Package bixo.pipes

Examples of bixo.pipes.FetchPipe

185
186
187
188
189
190
191
192
193
194
195
196
197
        // The scorer is used by the FetchPipe to assign a score to every URL that passes the
        // robots.txt processing. The score is used to sort URLs such that higher scoring URLs
        // are fetched first. If URLs are skipped for any reason(s) lower scoring URLs are skipped.
        BaseScoreGenerator scorer = new FixedScoreGenerator();

        FetchPipe fetchPipe = new FetchPipe(urlsToFetchPipe, scorer, fetcher, platform.getNumReduceTasks());
        Pipe statusPipe = new Pipe("status pipe", fetchPipe.getStatusTailPipe());
        Pipe contentPipe = new Pipe("content pipe", fetchPipe.getContentTailPipe());
        contentPipe = TupleLogger.makePipe(contentPipe, true);
       
        // Take content and split it into content output plus parse to extract URLs.
        SimpleParser parser;
        if (options.isUseBoilerpipe()) {
View Full Code Here
117
118
119
120
121
122
123
124
125
126
127
        FetcherPolicy fetcherPolicy = new FetcherPolicy();
        fetcherPolicy.setMaxRequestsPerConnection(1);
        fetcherPolicy.setCrawlDelay(5 * 1000L);
        BaseFetcher fetcher = new SimpleHttpFetcher(2, fetcherPolicy, userAgent);
        BaseScoreGenerator scorer = new FixedScoreGenerator();
        FetchPipe fetchPipe = new FetchPipe(pipe, scorer, fetcher, 1);

        FlowConnector flowConnector = platform.makeFlowConnector();
        Flow flow = flowConnector.connect(in, FetchPipe.makeSinkMap(status, content), fetchPipe);
        flow.complete();
       
View Full Code Here
164
165
166
167
168
169
170
171
172
173
174
        Pipe pipe = new Pipe("urlSource");

        UserAgent userAgent = new FirefoxUserAgent();
        BaseFetcher fetcher = new SimpleHttpFetcher(10, userAgent);
        BaseScoreGenerator scorer = new FixedScoreGenerator();
        FetchPipe fetchPipe = new FetchPipe(pipe, scorer, fetcher, 1);

        FlowConnector flowConnector = platform.makeFlowConnector();

        Flow flow = flowConnector.connect(in, FetchPipe.makeSinkMap(status, content), fetchPipe);
        flow.complete();
View Full Code Here
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
            Pipe importPipe = new Each("url importer", new Fields("line"), new LoadUrlFunction());
           
            BaseScoreGenerator scorer = new FixedScoreGenerator();
           
            BaseFetcher fetcher = new SimpleHttpFetcher(MAX_THREADS, userAgent);
            FetchPipe fetchPagePipe = new FetchPipe(importPipe, scorer, fetcher, NUM_REDUCERS);
           
            // Here's the pipe that will output UrlDatum tuples, by extracting URLs from the mod_mbox-generated page.
        Pipe mboxPagePipe = new Each(fetchPagePipe.getContentTailPipe(), new ParseModMboxPageFunction(), Fields.RESULTS);

        // Create a named pipe for the status of the mod_mbox-generated pages.
            Pipe mboxPageStatusPipe = new Pipe(MBOX_PAGE_STATUS_PIPE_NAME, fetchPagePipe.getStatusTailPipe());

            // Set up appropriate FetcherPolicy, where we increase the max content size (since mailbox files
            // can be big, e.g. 4MB).
            FetcherPolicy defaultPolicy = new FetcherPolicy();
            defaultPolicy.setMaxContentSize(MAX_CONTENT_SIZE);
            fetcher = new SimpleHttpFetcher(MAX_THREADS, defaultPolicy, userAgent);
           
            // We can create the fetch pipe, and set up our Mbox splitter to run on content.
            FetchPipe fetchMboxPipe = new FetchPipe(mboxPagePipe, scorer, fetcher, NUM_REDUCERS);
            SplitEmails splitterPipe = new SplitEmails(fetchMboxPipe);
           
            // Now create the pipe that's going to analyze the emails we get after splitting them up.
            Pipe analysisPipe = new Pipe(ANALYZER_PIPE_NAME, splitterPipe.getTails()[0]);
            analysisPipe = new Each(analysisPipe, new ParseEmailFunction());
View Full Code Here
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
        SimpleHttpFetcher fetcher = new SimpleHttpFetcher(maxThreads, fetcherPolicy, userAgent);
        fetcher.setMaxRetryCount(CrawlConfig.MAX_RETRIES);
        fetcher.setSocketTimeout(CrawlConfig.SOCKET_TIMEOUT);
        fetcher.setConnectionTimeout(CrawlConfig.CONNECTION_TIMEOUT);

        FetchPipe fetchPipe = new FetchPipe(urlsToFetchPipe, scorer, fetcher, platform.getNumReduceTasks());
        Pipe statusPipe = new Pipe("status pipe", fetchPipe.getStatusTailPipe());
        Pipe contentPipe = new Pipe("content pipe", fetchPipe.getContentTailPipe());
        contentPipe = TupleLogger.makePipe(contentPipe, true);

        // Create a parser that returns back the raw HTML (cleaned up by Tika) as the parsed content.
        SimpleParser parser = new SimpleParser(new ParserPolicy(), true);
        ParsePipe parsePipe = new ParsePipe(fetchPipe.getContentTailPipe(), parser);
       
        Pipe analyzerPipe = new Pipe("analyzer pipe");
        analyzerPipe = new Each(parsePipe.getTailPipe(), new AnalyzeHtml());
       
        Pipe outlinksPipe = new Pipe("outlinks pipe", analyzerPipe);
View Full Code Here
TOP

Related Classes of bixo.pipes.FetchPipe

  • bixo.config.DefaultFetchJobPolicy
  • bixo.datum.FetchedDatum
  • bixo.datum.ScoredUrlDatum
  • bixo.datum.StatusDatum
  • bixo.datum.UrlStatus
  • bixo.examples.crawl.DemoCrawlWorkflow
  • bixo.examples.webmining.DemoWebMiningWorkflow
  • bixo.fetcher.FetcherTest
  • bixo.operations.FetchBuffer
  • bixo.operations.FilterAndScoreByUrlAndRobots
    • 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.