Package org.apache.nutch.storage

Examples of org.apache.nutch.storage.WebPage

320
321
322
323
324
325
326
327
328
329
330
331
332
333
    DataInputStream in = new DataInputStream(new FileInputStream(file));
    in.readFully(bytes);
    Configuration conf = NutchConfiguration.create();
    HtmlParser parser = new HtmlParser();
    parser.setConf(conf);
    WebPage page = new WebPage();
    page.setBaseUrl(new Utf8(url));
    page.setContent(ByteBuffer.wrap(bytes));
    page.setContentType(new Utf8("text/html"));
    Parse parse = parser.getParse(url, page);
    System.out.println("title: "+parse.getTitle());
    System.out.println("text: "+parse.getText());
    System.out.println("outlinks: " + Arrays.toString(parse.getOutlinks()));
View Full Code Here
106
107
108
109
110
111
112
113
114
115
116
117
118
119
  private List<String> readDb() throws Exception {
    List<URLWebPage> pages = CrawlTestUtil.readContents(webPageStore, null, fields);
    ArrayList<String> read = new ArrayList<String>();
    for (URLWebPage up : pages) {
      WebPage page = up.getDatum();
      String representation = up.getUrl();
      representation += "\tnutch.score=" + (int)page.getScore();
      ByteBuffer bb = page.getFromMetadata(new Utf8("custom.attribute"));
      if (bb != null) {
        representation += "\tcustom.attribute=" + Bytes.toString(bb);
      }
      read.add(representation);
    }
View Full Code Here
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
    DataInputStream in = new DataInputStream(new FileInputStream(file));
    in.readFully(bytes);
    Configuration conf = NutchConfiguration.create();
    // TikaParser parser = new TikaParser();
    // parser.setConf(conf);
    WebPage page = new WebPage();
    page.setBaseUrl(new Utf8(url));
    page.setContent(ByteBuffer.wrap(bytes));
    MimeUtil mimeutil = new MimeUtil(conf);
    String mtype = mimeutil.getMimeType(file);
    page.setContentType(new Utf8(mtype));
    // Parse parse = parser.getParse(url, page);

    Parse parse = new ParseUtil(conf).parse(url, page);

    System.out.println("content type: " + mtype);
View Full Code Here
234
235
236
237
238
239
240
241
242
243
244
    Result<String, WebPage> result = datastore.execute(query);
    boolean found = false;
    // should happen only once
    while (result.next()) {
      try {
        WebPage page = result.get();
        String skey = result.getKey();
        // we should not get to this point but nevermind
        if (page == null || skey == null)
          break;
        found = true;
View Full Code Here
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
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
184
185
186
187
188
189
190
191
192
193
194
195
196
197
  @Override
  protected void reduce(UrlWithScore key, Iterable<NutchWritable> values,
      Context context) throws IOException, InterruptedException {
    String keyUrl = key.getUrl().toString();

    WebPage page = null;
    inlinkedScoreData.clear();
   
    for (NutchWritable nutchWritable : values) {
      Writable val = nutchWritable.get();
      if (val instanceof WebPageWritable) {
        page = ((WebPageWritable) val).getWebPage();
      } else {
        inlinkedScoreData.add((ScoreDatum) val);
        if (inlinkedScoreData.size() >= maxLinks) {
          LOG.info("Limit reached, skipping further inlinks for " + keyUrl);
          break;
        }
      }
    }
    String url;
    try {
      url = TableUtil.unreverseUrl(keyUrl);
    } catch (Exception e) {
      // this can happen because a newly discovered malformed link
      // may slip by url filters
      // TODO: Find a better solution
      return;
    }

