Package org.apache.nutch.parse

Examples of org.apache.nutch.parse.Outlink

100
101
102
103
104
105
106
107
108
109
110
            Parse parse = new ParseUtil(this.conf).parse(content);
            ParseData theParseData = parse.getData();
            Outlink[] theOutlinks = theParseData.getOutlinks();
           
            for(int count = 0; count < theOutlinks.length; count++) {
              outLinksList.add(new Outlink(theOutlinks[count].getToUrl(), theOutlinks[count].getAnchor(), this.conf));
            }
           
            resultText += entry.getName() + " " + parse.getText() + " ";
          } catch (ParseException e) {
            if (LOG.isInfoEnabled()) {
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
      setAlbum(value);
    if (name.equals("TPE1-Text"))
      setArtist(value);

    if (name.indexOf("URL Link") > -1) {
      links.add(new Outlink(value, "", this.conf));
    } else if (name.indexOf("Text") > -1) {
      text += value + "\n";
    }

    metadata.set(name, value);
View Full Code Here
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
                if (r.getLink() != null) {
                    try {
                        // get the outlink
      if (r.getDescription()!= null ) {
          theOutlinks.add(new Outlink(r.getLink(), r.getDescription(), getConf()));
      } else {
          theOutlinks.add(new Outlink(r.getLink(), "", getConf()));
      }
                    } catch (MalformedURLException e) {
                        if (LOG.isWarnEnabled()) {
                          LOG.warn("MalformedURL: " + r.getLink());
                          LOG.warn("Attempting to continue processing outlinks");
                          e.printStackTrace(LogUtil.getWarnStream(LOG));
                        }
                        continue;
                    }
                }

                // now get the descriptions of all the underlying RSS Items and
                // then index them too
                for (int j = 0; j < r.getItems().size(); j++) {
                    RSSItem theRSSItem = (RSSItem) r.getItems().get(j);
                    indexText.append(theRSSItem.getDescription());
                    indexText.append(" ");

                    String whichLink = null;

                    if (theRSSItem.getPermalink() != null)
                        whichLink = theRSSItem.getPermalink();
                    else
                        whichLink = theRSSItem.getLink();

                    if (whichLink != null) {
                        try {
          if (theRSSItem.getDescription()!=null) {
        theOutlinks.add(new Outlink(whichLink, theRSSItem.getDescription(), getConf()));
          } else {
        theOutlinks.add(new Outlink(whichLink, "", getConf()));
          }
                        } catch (MalformedURLException e) {
                            if (LOG.isWarnEnabled()) {
                              LOG.warn("MalformedURL: " + whichLink);
                              LOG.warn("Attempting to continue processing outlinks");
View Full Code Here
228
229
230
231
232
233
234
235
236
237
238
        }
        url = url.replaceAll("&amp;", "&");
        if (LOG.isTraceEnabled()) {
          LOG.trace(" - outlink from JS: '" + url + "'");
        }
        outlinks.add(new Outlink(url, anchor, getConf()));
      }
    } catch (Exception ex) {
      // if it is a malformed URL we just throw it away and continue with
      // extraction.
      if (LOG.isErrorEnabled()) { LOG.error("getJSLinks", ex); }
View Full Code Here
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
      testDOMs[i]= node;
    }
    try {
     answerOutlinks = new Outlink[][]{
         {
           new Outlink("http://www.nutch.org", "anchor", conf),
         },
         {
           new Outlink("http://www.nutch.org/", "home", conf),
           new Outlink("http://www.nutch.org/docs/bot.html", "bots", conf),
         },
         {
           new Outlink("http://www.nutch.org/", "separate this", conf),
           new Outlink("http://www.nutch.org/docs/ok", "from this", conf),
         },
         {
           new Outlink("http://www.nutch.org/", "home", conf),
           new Outlink("http://www.nutch.org/docs/1", "1", conf),
           new Outlink("http://www.nutch.org/docs/2", "2", conf),
         },
         {
           new Outlink("http://www.nutch.org/frames/top.html", "", conf),
           new Outlink("http://www.nutch.org/frames/left.html", "", conf),
           new Outlink("http://www.nutch.org/frames/invalid.html", "", conf),
           new Outlink("http://www.nutch.org/frames/right.html", "", conf),
         },
         {
           new Outlink("http://www.nutch.org/maps/logo.gif", "", conf),
           new Outlink("http://www.nutch.org/index.html", "", conf),
           new Outlink("http://www.nutch.org/maps/#bottom", "", conf),
           new Outlink("http://www.nutch.org/bot.html", "", conf),
           new Outlink("http://www.nutch.org/docs/index.html", "", conf),
         },
         {
             new Outlink("http://www.nutch.org/index.html", "whitespace test", conf),
         },
         {
         },
         {
           new Outlink("http://www.nutch.org/dummy.jsp", "test2", conf),
         },
         {
         },
         {
           new Outlink("http://www.nutch.org/;x", "anchor1", conf),
           new Outlink("http://www.nutch.org/g;x", "anchor2", conf),
           new Outlink("http://www.nutch.org/g;x?y#s", "anchor3", conf)
         },
         {
           new Outlink("http://www.nutch.org/g;something", "anchor1", conf),
           new Outlink("http://www.nutch.org/g;something?y#s", "anchor2", conf),
           new Outlink("http://www.nutch.org/;something?y=1", "anchor3", conf),
           new Outlink("http://www.nutch.org/;something?y=1#s", "anchor4", conf),
           new Outlink("http://www.nutch.org/?y=1;somethingelse", "anchor5", conf)
         }
      };
  
