Package cn.edu.hfut.dmic.webcollector.model

Examples of cn.edu.hfut.dmic.webcollector.model.CrawlDatum

218
219
220
221
222
223
224
225
226
227
228
                    }
                    continue;
                }
                while (feed > 0 && hasMore) {

                    CrawlDatum datum = generator.next();
                    hasMore = (datum != null);

                    if (hasMore) {
                        queue.addFetchItem(new FetchItem(datum));
                        feed--;
View Full Code Here
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
                            }
                        }

                        lastRequestStart.set(System.currentTimeMillis());

                        CrawlDatum crawldatum = new CrawlDatum();
                        String url = item.datum.getUrl();
                        crawldatum.setUrl(url);

                        Request request = requestFactory.createRequest(url);
                        Response response = null;

                        for (int i = 0; i <= retry; i++) {
                            if (i > 0) {
                                LogUtils.getLogger().info("retry " + i + "th " + url);
                            }
                            try {
                                response = request.getResponse(crawldatum);
                                break;
                            } catch (Exception ex) {

                            }
                        }

                        crawldatum.setStatus(CrawlDatum.STATUS_DB_FETCHED);
                        crawldatum.setFetchTime(System.currentTimeMillis());

                        Page page = new Page();
                        page.setUrl(url);
                        page.setFetchTime(crawldatum.getFetchTime());

                        if (response == null) {
                            LogUtils.getLogger().info("failed " + url);
                            HandlerUtils.sendMessage(handler, new Message(Fetcher.FETCH_FAILED, page), true);
                            continue;
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
71
72
        if(inject_file.exists())
            writer=new DbWriter<CrawlDatum>(CrawlDatum.class,inject_file,append);
        else
            writer=new DbWriter<CrawlDatum>(CrawlDatum.class,inject_file,false);
        for(String url:urls){
            CrawlDatum crawldatum=new CrawlDatum();
            crawldatum.setUrl(url);
            crawldatum.setStatus(CrawlDatum.STATUS_DB_UNFETCHED);
            writer.write(crawldatum); 
            LogUtils.getLogger().info("inject "+url);
        }
        writer.close();
       
View Full Code Here
41
42
43
44
45
46
47
48
49
50
51
52
53
        iterator=data.iterator();
    }
   
    public void addUrls(Collection<String> urls){
        for(String url:urls){
            CrawlDatum crawldatum=new CrawlDatum();
            crawldatum.setUrl(url);
            crawldatum.setFetchTime(CrawlDatum.FETCHTIME_UNDEFINED);
            crawldatum.setStatus(CrawlDatum.STATUS_DB_UNFETCHED);
            data.add(crawldatum);
        }
        iterator=data.iterator();
    }
View Full Code Here
52
53
54
55
56
57
58
59
60
61
62
63
        iterator=data.iterator();
    }
   
    public void addUrl(String url){
      
        CrawlDatum crawldatum=new CrawlDatum();
        crawldatum.setUrl(url);
        crawldatum.setFetchTime(CrawlDatum.FETCHTIME_UNDEFINED);
        crawldatum.setStatus(CrawlDatum.STATUS_DB_UNFETCHED);
        data.add(crawldatum);
        iterator=data.iterator();
    }
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
        if (!dbreader.hasNext()) {
            return null;
        }

        CrawlDatum crawldatum = dbreader.readNext();

        if (crawldatum == null) {
            return null;
        }

        if (shouldFilter(crawldatum.getUrl())) {
            return next();
        }
        return crawldatum;
    }
View Full Code Here
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
        int sum=0;
        int sum_fetched=0;
        int sum_unfetched=0;
       
       
        CrawlDatum crawldatum=null;

        System.out.println("start read:");
        while(reader.hasNext()){
            crawldatum=reader.readNext();
            System.out.println(crawldatum.getUrl());
            sum++;
            switch(crawldatum.getStatus()){
                case CrawlDatum.STATUS_DB_FETCHED:
                    sum_fetched++;
                    break;
                case CrawlDatum.STATUS_DB_UNFETCHED:
                    sum_unfetched++;
View Full Code Here
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
        DbReader<CrawlDatum> reader_fetch = new DbReader<CrawlDatum>(CrawlDatum.class, file_fetch);