    if (page == null) { // new row
      if (!additionsAllowed) {
        return;
      }
      page = new WebPage();
      schedule.initializeSchedule(url, page);
      page.setStatus(CrawlStatus.STATUS_UNFETCHED);
      try {
        scoringFilters.initialScore(url, page);
      } catch (ScoringFilterException e) {
        page.setScore(0.0f);
      }
    } else {
      byte status = (byte)page.getStatus();
      switch (status) {
      case CrawlStatus.STATUS_FETCHED:         // succesful fetch
      case CrawlStatus.STATUS_REDIR_TEMP:      // successful fetch, redirected
      case CrawlStatus.STATUS_REDIR_PERM:
      case CrawlStatus.STATUS_NOTMODIFIED:     // successful fetch, notmodified
        int modified = FetchSchedule.STATUS_UNKNOWN;
        if (status == CrawlStatus.STATUS_NOTMODIFIED) {
          modified = FetchSchedule.STATUS_NOTMODIFIED;
        }
        ByteBuffer prevSig = page.getPrevSignature();
        ByteBuffer signature = page.getSignature();
        if (prevSig != null && signature != null) {
          if (SignatureComparator.compare(prevSig, signature) != 0) {
            modified = FetchSchedule.STATUS_MODIFIED;
          } else {
            modified = FetchSchedule.STATUS_NOTMODIFIED;
          }
        }
        long fetchTime = page.getFetchTime();
        long prevFetchTime = page.getPrevFetchTime();
        long modifiedTime = page.getModifiedTime();
        long prevModifiedTime = page.getPrevModifiedTime();

        schedule.setFetchSchedule(url, page, prevFetchTime, prevModifiedTime,
            fetchTime, modifiedTime, modified);
        if (maxInterval < page.getFetchInterval())
          schedule.forceRefetch(url, page, false);
        break;
      case CrawlStatus.STATUS_RETRY:
        schedule.setPageRetrySchedule(url, page, 0L, page.getPrevModifiedTime(), page.getFetchTime());
        if (page.getRetriesSinceFetch() < retryMax) {
          page.setStatus(CrawlStatus.STATUS_UNFETCHED);
        } else {
          page.setStatus(CrawlStatus.STATUS_GONE);
        }
        break;
      case CrawlStatus.STATUS_GONE:
        schedule.setPageGoneSchedule(url, page, 0L, page.getPrevModifiedTime(), page.getFetchTime());
        break;
      }
    }

    if (page.getInlinks() != null) {
      page.getInlinks().clear();
    }
    for (ScoreDatum inlink : inlinkedScoreData) {
      page.putToInlinks(new Utf8(inlink.getUrl()), new Utf8(inlink.getAnchor()));
    }

    // Distance calculation.
    // Retrieve smallest distance from all inlinks distances
    // Calculate new distance for current page: smallest inlink distance plus 1.
    // If the new distance is smaller than old one (or if old did not exist yet),
    // write it to the page.
    int smallestDist=Integer.MAX_VALUE;
    for (ScoreDatum inlink : inlinkedScoreData) {
      int inlinkDist = inlink.getDistance();
      if (inlinkDist < smallestDist) {
        smallestDist=inlinkDist;
      }
      page.putToInlinks(new Utf8(inlink.getUrl()), new Utf8(inlink.getAnchor()));
    }
    if (smallestDist != Integer.MAX_VALUE) {
      int oldDistance=Integer.MAX_VALUE;
      Utf8 oldDistUtf8 = page.getFromMarkers(DbUpdaterJob.DISTANCE);
      if (oldDistUtf8 != null)oldDistance=Integer.parseInt(oldDistUtf8.toString());
      int newDistance = smallestDist+1;
      if (newDistance < oldDistance) {
        page.putToMarkers(DbUpdaterJob.DISTANCE, new Utf8(Integer.toString(newDistance)));
      }
    }

    try {
      scoringFilters.updateScore(url, page, inlinkedScoreData);
    } catch (ScoringFilterException e) {
      LOG.warn("Scoring filters failed with exception " +
                StringUtils.stringifyException(e));
    }

    // clear markers
    // But only delete when they exist. This is much faster for the underlying
    // store. The markers are on the input anyway.
    if (page.getFromMetadata(FetcherJob.REDIRECT_DISCOVERED) != null) {
      page.removeFromMetadata(FetcherJob.REDIRECT_DISCOVERED);
    }
    Mark.GENERATE_MARK.removeMarkIfExist(page);
    Mark.FETCH_MARK.removeMarkIfExist(page);
    Utf8 parse_mark = Mark.PARSE_MARK.checkMark(page);
    if (parse_mark != null) {
View Full Code Here
160
161
162
163
164
165
166
167
168
169
170
    int numReduceTasks = 100;
   
    int partitionFromRef = refPartitioner.getPartition("http://www.example.org/", numReduceTasks);
    //init selector entry (score shouldn't matter)
    SelectorEntry selectorEntry = new SelectorEntry("http://www.example.org/", 1337);
    WebPage page = new WebPage();
    int partitionFromSig = sigPartitioner.getPartition(selectorEntry, page, numReduceTasks);
   
    assertEquals("partitions should be same",
        partitionFromRef, partitionFromSig);
   
