())
          .getEmptyParseResult(content.getUrl(), getConf());
    }

    HTMLMetaTags metaTags = new HTMLMetaTags();
    String text = "";
    String title = "";
    Outlink[] outlinks = new Outlink[0];
    org.apache.nutch.metadata.Metadata nutchMetadata = new org.apache.nutch.metadata.Metadata();

    // we have converted the sax events generated by Tika into a DOM object
    // so we can now use the usual HTML resources from Nutch
    // get meta directives
    HTMLMetaProcessor.getMetaTags(metaTags, root, base);
    if (LOG.isTraceEnabled()) {
      LOG.trace("Meta tags for " + base + ": " + metaTags.toString());
    }

    // check meta directives
    if (!metaTags.getNoIndex()) { // okay to index
      StringBuffer sb = new StringBuffer();
      if (LOG.isTraceEnabled()) {
        LOG.trace("Getting text...");
      }
      utils.getText(sb, root); // extract text
      text = sb.toString();
      sb.setLength(0);
      if (LOG.isTraceEnabled()) {
        LOG.trace("Getting title...");
      }
      utils.getTitle(sb, root); // extract title
      title = sb.toString().trim();
    }

    if (!metaTags.getNoFollow()) { // okay to follow links
      ArrayList<Outlink> l = new ArrayList<Outlink>(); // extract outlinks
      URL baseTag = utils.getBase(root);
      if (LOG.isTraceEnabled()) {
        LOG.trace("Getting links...");
      }
      utils.getOutlinks(baseTag != null ? baseTag : base, l, root);
      outlinks = l.toArray(new Outlink[l.size()]);
      if (LOG.isTraceEnabled()) {
        LOG.trace("found " + outlinks.length + " outlinks in "
            + content.getUrl());
      }
    }

    // populate Nutch metadata with Tika metadata
    String[] TikaMDNames = tikamd.names();
    for (String tikaMDName : TikaMDNames) {
      if (tikaMDName.equalsIgnoreCase(Metadata.TITLE))
        continue;
      // TODO what if multivalued?
      nutchMetadata.add(tikaMDName, tikamd.get(tikaMDName));
    }

    // no outlinks? try OutlinkExtractor e.g works for mime types where no
    // explicit markup for anchors

    if (outlinks.length == 0) {
      outlinks = OutlinkExtractor.getOutlinks(text, getConf());
    }

    ParseStatus status = new ParseStatus(ParseStatus.SUCCESS);
    if (metaTags.getRefresh()) {
      status.setMinorCode(ParseStatus.SUCCESS_REDIRECT);
      status.setArgs(new String[] { metaTags.getRefreshHref().toString(),
          Integer.toString(metaTags.getRefreshTime()) });
    }
    ParseData parseData = new ParseData(status, title, outlinks, content
        .getMetadata(), nutchMetadata);
    ParseResult parseResult = ParseResult.createParseResult(content
        .getUrl(), new ParseImpl(text, parseData));

    // run filters on parse
    ParseResult filteredParse = this.htmlParseFilters.filter(content,
        parseResult, metaTags, root);
    if (metaTags.getNoCache()) { // not okay to cache
      for (Map.Entry<org.apache.hadoop.io.Text, Parse> entry : filteredParse)
        entry.getValue().getData().getParseMeta().set(
            Nutch.CACHING_FORBIDDEN_KEY, cachingPolicy);
    }
    return filteredParse;
View Full Code Here

Examples of org.apache.nutch.parse.HTMLMetaTags

154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
        parser.parse(new InputSource(new ByteArrayInputStream(bytes)), node);
      } catch (Exception e) {
        e.printStackTrace();
      }

      HTMLMetaTags robotsMeta= new HTMLMetaTags();
      HTMLMetaProcessor.getMetaTags(robotsMeta, node,
          currURLsAndAnswers[i][0]);