        HashMap<String, Integer> indexmap = new HashMap<String, Integer>();

        ArrayList<CrawlDatum> datums_origin = new ArrayList<CrawlDatum>();
        CrawlDatum datum = null;
        while (reader_current.hasNext()) {
            datum = reader_current.readNext();
            datums_origin.add(datum);
            indexmap.put(datum.getUrl(), datums_origin.size() - 1);
        }

        while (reader_fetch.hasNext()) {
            datum = reader_fetch.readNext();
            if (indexmap.containsKey(datum.getUrl())) {
                if (datum.getStatus() == CrawlDatum.STATUS_DB_UNFETCHED) {
                    continue;
                } else {
                    int preindex = indexmap.get(datum.getUrl());
                    datums_origin.set(preindex, datum);
                    indexmap.put(datum.getUrl(), preindex);
                }

            } else {
                datums_origin.add(datum);
                indexmap.put(datum.getUrl(), datums_origin.size() - 1);
            }

        }
        reader_fetch.close();

        File file_parse = new File(getSegmentPath(), "parse_data/info.avro");
        if (file_parse.exists()) {
            DbReader<ParseData> reader_parse = new DbReader<ParseData>(ParseData.class, file_parse);
            ParseData parseresult = null;
            while (reader_parse.hasNext()) {
                parseresult = reader_parse.readNext();
                for (Link link : parseresult.getLinks()) {
                    datum = new CrawlDatum();
                    datum.setUrl(link.getUrl());
                    datum.setStatus(CrawlDatum.STATUS_DB_UNFETCHED);
                    if (indexmap.containsKey(datum.getUrl())) {
                        continue;
                    } else {
                        datums_origin.add(datum);
                        indexmap.put(datum.getUrl(), datums_origin.size() - 1);
                    }
                }
            }
            reader_parse.close();
        }
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
     * @return 下一个达到时间间隔要求的爬取任务，如果没有符合规则的任务，返回null
     */
    @Override
    public CrawlDatum next() {
        while(true){
        CrawlDatum crawldatum=generator.next();
       
         if(crawldatum==null){
            return null;
        }
        
       
        if(crawldatum.getStatus()==CrawlDatum.STATUS_DB_UNFETCHED){
            return crawldatum;
        }
        if(Config.interval==-1){
            continue;
        }
      
        Long lasttime=crawldatum.getFetchTime();
        if(lasttime+Config.interval>System.currentTimeMillis()){
            continue;
        }
        return crawldatum;
        }
View Full Code Here
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
     */

    @Override
    public CrawlDatum next() {
        while(true){
        CrawlDatum crawldatum=generator.next();
        if(crawldatum==null){
            return null;
        }
        String url=crawldatum.getUrl();
        if(hashset.contains(url)){
            continue;
        }
        else{
            addUrl(url);
View Full Code Here
TOP

Related Classes of cn.edu.hfut.dmic.webcollector.model.CrawlDatum

  • cn.edu.hfut.dmic.webcollector.fetcher.Fetcher$FetcherThread
  • cn.edu.hfut.dmic.webcollector.fetcher.Fetcher$QueueFeeder
  • cn.edu.hfut.dmic.webcollector.generator.CollectionGenerator
  • cn.edu.hfut.dmic.webcollector.generator.DbReader
  • cn.edu.hfut.dmic.webcollector.generator.filter.IntervalFilter
  • cn.edu.hfut.dmic.webcollector.generator.filter.UniqueFilter
  • cn.edu.hfut.dmic.webcollector.generator.filter.URLRegexFilter
  • cn.edu.hfut.dmic.webcollector.generator.FSDbUpdater
  • cn.edu.hfut.dmic.webcollector.generator.FSGenerator
  • cn.edu.hfut.dmic.webcollector.generator.FSInjector
    • 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.