Package bixo.fetcher

Examples of bixo.fetcher.SimpleHttpFetcher$MyRequestInterceptor


        BasePath statusDirPath = platform.makePath(curWorkingDirPath, CrawlConfig.STATUS_SUBDIR_NAME);
        Tap statusSink = platform.makeTap(platform.makeTextScheme(), statusDirPath, SinkMode.REPLACE);

        // Create the sub-assembly that runs the fetch job
        SimpleHttpFetcher fetcher = new SimpleHttpFetcher(options.getMaxThreads(), fetcherPolicy, userAgent);
        fetcher.setMaxRetryCount(CrawlConfig.MAX_RETRIES);
        fetcher.setSocketTimeout(CrawlConfig.SOCKET_TIMEOUT);
        fetcher.setConnectionTimeout(CrawlConfig.CONNECTION_TIMEOUT);

        // You can also provide a set of mime types you want to restrict what content type you
        // want to deal with - for now keep it simple.
        Set<String> validMimeTypes = new HashSet<String>();
        validMimeTypes.add("text/plain");
View Full Code Here


public class SimpleHttpFetcherIntegrationTest {
   
    @Test
    public final void testNoDomain() {
        BaseFetcher fetcher = new SimpleHttpFetcher(1, ConfigUtils.BIXO_IT_AGENT);
        String url = "http://www.bogusbixodomainxxxxx.com";
       
        try {
            fetcher.get(new ScoredUrlDatum(url));
            Assert.fail("Exception not thrown");
        } catch (Exception e) {
            Assert.assertTrue(e instanceof IOFetchException);
        }
    }
View Full Code Here

            UserAgent userAgent = new UserAgent(options.getAgentName(), EMAIL_ADDRESS, WEB_ADDRESS);
            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);
           
View Full Code Here

        // Just to be really robust, allow a huge number of redirects and retries.
        FetcherPolicy policy = new FetcherPolicy();
        policy.setMaxRedirects(options.getMaxRedirects());
        policy.setMaxContentSize(options.getMaxSize());
        SimpleHttpFetcher fetcher = new SimpleHttpFetcher(1, policy, new FirefoxUserAgent());
        fetcher.setMaxRetryCount(options.getMaxRetries());
       
        // Give a long timeout for parsing
        ParserPolicy parserPolicy = new ParserPolicy(MAX_PARSE_DURATION);
        SimpleParser parser = new SimpleParser(parserPolicy);

        SimpleParser rawParser = new SimpleParser(parserPolicy, true);
       
        // Create Boilperpipe content extractor
        SimpleParser bpParser = new SimpleParser(new BoilerpipeContentExtractor(), new NullLinkExtractor(), parserPolicy);
       
        if (options.isTraceLogging()) {
            Logger.getRootLogger().setLevel(Level.TRACE);
            System.setProperty("bixo.root.level", "TRACE");
        }
       
        String urls[] = options.getUrls() == null ? null : options.getUrls().split(",");
        boolean interactive = (urls == null);
        int index = 0;
       
        while (interactive || (index < urls.length)) {
          String url;
         
          try {
              if (interactive) {
                System.out.print("URL to fetch: ");
                url = readInputLine();
                if (url.length() == 0) {
                  System.exit(0);
                }
              } else {
                url = args[index++];
              }

              System.out.println("Fetching " + url);
            FetchedDatum result = fetcher.get(new ScoredUrlDatum(url));
            System.out.println(String.format("Fetched %s: headers = %s", result.getUrl(), result.getHeaders()));
            System.out.flush();
           
            // System.out.println("Result = " + result.toString());
            ParsedDatum parsed = parser.parse(result);
View Full Code Here

       
        Tap in = makeInputData(platform, "testFetchPipe", "localhost:" + port, numPages, new Payload());

        Pipe pipe = new Pipe("urlSource");
        BaseScoreGenerator scorer = new FixedScoreGenerator();
        BaseFetcher fetcher = new SimpleHttpFetcher(ConfigUtils.BIXO_TEST_AGENT);
        FetchPipe fetchPipe = new FetchPipe(pipe, scorer, fetcher, 1);
       
        String output = "build/test/FetchPipeTest/testFetchPipe";
        BasePath outputPath = platform.makePath(output);
        BasePath statusPath = platform.makePath(outputPath, "status");
View Full Code Here

        Pipe pipe = new Pipe("urlSource");
        BaseScoreGenerator scorer = new FixedScoreGenerator();
        FetcherPolicy policy = new FetcherPolicy();
        policy.setRedirectMode(RedirectMode.FOLLOW_TEMP);
        BaseFetcher fetcher = new SimpleHttpFetcher(1, policy, ConfigUtils.BIXO_TEST_AGENT);
        FetchPipe fetchPipe = new FetchPipe(pipe, scorer, fetcher, 1);
       
        String output = "build/test/FetchPipeTest/testRedirectException";
        BasePath outputPath = platform.makePath(output);
        BasePath statusPath = platform.makePath(outputPath, "status");
View Full Code Here

        FetcherPolicy policy = new FetcherPolicy();
        policy.setCrawlEndTime(System.currentTimeMillis() + 50000);
        // Assume we should only need 10ms for fetching all 10 URLs.
        policy.setRequestTimeout(10);
       
        BaseFetcher fetcher = new SimpleHttpFetcher(1, policy, ConfigUtils.BIXO_TEST_AGENT);
        FetchPipe fetchPipe = new FetchPipe(pipe, scorer, fetcher, 1);
       
        BasePath outputPath = makeOutputPath(platform, "testTerminatingFetchPipe");
        BasePath statusPath = platform.makePath(outputPath, "status");
        Tap status = platform.makeTap(platform.makeBinaryScheme(StatusDatum.FIELDS), statusPath, SinkMode.REPLACE);
View Full Code Here

    @SuppressWarnings({ "unchecked", "rawtypes" })
    @Test
    public void testUsingAllThreads() throws Exception {
        final int maxThreads = 10;
       
        SimpleHttpFetcher fetcher = new SimpleHttpFetcher(maxThreads, ConfigUtils.BIXO_TEST_AGENT);
        BaseScoreGenerator scorer = new FixedScoreGenerator(1.0);
        BaseRobotsParser parser = new SimpleRobotRulesParser();
        FilterAndScoreByUrlAndRobots op = new FilterAndScoreByUrlAndRobots(fetcher, parser, scorer);
       
        FlowProcess fp = Mockito.mock(NullFlowProcess.class);
View Full Code Here

    @SuppressWarnings({ "unchecked", "rawtypes" })
    @Test
    public void testBlockedRobots() throws Exception {
        final int maxThreads = 1;
       
        SimpleHttpFetcher fetcher = new SimpleHttpFetcher(maxThreads, ConfigUtils.BIXO_TEST_AGENT);
        BaseScoreGenerator scorer = new FixedScoreGenerator(1.0);
        BaseRobotsParser parser = new SimpleRobotRulesParser();
        FilterAndScoreByUrlAndRobots op = new FilterAndScoreByUrlAndRobots(fetcher, parser, scorer);
       
        FlowProcess fp = Mockito.mock(NullFlowProcess.class);
View Full Code Here

        BaseScoreGenerator scorer = new LinkScoreGenerator();

        // Create the sub-assembly that runs the fetch job
        int maxThreads = isLocal ? CrawlConfig.DEFAULT_NUM_THREADS_LOCAL :  CrawlConfig.DEFAULT_NUM_THREADS_CLUSTER;
        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);
View Full Code Here

TOP

Related Classes of bixo.fetcher.SimpleHttpFetcher$MyRequestInterceptor

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.