      Assert.assertTrue("got index wrong on test " + i,
          robotsMeta.getNoIndex() == answers[i][0]);
      Assert.assertTrue("got follow wrong on test " + i,
          robotsMeta.getNoFollow() == answers[i][1]);
      Assert.assertTrue("got cache wrong on test " + i,
          robotsMeta.getNoCache() == answers[i][2]);
      Assert.assertTrue("got base href wrong on test " + i + " (got "
          + robotsMeta.getBaseHref() + ")",
          ( (robotsMeta.getBaseHref() == null)
              && (currURLsAndAnswers[i][1] == null) )
              || ( (robotsMeta.getBaseHref() != null)
                  && robotsMeta.getBaseHref().equals(
                      currURLsAndAnswers[i][1]) ) );

    }
  }
View Full Code Here

Examples of org.apache.nutch.parse.HTMLMetaTags

155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
        parser.parse(new InputSource(new ByteArrayInputStream(bytes)), node);
      } catch (Exception e) {
        e.printStackTrace();
      }

      HTMLMetaTags robotsMeta= new HTMLMetaTags();
      HTMLMetaProcessor.getMetaTags(robotsMeta, node,
          currURLsAndAnswers[i][0]);

      Assert.assertTrue("got index wrong on test " + i,
          robotsMeta.getNoIndex() == answers[i][0]);
      Assert.assertTrue("got follow wrong on test " + i,
          robotsMeta.getNoFollow() == answers[i][1]);
      Assert.assertTrue("got cache wrong on test " + i,
          robotsMeta.getNoCache() == answers[i][2]);
      Assert.assertTrue("got base href wrong on test " + i + " (got "
          + robotsMeta.getBaseHref() + ")",
          ( (robotsMeta.getBaseHref() == null)
              && (currURLsAndAnswers[i][1] == null) )
              || ( (robotsMeta.getBaseHref() != null)
                  && robotsMeta.getBaseHref().equals(
                      currURLsAndAnswers[i][1]) ) );

    }
  }
View Full Code Here

Examples of org.apache.nutch.parse.HTMLMetaTags

156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
        parser.parse(new InputSource(new ByteArrayInputStream(bytes)), node);
      } catch (Exception e) {
        e.printStackTrace();
      }

      HTMLMetaTags robotsMeta= new HTMLMetaTags();
      HTMLMetaProcessor.getMetaTags(robotsMeta, node,
                                                  currURLsAndAnswers[i][0]);

      assertTrue("got index wrong on test " + i,
                 robotsMeta.getNoIndex() == answers[i][0]);
      assertTrue("got follow wrong on test " + i,
                 robotsMeta.getNoFollow() == answers[i][1]);
      assertTrue("got cache wrong on test " + i,
                 robotsMeta.getNoCache() == answers[i][2]);
      assertTrue("got base href wrong on test " + i + " (got "
                 + robotsMeta.getBaseHref() + ")",
                 ( (robotsMeta.getBaseHref() == null)
                    && (currURLsAndAnswers[i][1] == null) )
                 || ( (robotsMeta.getBaseHref() != null)
                      && robotsMeta.getBaseHref().equals(
                        currURLsAndAnswers[i][1]) ) );
     
    }
  }
View Full Code Here

Examples of org.apache.nutch.parse.HTMLMetaTags

136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
  private ParseFilters htmlParseFilters;

  private String cachingPolicy;

  public Parse getParse(String url, WebPage page) {
    HTMLMetaTags metaTags = new HTMLMetaTags();

    String baseUrl = TableUtil.toString(page.getBaseUrl());
    URL base;
    try {
      base = new URL(baseUrl);
    } catch (MalformedURLException e) {
      return ParseStatusUtils.getEmptyParse(e, getConf());
    }

    String text = "";
    String title = "";
    Outlink[] outlinks = new Outlink[0];
    Metadata metadata = new Metadata();

    // parse the content
    DocumentFragment root;
    try {
      ByteBuffer contentInOctets = page.getContent();
      InputSource input = new InputSource(new ByteArrayInputStream(contentInOctets.array(),
          contentInOctets.arrayOffset() + contentInOctets.position(), contentInOctets.remaining()));

