Package org.apache.nutch.storage

Examples of org.apache.nutch.storage.WebPage

109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
      query.setFields(fields);
    }

    Result<String, WebPage> results = store.execute(query);
    while (results.next()) {
      WebPage page = results.get();
      String url = results.getKey();

      if (page == null)
        continue;

      if (requiredMark != null && requiredMark.checkMark(page) == null)
        continue;

      l.add(new URLWebPage(TableUtil.unreverseUrl(url), (WebPage)page.clone()));
    }

    return l;
  }
View Full Code Here
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
43
44
45
46
47
48
49
50
51
52
53
54
55
56
    Configuration conf = NutchConfiguration.create();
    conf.setBoolean("anchorIndexingFilter.deduplicate", true);
    AnchorIndexingFilter filter = new AnchorIndexingFilter();
    filter.setConf(conf);
    NutchDocument doc = new NutchDocument();
    WebPage page = new WebPage();
    page.putToInlinks(new Utf8("http://example1.com/"), new Utf8("cool site"));
    page.putToInlinks(new Utf8("http://example2.com/"), new Utf8("cool site"));
    page.putToInlinks(new Utf8("http://example3.com/"), new Utf8("fun site"));
    filter.filter(doc, "http://myurldoesnotmatter.com/", page);
   
    assertTrue("test if there is an anchor at all", doc.getFieldNames().contains("anchor"));
   
    assertEquals("test dedup, we expect 2", 2, doc.getFieldValues("anchor").size());
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
   *
   */
  public void setContentType(String testTextFile) throws ProtocolNotFound {
    String urlString = "file:" + sampleDir + fileSeparator + testTextFile;
    assertNotNull(urlString);
    WebPage datum = new WebPage();
    Protocol protocol = new ProtocolFactory(conf).getProtocol(urlString);
    ProtocolOutput output = protocol.getProtocolOutput(urlString,datum);
    assertNotNull(output);

    assertEquals("Status code: [" + output.getStatus().getCode()
View Full Code Here
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
      if (url == null) {
        context.getCounter("injector", "urls_filtered").increment(1);
        return;
      } else {                                         // if it passes
      String reversedUrl = TableUtil.reverseUrl(url);  // collect it
      WebPage row = new WebPage();
      row.setFetchTime(curTime);
      row.setFetchInterval(customInterval);

      // now add the metadata
      Iterator<String> keysIter = metadata.keySet().iterator();
      while (keysIter.hasNext()) {
        String keymd = keysIter.next();
        String valuemd = metadata.get(keymd);
        row.putToMetadata(new Utf8(keymd), ByteBuffer.wrap(valuemd.getBytes()));
      }

      if (customScore != -1)
        row.setScore(customScore);
      else
        row.setScore(scoreInjected);

      try {
        scfilters.injectedScore(url, row);
      } catch (ScoringFilterException e) {
        if (LOG.isWarnEnabled()) {
          LOG.warn("Cannot filter injected score for url " + url
          + ", using default (" + e.getMessage() + ")");
        }
      }
      context.getCounter("injector", "urls_injected").increment(1);
      row.putToMarkers(DbUpdaterJob.DISTANCE, new Utf8(String.valueOf(0)));
      Mark.INJECT_MARK.putMark(row, YES_STRING);
      context.write(reversedUrl, row);
    }
    }
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.array(), signature.array()) != 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
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
    byte[] bytes = new byte[(int) file.length()];
    DataInputStream in = new DataInputStream(new FileInputStream(file));
    in.readFully(bytes);
    in.close();

    WebPage page = new WebPage();
    page.setBaseUrl(new Utf8(urlString));
    page.setContent(ByteBuffer.wrap(bytes));
    MimeUtil mimeutil = new MimeUtil(conf);
    String mtype = mimeutil.getMimeType(file);
    page.setContentType(new Utf8(mtype));
    parse = new ParseUtil(conf).parse(urlString, page);
    //begin assertion for tests
    ByteBuffer bbuf = page.getFromMetadata(new Utf8("Rel-Tag"));
    byte[] byteArray = new byte[bbuf.remaining()];
    bbuf.get(byteArray);
    String s = new String(byteArray);
    //bbuf.flip();
    assertEquals("We expect 2 tab-separated rel-tag's extracted by the filter",
View Full Code Here
40
41
42
43
44
45
46
47
48
49
50
51
52
53
    Configuration conf = NutchConfiguration.create();
    RelTagIndexingFilter filter = new RelTagIndexingFilter();
    filter.setConf(conf);
    assertNotNull(filter);
    NutchDocument doc = new NutchDocument();
    WebPage page = new WebPage();
    byte[] bytes = new byte[10];
    ByteBuffer bbuf = ByteBuffer.wrap(bytes);
    page.putToMetadata(new Utf8(RelTagParser.REL_TAG), bbuf);
    try {
      filter.filter(doc, "http://nutch.apache.org/", page);
    } catch (Exception e) {
      e.printStackTrace();
      fail(e.getMessage());
View Full Code Here
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
    IndexingFilters indexers = new IndexingFilters(conf);

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

    WebPage page = new WebPage();
    page.setBaseUrl(new org.apache.avro.util.Utf8(url));
    ProtocolOutput protocolOutput = protocol.getProtocolOutput(url, page);
    page.setProtocolStatus(protocolOutput.getStatus());
    if (protocolOutput.getStatus().getCode() == ProtocolStatusCodes.SUCCESS) {
      page.setStatus(CrawlStatus.STATUS_FETCHED);
      page.setFetchTime(System.currentTimeMillis());
    } else {
      LOG.error("Fetch failed with protocol status: "
          + ProtocolStatusUtils.getName(protocolOutput.getStatus().getCode())
          + ": " + ProtocolStatusUtils.getMessage(protocolOutput.getStatus()));
      return -1;
    }
   
    Content content = protocolOutput.getContent();
    if (content == null) {
      LOG.warn("No content for " + url);
      return 0;
    }

    page.setContent(ByteBuffer.wrap(content.getContent()));
    contentType = content.getContentType();
    if (contentType == null) {
      return -1;
    }
    page.setContentType(new Utf8(contentType));
   
    if (LOG.isInfoEnabled()) {
      LOG.info("parsing: " + url);
      LOG.info("contentType: " + contentType);
    }

    if (ParserJob.isTruncated(url, page)) {
      LOG.warn("Content is truncated, parse may fail!");
    }

    (new ParseUtil(conf)).process(url, page);
    if (!ParseStatusUtils.isSuccess(page.getParseStatus())) {
      LOG.warn("Problem with parse - check log");
      return (-1);
    }

    NutchDocument doc = new NutchDocument();
View Full Code Here
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
  Configuration conf = NutchConfiguration.create();
  BasicIndexingFilter filter = new BasicIndexingFilter();
  filter.setConf(conf);
  assertNotNull(filter);
  NutchDocument doc = new NutchDocument();
  WebPage page = new WebPage();
  page.putToInlinks(new Utf8("http://nutch.apache.org/"), new Utf8("Welcome to Nutch"));
  page.setTitle(new Utf8("Welcome to Nutch"));
    page.setReprUrl(new Utf8("http://www.urldoesnotmatter.org"));
    byte[] bytes = new byte[10];
    ByteBuffer bbuf = ByteBuffer.wrap(bytes);
    page.putToMetadata(Nutch.CACHING_FORBIDDEN_KEY_UTF8, bbuf);
    page.setFetchTime(System.currentTimeMillis());
  try {
    filter.filter(doc, "http://www.apache.org/", page);
  } catch(Exception e) {
    e.printStackTrace();
    fail(e.getMessage());
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.