nutch无法下载中文文件的问题［解决］

nutch无法下载中文文件的问题比如：http://www.example.com/中文.pdf

 

wireshark抓包后发现是其无法正确encode中文。解决办法修改src/java/org/apache/nutch/fetcher/Fetcher.java 加上编码功能

 

附上

Fetcher.java：

 

/* * Licensed to the Apache Software Foundation (ASF) under one or more * contributor license agreements. See the NOTICE file distributed with * this work for additional information regarding copyright ownership. * The ASF licenses this file to You under the Apache License, Version 2.0 * (the "License"); you may not use this file except in compliance with * the License. You may obtain a copy of the License at * * http://www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an "AS IS" BASIS, * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * See the License for the specific language governing permissions and * limitations under the License. */ package org.apache.nutch.fetcher; import java.io.IOException; import java.net.InetAddress; import java.net.MalformedURLException; import java.net.URL; import java.net.UnknownHostException; import java.util.*; import java.util.Map.Entry; import java.util.concurrent.atomic.AtomicInteger; import java.util.concurrent.atomic.AtomicLong; // Commons Logging imports import org.apache.commons.logging.Log; import org.apache.commons.logging.LogFactory; import org.apache.hadoop.io.*; import org.apache.hadoop.fs.*; import org.apache.hadoop.conf.*; import org.apache.hadoop.mapred.*; import org.apache.hadoop.util.StringUtils; import org.apache.hadoop.util.Tool; import org.apache.hadoop.util.ToolRunner; import org.apache.nutch.crawl.CrawlDatum; import org.apache.nutch.crawl.NutchWritable; import org.apache.nutch.crawl.SignatureFactory; import org.apache.nutch.metadata.Metadata; import org.apache.nutch.metadata.Nutch; import org.apache.nutch.net.*; import org.apache.nutch.protocol.*; import org.apache.nutch.parse.*; import org.apache.nutch.scoring.ScoringFilterException; import org.apache.nutch.scoring.ScoringFilters; import org.apache.nutch.util.*; import java.io.UnsupportedEncodingException; import java.net.URLEncoder; /** * A queue-based fetcher. * * <p>This fetcher uses a well-known model of one producer (a QueueFeeder) * and many consumers (FetcherThread-s). * * <p>QueueFeeder reads input fetchlists and * populates a set of FetchItemQueue-s, which hold FetchItem-s that * describe the items to be fetched. There are as many queues as there are unique * hosts, but at any given time the total number of fetch items in all queues * is less than a fixed number (currently set to a multiple of the number of * threads). * * <p>As items are consumed from the queues, the QueueFeeder continues to add new * input items, so that their total count stays fixed (FetcherThread-s may also * add new items to the queues e.g. as a results of redirection) - until all * input items are exhausted, at which point the number of items in the queues * begins to decrease. When this number reaches 0 fetcher will finish. * * <p>This fetcher implementation handles per-host blocking itself, instead * of delegating this work to protocol-specific plugins. * Each per-host queue handles its own "politeness" settings, such as the * maximum number of concurrent requests and crawl delay between consecutive * requests - and also a list of requests in progress, and the time the last * request was finished. As FetcherThread-s ask for new items to be fetched, * queues may return eligible items or null if for "politeness" reasons this * host's queue is not yet ready. * * <p>If there are still unfetched items in the queues, but none of the items * are ready, FetcherThread-s will spin-wait until either some items become * available, or a timeout is reached (at which point the Fetcher will abort, * assuming the task is hung). * * @author Andrzej Bialecki */ public class Fetcher extends Configured implements Tool, MapRunnable<Text, CrawlDatum, Text, NutchWritable> { public static final int PERM_REFRESH_TIME = 5; public static final String CONTENT_REDIR = "content"; public static final String PROTOCOL_REDIR = "protocol"; public static final Log LOG = LogFactory.getLog(Fetcher.class); public static class InputFormat extends SequenceFileInputFormat<Text, CrawlDatum> { /** Don't split inputs, to keep things polite. */ public InputSplit[] getSplits(JobConf job, int nSplits) throws IOException { FileStatus[] files = listStatus(job); FileSplit[] splits = new FileSplit[files.length]; for (int i = 0; i < files.length; i++) { FileStatus