Package com.flaptor.hounder.crawler.modules

Examples of com.flaptor.hounder.crawler.modules.FetchDocument

111
112
113
114
115
116
117
118
119
120
121
        Iterator<FetchDocument> iter = fetchdata.iterator();

        // Feed the thread pool queue.
        while (iter.hasNext() && Crawler.running()) {
            FetchDocument doc = iter.next();
            Runnable processorJob = new ProcessorJob(doc, oldPageDB, newPageDB);
            pool.execute(processorJob);
        }

        // So the fetchdata ended, or the crawler is no longer running.
View Full Code Here
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
                    // At this point, we don't hace the fetched data, but we do
                    // have the original and the new url, so we store the mapping.
                    redirects.put(rec.newurl, rec.origurl);
                } else {
                    // This is a non-redirected page.
                    fetchdata.addDoc(new FetchDocument(page, rec.origurl, rec.content, rec.header, success(rec), recoverable(rec), internalError(rec), true));
                }
            }
        }
        // Now go through the redirects.
        for (SegmentRecord rec : unknownPages) {
            FetchDocument doc = null;
            if (redirects.containsKey(rec.newurl)) {
                rec.origurl = redirects.get(rec.newurl);
                page = fetchlist.getPage(rec.origurl);
                if (null != page) {
                    // Override URL with fetched URL if the fetcher is configured to do so
                    if (!keepUrl) {
                        try {
                            page.setUrl(rec.newurl);
                        } catch (MalformedURLException e) {
                            logger.debug("Malformed redirect url. Keeping original url.",e);
                        }
                    }
                    // finally we could reconstruct the redirect and can now store the page.
                    doc = new FetchDocument(page, rec.origurl, rec.content, rec.header, success(rec), recoverable(rec), internalError(rec), true);
                }
                if (null != doc) {
                    fetchdata.addDoc(doc);
                } else {
                    logger.error("Unknown page fetched. This is a bug in Nutch9Fetcher.");
View Full Code Here
72
73
74
75
76
77
78
79
80
                    Map<String,String> header = new HashMap<String,String>(); // this info is lost, it should be stored in the cache along with the page contents.
                    boolean success = true;
                    boolean recoverable = true;
                    boolean internalError = false;
                    boolean changed = false;
                    doc = new FetchDocument(page, url, content, header, success, recoverable, internalError, changed);
                }
            }
        }
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
            return (null != doc);
        }


        public synchronized FetchDocument next () {
            FetchDocument ret = doc;
            if (null == doc) { 
                throw new NoSuchElementException("No more pages in the pagedb and cache");
            }
            advance();
            return ret;
View Full Code Here
34
35
36
37
38
39
40
41
        cbv = new ConstantBoostValue(config);
    }

    @TestInfo(testType = TestInfo.TestType.UNIT)
    public void testHasValue() throws Exception {
        FetchDocument doc = new FetchDocument(new Page("",1f));
        assertTrue(cbv.hasValue(doc));
    }
View Full Code Here
40
41
42
43
44
45
46
47
        assertTrue(cbv.hasValue(doc));
    }

    @TestInfo(testType = TestInfo.TestType.UNIT)
    public void testGetValue() throws Exception {
        FetchDocument doc = new FetchDocument(new Page("",1f));
        assertTrue(new Double(1000).equals(cbv.getValue(doc)));
    }
View Full Code Here
66
67
68
69
70
71
72
73
74
75
                text = TestUtils.randomText(5,50);
                title = TestUtils.randomText(2,5);
                content = text.getBytes();
                header.put("length",String.valueOf(content.length));
            }
            FetchDocument doc = new FetchDocument(page, url, text, title, links, content, header, success, recoverable, internalError, changed);
            fetchdata.addDoc(doc);
        }
        return fetchdata;
    }
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
74
75
76
    }

    @TestInfo(testType = TestInfo.TestType.UNIT)
    public void testApplyBoost() throws MalformedURLException {
        Page page = new Page("http://test.flaptor.com",1f);
        FetchDocument doc = new FetchDocument(page);
        kbm.applyBoost(doc,times);

        String text = doc.getIndexableAttribute(field).toString();
        int found = 0;
        for (String value : text.split(" ")) {
            if (value.equals(keyword)){
                found++;
            }
View Full Code Here
TOP

Related Classes of com.flaptor.hounder.crawler.modules.FetchDocument

  • com.flaptor.hounder.crawler.FetchdataProcessor
  • com.flaptor.hounder.crawler.modules.boost.ConstantBoostValueTest
  • com.flaptor.hounder.crawler.modules.boost.KeywordBoostMethodTest
  • com.flaptor.hounder.crawler.Nutch9Fetcher
  • com.flaptor.hounder.crawler.PageCache$PageCacheIterator
  • com.flaptor.hounder.crawler.pagedb.Link
  • com.flaptor.hounder.crawler.SimFetcher
  • com.flaptor.util.Config
  • com.flaptor.util.parser.HtmlParser
  • com.flaptor.util.parser.IParser
    • 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.