    } catch (MalformedURLException e) {
       
View Full Code Here
379
380
381
382
383
384
385
386
387
388
389
          if (target != null && !noFollow && !post)
            try {
             
              URL url = (base.toString().indexOf(';') > 0) ?
                fixEmbeddedParams(base, target) :  new URL(base, target);
              outlinks.add(new Outlink(url.toString(),
                                       linkText.toString().trim(), conf));
            } catch (MalformedURLException e) {
              // don't care
            }
        }
View Full Code Here
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
                if (r.getLink() != null) {
                    try {
                        // get the outlink
      if (r.getDescription()!= null ) {
          theOutlinks.add(new Outlink(r.getLink(), r.getDescription()));
      } else {
          theOutlinks.add(new Outlink(r.getLink(), ""));
      }
                    } catch (MalformedURLException e) {
                        if (LOG.isWarnEnabled()) {
                          LOG.warn("MalformedURL: " + r.getLink());
                          LOG.warn("Attempting to continue processing outlinks");
                          e.printStackTrace(LogUtil.getWarnStream(LOG));
                        }
                        continue;
                    }
                }

                // now get the descriptions of all the underlying RSS Items and
                // then index them too
                for (int j = 0; j < r.getItems().size(); j++) {
                    RSSItem theRSSItem = (RSSItem) r.getItems().get(j);
                    indexText.append(theRSSItem.getDescription());
                    indexText.append(" ");

                    String whichLink = null;

                    if (theRSSItem.getPermalink() != null)
                        whichLink = theRSSItem.getPermalink();
                    else
                        whichLink = theRSSItem.getLink();

                    if (whichLink != null) {
                        try {
          if (theRSSItem.getDescription()!=null) {
        theOutlinks.add(new Outlink(whichLink, theRSSItem.getDescription()));
          } else {
        theOutlinks.add(new Outlink(whichLink, ""));
          }
                        } catch (MalformedURLException e) {
                            if (LOG.isWarnEnabled()) {
                              LOG.warn("MalformedURL: " + whichLink);
                              LOG.warn("Attempting to continue processing outlinks");
View Full Code Here
192
193
194
195
196
197
198
199
200
201
202
        if (url.startsWith("www.")) {
            url = "http://" + url;
        } else url = new URL(baseURL, url).toString();
        url = url.replaceAll("&amp;", "&");
        LOG.fine(" - outlink from JS: '" + url + "'");
        outlinks.add(new Outlink(url, anchor));
      }
    } catch (Exception ex) {
      // if it is a malformed URL we just throw it away and continue with
      // extraction.
      LOG.throwing(JSParseFilter.class.getName(), "getJSLinks", ex);
View Full Code Here
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
                if (r.getLink() != null) {
                    try {
                        // get the outlink
      if (r.getDescription()!= null ) {
          theOutlinks.add(new Outlink(r.getLink(), r.getDescription()));
      } else {
          theOutlinks.add(new Outlink(r.getLink(), ""));
      }
                    } catch (MalformedURLException e) {
                        LOG.info("nutch:parse-rss:RSSParser Exception: MalformedURL: "
                                        + r.getLink()
                                        + ": Attempting to continue processing outlinks");
                        e.printStackTrace();
                        continue;
                    }
                }

                // now get the descriptions of all the underlying RSS Items and
                // then index them too
                for (int j = 0; j < r.getItems().size(); j++) {
                    RSSItem theRSSItem = (RSSItem) r.getItems().get(j);
                    indexText.append(theRSSItem.getDescription());
                    indexText.append(" ");

                    String whichLink = null;

                    if (theRSSItem.getPermalink() != null)
                        whichLink = theRSSItem.getPermalink();
                    else
                        whichLink = theRSSItem.getLink();

                    if (whichLink != null) {
                        try {
          if (theRSSItem.getDescription()!=null) {
        theOutlinks.add(new Outlink(whichLink, theRSSItem.getDescription()));
          } else {
        theOutlinks.add(new Outlink(whichLink, ""));
          }
                        } catch (MalformedURLException e) {
                            LOG.info("nutch:parse-rss:RSSParser Exception: MalformedURL: "
                                            + whichLink
                                            + ": Attempting to continue processing outlinks");
View Full Code Here
42
43
44
45
46
47
48
49
50
51
52
      setAlbum(value);
    if (name.equals("TPE1-Text"))
      setArtist(value);

    if (name.indexOf("URL Link") > -1) {
      links.add(new Outlink(value, ""));
    } else if (name.indexOf("Text") > -1) {
      text += value + "\n";
    }

    metadata.setProperty(name, value);
View Full Code Here
TOP

Related Classes of org.apache.nutch.parse.Outlink

  • org.apache.hadoop.io.MapWritable
  • org.apache.nutch.indexer.basic.TestBasicIndexingFilter
  • org.apache.nutch.net.UrlNormalizerFactory
  • org.apache.nutch.net.URLNormalizers
  • org.apache.nutch.parse.html.DOMContentUtils
  • org.apache.nutch.parse.html.TestDOMContentUtils
  • org.apache.nutch.parse.js.JSParseFilter
  • org.apache.nutch.parse.mp3.MetadataCollector
  • org.apache.nutch.parse.rss.RSSParser
  • org.apache.nutch.parse.tika.DOMContentUtils
    • 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.