cur = files[i]; splits[i] = new FileSplit(cur.getPath(), 0, cur.getLen(), (String[])null); } return splits; } } private OutputCollector<Text, NutchWritable> output; private Reporter reporter; private String segmentName; private AtomicInteger activeThreads = new AtomicInteger(0); private AtomicInteger spinWaiting = new AtomicInteger(0); private long start = System.currentTimeMillis(); // start time of fetcher run private AtomicLong lastRequestStart = new AtomicLong(start); private AtomicLong bytes = new AtomicLong(0); // total bytes fetched private AtomicInteger pages = new AtomicInteger(0); // total pages fetched private AtomicInteger errors = new AtomicInteger(0); // total pages errored private boolean storingContent; private boolean parsing; FetchItemQueues fetchQueues; QueueFeeder feeder; /** * This class described the item to be fetched. */ private static class FetchItem { String queueID; Text url; URL u; CrawlDatum datum; public FetchItem(Text url, URL u, CrawlDatum datum, String queueID) { this.url = url; this.u = u; this.datum = datum; this.queueID = queueID; } /** Create an item. Queue id will be created based on <code>byIP</code> * argument, either as a protocol + hostname pair, or protocol + IP * address pair. */ public static FetchItem create(Text url, CrawlDatum datum, boolean byIP) { String queueID; URL u = null; try { u = new URL(url.toString()); } catch (Exception e) { LOG.warn("Cannot parse url: " + url, e); return null; } String proto = u.getProtocol().toLowerCase(); String host; if (byIP) { try { InetAddress addr = InetAddress.getByName(u.getHost()); host = addr.getHostAddress(); } catch (UnknownHostException e) { // unable to resolve it, so don't fall back to host name LOG.warn("Unable to resolve: " + u.getHost() + ", skipping."); return null; } } else { host = u.getHost(); if (host == null) { LOG.warn("Unknown host for url: " + url + ", skipping."); return null; } host = host.toLowerCase(); } queueID = proto + "://" + host; return new FetchItem(url, u, datum, queueID); } public CrawlDatum getDatum() { return datum; } public String getQueueID() { return queueID; } public Text getUrl() { return url; } public URL getURL2() { return u; } } /** * This class handles FetchItems which come from the same host ID (be it * a proto/hostname or proto/IP pair). It also keeps track of requests in * progress and elapsed time between requests. */ private static class FetchItemQueue { List<FetchItem> queue = Collections.synchronizedList(new LinkedList<FetchItem>()); Set<FetchItem> inProgress = Collections.synchronizedSet(new HashSet<FetchItem>()); AtomicLong nextFetchTime = new AtomicLong(); AtomicInteger exceptionCounter = new AtomicInteger(); long crawlDelay; long minCrawlDelay; int maxThreads; Configuration conf; public FetchItemQueue(Configuration conf, int maxThreads, long crawlDelay, long minCrawlDelay) { this.conf = conf; this.maxThreads = maxThreads; this.crawlDelay = crawlDelay; this.minCrawlDelay = minCrawlDelay; // ready to start setEndTime(System.currentTimeMillis() - crawlDelay); } public synchronized int emptyQueue() { int presize = queue.size(); queue.clear(); return presize; } public int getQueueSize() { return queue.size(); } public int getInProgressSize() { return inProgress.size(); } public int incrementExceptionCounter() { return exceptionCounter.incrementAndGet(); } public void finishFetchItem(FetchItem it, boolean asap) { if (it != null) { inProgress.remove(it); setEndTime(System.currentTimeMillis(), asap); } } public void addFetchItem(FetchItem it) { if (it == null) return; queue.add(it); } public void addInProgressFetchItem(FetchItem it) { if (it == null) return; inProgress.add(it); } public FetchItem getFetchItem() { if (inProgress.size() >= maxThreads) return null; long now = System.currentTimeMillis(); if (nextFetchTime.get() > now) return null; FetchItem it = null; if (queue.size() == 0) return null; try { it = queue.remove(0); inProgress.add(it); } catch (Exception e) { LOG.error("Cannot remove FetchItem from queue or cannot add it to inProgress queue", e); } return it; } public synchronized void dump() { LOG.info(" maxThreads = " + maxThreads); LOG.info(" inProgress = " + inProgress.size()); LOG.info(" crawlDelay = " + crawlDelay); LOG.info(" minCrawlDelay = " + minCrawlDelay); LOG.info(" nextFetchTime = " + nextFetchTime.get()); LOG.info(" now = " + System.currentTimeMillis()); for (int i = 0; i < queue.size(); i++) { FetchItem it = queue.get(i); LOG.info(" " + i + ". " + it.url); } } private void setEndTime(long endTime) { setEndTime(endTime, false); } private void setEndTime(long endTime, boolean asap) { if (!asap) nextFetchTime.set(endTime + (maxThreads > 1 ? minCrawlDelay : crawlDelay)); else nextFetchTime.set(endTime); } } /** * Convenience class - a collection of queues that keeps track of the total * number of items, and provides items eligible for fetching from any queue. */ private static class FetchItemQueues { public static final String DEFAULT_ID = "default"; Map<String, FetchItemQueue> queues = new HashMap<String, FetchItemQueue>(); AtomicInteger totalSize = new AtomicInteger(0); int maxThreads; boolean byIP; long crawlDelay; long minCrawlDelay; long timelimit = -1; int maxExceptionsPerQueue = -1; Configuration conf; public FetchItemQueues(Configuration conf) { this.conf = conf; this.maxThreads = conf.getInt("fetcher.threads.per.host", 1); // backward-compatible default setting this.byIP = conf.getBoolean("fetcher.threads.per.host.by.ip", false); this.crawlDelay = (long) (conf.getFloat("fetcher.server.delay", 1.0f) * 1000); this.minCrawlDelay = (long) (conf.getFloat("fetcher.server.min.delay", 0.0f) * 1000); this.timelimit = conf.getLong("fetcher.timelimit.mins", -1); this.maxExceptionsPerQueue = conf.getInt("fetcher.max.exceptions.per.queue", -1); } public int getTotalSize() { return totalSize.get(); } public int getQueueCount() { return queues.size(); } public void addFetchItem(Text url, CrawlDatum datum) { FetchItem it = FetchItem.create(url, datum, byIP); if (it != null) addFetchItem(it); } public synchronized void addFetchItem(FetchItem it) { FetchItemQueue fiq = getFetchItemQueue(it.queueID); fiq.addFetchItem(it); totalSize.incrementAndGet(); } public void finishFetchItem(FetchItem it) { finishFetchItem(it, false); } public void finishFetchItem(FetchItem it, boolean asap) { FetchItemQueue fiq = queues.get(it.queueID); if (fiq == null) { LOG.warn("Attempting to finish item from unknown queue: " + it); return; } fiq.finishFetchItem(it, asap); } public synchronized FetchItemQueue getFetchItemQueue(String id) { FetchItemQueue fiq = queues.get(id); if (fiq == null) { // initialize queue fiq = new FetchItemQueue(conf, maxThreads, crawlDelay, minCrawlDelay); queues.put(id, fiq); } return fiq; } public synchronized FetchItem getFetchItem() { Iterator<Map.Entry<String, FetchItemQueue>> it = queues.entrySet().iterator(); while (it.hasNext()) { FetchItemQueue fiq = it.next().getValue(); // reap empty queues if (fiq.getQueueSize() == 0 && fiq.getInProgressSize() == 0) { it.remove(); continue; } FetchItem fit = fiq.getFetchItem(); if (fit != null) { totalSize.decrementAndGet(); return fit; } } return null; } // called only once the feeder has stopped public synchronized int checkTimelimit() { int count = 0; if (System.currentTimeMillis() >= timelimit && timelimit != -1) { // emptying the queues for (String id : queues.keySet()) { FetchItemQueue fiq = queues.get(id); if (fiq.getQueueSize() == 0) continue; LOG.info("* queue: " + id + " >> timelimit! "); int deleted = fiq.emptyQueue(); for (int i = 0; i < deleted; i++) { totalSize.decrementAndGet(); } count += deleted; } // there might also be a case where totalsize !=0 but number of queues // == 0 // in which case we simply force it to 0 to avoid blocking if (totalSize.get() != 0 && queues.size() == 0) totalSize.set(0); } return count; } /** * Increment the exception counter of a queue in case of an exception e.g. * timeout; when higher than a given threshold simply empty the queue. * * @param queueid * @return number of purged items */ public synchronized int checkExceptionThreshold(String queueid) { FetchItemQueue fiq = queues.get(queueid); if (fiq == null) { return 0; } if (fiq.getQueueSize() == 0) { return 0; } int excCount = fiq.incrementExceptionCounter(); if (maxExceptionsPerQueue!