      EncodingDetector detector = new EncodingDetector(conf);
      detector.autoDetectClues(page, true);
      detector.addClue(sniffCharacterEncoding(contentInOctets), "sniffed");
      String encoding = detector.guessEncoding(page, defaultCharEncoding);

      metadata.set(Metadata.ORIGINAL_CHAR_ENCODING, encoding);
      metadata.set(Metadata.CHAR_ENCODING_FOR_CONVERSION, encoding);

      input.setEncoding(encoding);
      if (LOG.isTraceEnabled()) { LOG.trace("Parsing..."); }
      root = parse(input);
    } catch (IOException e) {
      LOG.error("Failed with the following IOException: ", e);
      return ParseStatusUtils.getEmptyParse(e, getConf());
    } catch (DOMException e) {
      LOG.error("Failed with the following DOMException: ", e);
      return ParseStatusUtils.getEmptyParse(e, getConf());
    } catch (SAXException e) {
      LOG.error("Failed with the following SAXException: ", e);
      return ParseStatusUtils.getEmptyParse(e, getConf());
    } catch (Exception e) {
      LOG.error("Failed with the following Exception: ", e);
      return ParseStatusUtils.getEmptyParse(e, getConf());
    }

    // get meta directives
    HTMLMetaProcessor.getMetaTags(metaTags, root, base);
    if (LOG.isTraceEnabled()) {
      LOG.trace("Meta tags for " + base + ": " + metaTags.toString());
    }
    // check meta directives
    if (!metaTags.getNoIndex()) {               // okay to index
      StringBuilder sb = new StringBuilder();
      if (LOG.isTraceEnabled()) { LOG.trace("Getting text..."); }
      utils.getText(sb, root);          // extract text
      text = sb.toString();
      sb.setLength(0);
      if (LOG.isTraceEnabled()) { LOG.trace("Getting title..."); }
      utils.getTitle(sb, root);         // extract title
      title = sb.toString().trim();
    }

    if (!metaTags.getNoFollow()) {              // okay to follow links
      ArrayList<Outlink> l = new ArrayList<Outlink>();   // extract outlinks
      URL baseTag = utils.getBase(root);
      if (LOG.isTraceEnabled()) { LOG.trace("Getting links..."); }
      utils.getOutlinks(baseTag!=null?baseTag:base, l, root);
      outlinks = l.toArray(new Outlink[l.size()]);
      if (LOG.isTraceEnabled()) {
        LOG.trace("found "+outlinks.length+" outlinks in "+ url);
      }
    }

    ParseStatus status = new ParseStatus();
    status.setMajorCode(ParseStatusCodes.SUCCESS);
    if (metaTags.getRefresh()) {
      status.setMinorCode(ParseStatusCodes.SUCCESS_REDIRECT);
      status.addToArgs(new Utf8(metaTags.getRefreshHref().toString()));
      status.addToArgs(new Utf8(Integer.toString(metaTags.getRefreshTime())));
    }

    Parse parse = new Parse(text, title, outlinks, status);
    parse = htmlParseFilters.filter(url, page, parse, metaTags, root);

    if (metaTags.getNoCache()) {             // not okay to cache
      page.putToMetadata(new Utf8(Nutch.CACHING_FORBIDDEN_KEY),
          ByteBuffer.wrap(Bytes.toBytes(cachingPolicy)));
    }

    return parse;
View Full Code Here

Examples of org.apache.nutch.parse.HTMLMetaTags

118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
    } catch (Exception e) {
      LOG.error("Error parsing "+url,e);
      return ParseStatusUtils.getEmptyParse(e, getConf());
    }

    HTMLMetaTags metaTags = new HTMLMetaTags();
    String text = "";
    String title = "";
    Outlink[] outlinks = new Outlink[0];

    // we have converted the sax events generated by Tika into a DOM object
    // so we can now use the usual HTML resources from Nutch
    // get meta directives
    HTMLMetaProcessor.getMetaTags(metaTags, root, base);
    if (LOG.isTraceEnabled()) {
      LOG.trace("Meta tags for " + base + ": " + metaTags.toString());
    }