View Full Code Here
190
191
192
193
194
195
196
197
198
199
200
   
    int numReduceTasks = 100;
   
    int partitionFromRef = refPartitioner.getPartition("http://www.example.org/", numReduceTasks);
    IntWritable intWritable = new IntWritable(1337); //doesn't matter
    WebPage page = new WebPage();
    String key = TableUtil.reverseUrl("http://www.example.org/");
    FetchEntry fetchEntry = new FetchEntry(conf, key, page);
    int partitionFromSig = sigPartitioner.getPartition(intWritable, fetchEntry, numReduceTasks);
   
    assertEquals("partitions should be same",
View Full Code Here
269
270
271
272
273
274
275
276
277
278
279
   * @param score
   * @return Constructed object
   */
  private URLWebPage createURLWebPage(final String url,
      final int fetchInterval, final float score) {
    WebPage page = new WebPage();
    page.setFetchInterval(fetchInterval);
    page.setScore(score);
    page.setStatus(CrawlStatus.STATUS_UNFETCHED);
    return new URLWebPage(url, page);
  }
View Full Code Here
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
      LOG.info("fetching: " + url);
    }

    ProtocolFactory factory = new ProtocolFactory(conf);
    Protocol protocol = factory.getProtocol(url);
    WebPage page = new WebPage();
    Content content = protocol.getProtocolOutput(url, page).getContent();
    page.setBaseUrl(new org.apache.avro.util.Utf8(url));
    page.setContent(ByteBuffer.wrap(content.getContent()));

    if (force) {
      content.setContentType(contentType);
    } else {
      contentType = content.getContentType();
    }

    if (contentType == null) {
      System.err.println("");
      return (-1);
    }

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

    page.setContentType(new Utf8(contentType));

    Parse parse = new ParseUtil(conf).parse(url, page);

    if (parse == null) {
      System.err.println("Problem with parse - check log");
      return (-1);
    }

    System.out.print("---------\nUrl\n---------------\n");
    System.out.print(url + "\n");
    System.out.print("---------\nMetadata\n---------\n");
    Map<Utf8, ByteBuffer> metadata = page.getMetadata();
    StringBuffer sb = new StringBuffer();
    if (metadata != null) {
      Iterator<Entry<Utf8, ByteBuffer>> iterator = metadata.entrySet()
          .iterator();
      while (iterator.hasNext()) {
View Full Code Here
37
38
39
40
41
42
43
44
45
46
    IndexingFilters filters = new IndexingFilters(conf);
//    filters.filter(new NutchDocument(), new ParseImpl("text", new ParseData(
//        new ParseStatus(), "title", new Outlink[0], new Metadata())), new Text(
//        "http://www.example.com/"), new CrawlDatum(), new Inlinks());
    WebPage page = new WebPage();
    page.setText(new Utf8("text"));
    page.setTitle(new Utf8("title"));
    filters.filter(new NutchDocument(),"http://www.example.com/",page);
  }
View Full Code Here
TOP

Related Classes of org.apache.nutch.storage.WebPage

  • org.apache.gora.persistency.impl.StateManagerImpl
  • org.apache.nutch.analysis.lang.TestHTMLLanguageParser
  • org.apache.nutch.api.DbReader$DbIterator
  • org.apache.nutch.crawl.DbUpdateReducer
  • org.apache.nutch.crawl.InjectorJob$UrlMapper
  • org.apache.nutch.crawl.TestGenerator
  • org.apache.nutch.crawl.TestInjector
  • org.apache.nutch.crawl.TestURLPartitioner
  • org.apache.nutch.crawl.WebTableReader
  • org.apache.nutch.fetcher.FetcherReducer$FetcherThread
    • 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.