    // check meta directives
    if (!metaTags.getNoIndex()) { // okay to index
      StringBuffer sb = new StringBuffer();
      if (LOG.isTraceEnabled()) {
        LOG.trace("Getting text...");
      }
      utils.getText(sb, root); // extract text
      text = sb.toString();
      sb.setLength(0);
      if (LOG.isTraceEnabled()) {
        LOG.trace("Getting title...");
      }
      utils.getTitle(sb, root); // extract title
      title = sb.toString().trim();
    }

    if (!metaTags.getNoFollow()) { // okay to follow links
      ArrayList<Outlink> l = new ArrayList<Outlink>(); // extract outlinks
      URL baseTag = utils.getBase(root);
      if (LOG.isTraceEnabled()) {
        LOG.trace("Getting links...");
      }
      utils.getOutlinks(baseTag != null ? baseTag : base, l, root);
      outlinks = l.toArray(new Outlink[l.size()]);
      if (LOG.isTraceEnabled()) {
        LOG.trace("found " + outlinks.length + " outlinks in " + base);
      }
    }

    // populate Nutch metadata with Tika metadata
    String[] TikaMDNames = tikamd.names();
    for (String tikaMDName : TikaMDNames) {
      if (tikaMDName.equalsIgnoreCase(TikaCoreProperties.TITLE.toString()))
      continue;
      // TODO what if multivalued?
      page.putToMetadata(new Utf8(tikaMDName), ByteBuffer.wrap(Bytes.toBytes(tikamd
          .get(tikaMDName))));
    }

    // no outlinks? try OutlinkExtractor e.g works for mime types where no
    // explicit markup for anchors

    if (outlinks.length == 0) {
      outlinks = OutlinkExtractor.getOutlinks(text, getConf());
    }

    ParseStatus status = ParseStatusUtils.STATUS_SUCCESS;
    if (metaTags.getRefresh()) {
      status.setMinorCode(ParseStatusCodes.SUCCESS_REDIRECT);
      status.addToArgs(new Utf8(metaTags.getRefreshHref().toString()));
      status.addToArgs(new Utf8(Integer.toString(metaTags.getRefreshTime())));
    }

    Parse parse = new Parse(text, title, outlinks, status);
    parse = htmlParseFilters.filter(url, page, parse, metaTags, root);

    if (metaTags.getNoCache()) { // not okay to cache
      page.putToMetadata(new Utf8(Nutch.CACHING_FORBIDDEN_KEY), ByteBuffer.wrap(Bytes
          .toBytes(cachingPolicy)));
    }

    return parse;
View Full Code Here

Examples of org.apache.nutch.parse.HTMLMetaTags

155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
        parser.parse(new InputSource(new ByteArrayInputStream(bytes)), node);
      } catch (Exception e) {
        e.printStackTrace();
      }

      HTMLMetaTags robotsMeta= new HTMLMetaTags();
      HTMLMetaProcessor.getMetaTags(robotsMeta, node,
                                                  currURLsAndAnswers[i][0]);

      assertTrue("got index wrong on test " + i,
                 robotsMeta.getNoIndex() == answers[i][0]);
      assertTrue("got follow wrong on test " + i,
                 robotsMeta.getNoFollow() == answers[i][1]);
      assertTrue("got cache wrong on test " + i,
                 robotsMeta.getNoCache() == answers[i][2]);
      assertTrue("got base href wrong on test " + i + " (got "
                 + robotsMeta.getBaseHref() + ")",
                 ( (robotsMeta.getBaseHref() == null)
                    && (currURLsAndAnswers[i][1] == null) )
                 || ( (robotsMeta.getBaseHref() != null)
                      && robotsMeta.getBaseHref().equals(
                        currURLsAndAnswers[i][1]) ) );
     
    }
  }
View Full Code Here

Examples of org.apache.nutch.parse.HTMLMetaTags

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
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
      LOG.error("Error parsing "+content.getUrl(),e);
      return new ParseStatus(ParseStatus.FAILED, e.getMessage())
          .getEmptyParseResult(content.getUrl(), getConf());
    }

    HTMLMetaTags metaTags = new HTMLMetaTags();
    String text = "";
    String title = "";
    Outlink[] outlinks = new Outlink[0];
    org.apache.nutch.metadata.Metadata nutchMetadata = new org.apache.nutch.metadata.Metadata();

    // we have converted the sax events generated by Tika into a DOM object
    // so we can now use the usual HTML resources from Nutch
    // get meta directives
    HTMLMetaProcessor.getMetaTags(metaTags, root, base);
    if (LOG.isTraceEnabled()) {
      LOG.trace("Meta tags for " + base + ": " + metaTags.toString());
    }

    // check meta directives
    if (!metaTags.getNoIndex()) { // okay to index
      StringBuffer sb = new StringBuffer();
      if (LOG.isTraceEnabled()) {
        LOG.trace("Getting text...");
      }
      utils.getText(sb, root); // extract text
      text = sb.toString();
      sb.setLength(0);
      if (LOG.isTraceEnabled()) {
        LOG.trace("Getting title...");
      }
      utils.getTitle(sb, root); // extract title
      title = sb.toString().trim();
    }

    if (!metaTags.getNoFollow()) { // okay to follow links
      ArrayList<Outlink> l = new ArrayList<Outlink>(); // extract outlinks
      URL baseTag = utils.getBase(root);
      if (LOG.isTraceEnabled()) {
        LOG.trace("Getting links...");
      }
      utils.getOutlinks(baseTag != null ? baseTag : base, l, root);
      outlinks = l.toArray(new Outlink[l.size()]);
      if (LOG.isTraceEnabled()) {
        LOG.trace("found " + outlinks.length + " outlinks in "
            + content.getUrl());
      }
    }

    // populate Nutch metadata with Tika metadata
    String[] TikaMDNames = tikamd.names();
    for (String tikaMDName : TikaMDNames) {
      if (tikaMDName.equalsIgnoreCase(Metadata.TITLE))
        continue;
      // TODO what if multivalued?
      nutchMetadata.add(tikaMDName, tikamd.get(tikaMDName));
    }

    // no outlinks? try OutlinkExtractor e.g works for mime types where no
    // explicit markup for anchors

    if (outlinks.length == 0) {
      outlinks = OutlinkExtractor.getOutlinks(text, getConf());
    }

    ParseStatus status = new ParseStatus(ParseStatus.SUCCESS);
    if (metaTags.getRefresh()) {
      status.setMinorCode(ParseStatus.SUCCESS_REDIRECT);
      status.setArgs(new String[] { metaTags.getRefreshHref().toString(),
          Integer.toString(metaTags.getRefreshTime()) });
    }
    ParseData parseData = new ParseData(status, title, outlinks, content
        .getMetadata(), nutchMetadata);
    ParseResult parseResult = ParseResult.createParseResult(content
        .getUrl(), new ParseImpl(text, parseData));

    // run filters on parse
    ParseResult filteredParse = this.htmlParseFilters.filter(content,
        parseResult, metaTags, root);
    if (metaTags.getNoCache()) { // not okay to cache
      for (Map.Entry<org.apache.hadoop.io.Text, Parse> entry : filteredParse)
        entry.getValue().getData().getParseMeta().set(
            Nutch.CACHING_FORBIDDEN_KEY, cachingPolicy);
    }
    return filteredParse;
View Full Code Here

Examples of org.apache.nutch.parse.HTMLMetaTags

155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
        parser.parse(new InputSource(new ByteArrayInputStream(bytes)), node);
      } catch (Exception e) {
        e.printStackTrace();
      }

      HTMLMetaTags robotsMeta= new HTMLMetaTags();
      HTMLMetaProcessor.getMetaTags(robotsMeta, node,
                                                  currURLsAndAnswers[i][0]);

      assertTrue("got index wrong on test " + i,
                 robotsMeta.getNoIndex() == answers[i][0]);
      assertTrue("got follow wrong on test " + i,
                 robotsMeta.getNoFollow() == answers[i][1]);
      assertTrue("got cache wrong on test " + i,
                 robotsMeta.getNoCache() == answers[i][2]);
      assertTrue("got base href wrong on test " + i + " (got "
                 + robotsMeta.getBaseHref() + ")",
                 ( (robotsMeta.getBaseHref() == null)
                    && (currURLsAndAnswers[i][1] == null) )
                 || ( (robotsMeta.getBaseHref() != null)
                      && robotsMeta.getBaseHref().equals(
                        currURLsAndAnswers[i][1]) ) );
     
    }
  }
View Full Code Here

Examples of org.apache.nutch.parse.HTMLMetaTags

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
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
      LOG.error("Error parsing "+content.getUrl(),e);
      return new ParseStatus(ParseStatus.FAILED, e.getMessage())
          .getEmptyParseResult(content.getUrl(), getConf());
    }

    HTMLMetaTags metaTags = new HTMLMetaTags();
    String text = "";
    String title = "";
    Outlink[] outlinks = new Outlink[0];
    org.apache.nutch.metadata.Metadata nutchMetadata = new org.apache.nutch.metadata.Metadata();

    // we have converted the sax events generated by Tika into a DOM object
    // so we can now use the usual HTML resources from Nutch
    // get meta directives
    HTMLMetaProcessor.getMetaTags(metaTags, root, base);
    if (LOG.isTraceEnabled()) {
      LOG.trace("Meta tags for " + base + ": " + metaTags.toString());
    }

    // check meta directives
    if (!metaTags.getNoIndex()) { // okay to index
      StringBuffer sb = new StringBuffer();
      if (LOG.isTraceEnabled()) {
        LOG.trace("Getting text...");
      }
      utils.getText(sb, root); // extract text
      text = sb.toString();
      sb.setLength(0);
      if (LOG.isTraceEnabled()) {
        LOG.trace("Getting title...");
      }
      utils.getTitle(sb, root); // extract title
      title = sb.toString().trim();
    }

    if (!metaTags.getNoFollow()) { // okay to follow links
      ArrayList<Outlink> l = new ArrayList<Outlink>(); // extract outlinks
      URL baseTag = utils.getBase(root);
      if (LOG.isTraceEnabled()) {
        LOG.trace("Getting links...");
      }
      utils.getOutlinks(baseTag != null ? baseTag : base, l, root);
      outlinks = l.toArray(new Outlink[l.size()]);
      if (LOG.isTraceEnabled()) {
        LOG.trace("found " + outlinks.length + " outlinks in "
            + content.getUrl());
      }
    }

    // populate Nutch metadata with Tika metadata
    String[] TikaMDNames = tikamd.names();
    for (String tikaMDName : TikaMDNames) {
      if (tikaMDName.equalsIgnoreCase(Metadata.TITLE))
        continue;
      // TODO what if multivalued?
      nutchMetadata.add(tikaMDName, tikamd.get(tikaMDName));
    }

    // no outlinks? try OutlinkExtractor e.g works for mime types where no
    // explicit markup for anchors

    if (outlinks.length == 0) {
      outlinks = OutlinkExtractor.getOutlinks(text, getConf());
    }

    ParseStatus status = new ParseStatus(ParseStatus.SUCCESS);
    if (metaTags.getRefresh()) {
      status.setMinorCode(ParseStatus.SUCCESS_REDIRECT);
      status.setArgs(new String[] { metaTags.getRefreshHref().toString(),
          Integer.toString(metaTags.getRefreshTime()) });
    }
    ParseData parseData = new ParseData(status, title, outlinks, content
        .getMetadata(), nutchMetadata);
    ParseResult parseResult = ParseResult.createParseResult(content
        .getUrl(), new ParseImpl(text, parseData));

    // run filters on parse
    ParseResult filteredParse = this.htmlParseFilters.filter(content,
        parseResult, metaTags, root);
    if (metaTags.getNoCache()) { // not okay to cache
      for (Map.Entry<org.apache.hadoop.io.Text, Parse> entry : filteredParse)
        entry.getValue().getData().getParseMeta().set(
            Nutch.CACHING_FORBIDDEN_KEY, cachingPolicy);
    }
    return filteredParse;
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.