= -1 && excCount >= maxExceptionsPerQueue) { // too many exceptions for items in this queue - purge it int deleted = fiq.emptyQueue(); LOG.info("* queue: " + queueid + " >> removed " + deleted + " URLs from queue because " + excCount + " exceptions occurred"); for (int i = 0; i < deleted; i++) { totalSize.decrementAndGet(); } return deleted; } return 0; } public synchronized void dump() { for (String id : queues.keySet()) { FetchItemQueue fiq = queues.get(id); if (fiq.getQueueSize() == 0) continue; LOG.info("* queue: " + id); fiq.dump(); } } } /** * This class feeds the queues with input items, and re-fills them as * items are consumed by FetcherThread-s. */ private static class QueueFeeder extends Thread { private RecordReader<Text, CrawlDatum> reader; private FetchItemQueues queues; private int size; private long timelimit = -1; public QueueFeeder(RecordReader<Text, CrawlDatum> reader, FetchItemQueues queues, int size) { this.reader = reader; this.queues = queues; this.size = size; this.setDaemon(true); this.setName("QueueFeeder"); } public void setTimeLimit(long tl) { timelimit = tl; } public void run() { boolean hasMore = true; int cnt = 0; int timelimitcount = 0; while (hasMore) { if (System.currentTimeMillis() >= timelimit && timelimit != -1) { // enough .. lets' simply // read all the entries from the input without processing them try { Text url = new Text(); CrawlDatum datum = new CrawlDatum(); hasMore = reader.next(url, datum); timelimitcount++; } catch (IOException e) { LOG.fatal("QueueFeeder error reading input, record " + cnt, e); return; } continue; } int feed = size - queues.getTotalSize(); if (feed <= 0) { // queues are full - spin-wait until they have some free space try { Thread.sleep(1000); } catch (Exception e) {}; continue; } else { LOG.debug("-feeding " + feed + " input urls ..."); while (feed > 0 && hasMore) { try { Text url = new Text(); CrawlDatum datum = new CrawlDatum(); hasMore = reader.next(url, datum); if (hasMore) { queues.addFetchItem(url, datum); cnt++; feed--; } } catch (IOException e) { LOG.fatal("QueueFeeder error reading input, record " + cnt, e); return; } } } } LOG.info("QueueFeeder finished: total " + cnt + " records + hit by time limit :" + timelimitcount); } } /** * This class picks items from queues and fetches the pages. */ private class FetcherThread extends Thread { private Configuration conf; private URLFilters urlFilters; private ScoringFilters scfilters; private ParseUtil parseUtil; private URLNormalizers normalizers; private ProtocolFactory protocolFactory; private long maxCrawlDelay; private boolean byIP; private int maxRedirect; private String reprUrl; private boolean redirecting; private int redirectCount; private boolean ignoreExternalLinks; public FetcherThread(Configuration conf) { this.setDaemon(true); // don't hang JVM on exit this.setName("FetcherThread"); // use an informative name this.conf = conf; this.urlFilters = new URLFilters(conf); this.scfilters = new ScoringFilters(conf); this.parseUtil = new ParseUtil(conf); this.protocolFactory = new ProtocolFactory(conf); this.normalizers = new URLNormalizers(conf, URLNormalizers.SCOPE_FETCHER); this.maxCrawlDelay = conf.getInt("fetcher.max.crawl.delay", 30) * 1000; this.byIP = conf.getBoolean("fetcher.threads.per.host.by.ip", false); this.maxRedirect = conf.getInt("http.redirect.max", 3); this.ignoreExternalLinks = conf.getBoolean("db.ignore.external.links", false); } public void run() { activeThreads.incrementAndGet(); // count threads FetchItem fit = null; try { while (true) { fit = fetchQueues.getFetchItem(); if (fit == null) { if (feeder.isAlive() || fetchQueues.getTotalSize() > 0) { LOG.debug(getName() + " spin-waiting ..."); // spin-wait. spinWaiting.incrementAndGet(); try { Thread.sleep(500); } catch (Exception e) {} spinWaiting.decrementAndGet(); continue; } else { // all done, finish this thread return; } } System.out.println("罗磊说改URL编码"); System.out.println("罗磊说改URL Origin : " + fit.url.toString()); String utf8url = ""; try{ String fiturl = fit.url.toString(); int lastSlide = fiturl.lastIndexOf('/'); if (lastSlide == fiturl.length()) { utf8url = fiturl; } else { utf8url = fiturl.substring(0, lastSlide+1) + URLEncoder.encode(fiturl.substring(lastSlide+1), "UTF-8"); } }catch (UnsupportedEncodingException e) { e.printStackTrace(); } System.out.println("罗磊说改URL now : " + utf8url); Text urlText = new Text(utf8url); lastRequestStart.set(System.currentTimeMillis()); Text reprUrlWritable = (Text) fit.datum.getMetaData().get(Nutch.WRITABLE_REPR_URL_KEY); if (reprUrlWritable == null) { reprUrl = urlText.toString(); } else { reprUrl = reprUrlWritable.toString(); } try { if (LOG.isInfoEnabled()) { LOG.info("fetching " + urlText); } // fetch the page redirecting = false; redirectCount = 0; do { if (LOG.isDebugEnabled()) { LOG.debug("redirectCount=" + redirectCount); } redirecting = false; Protocol protocol = this.protocolFactory.getProtocol(urlText.toString()); RobotRules rules = protocol.getRobotRules(urlText, fit.datum); if (!rules.isAllowed(fit.u)) { // unblock fetchQueues.finishFetchItem(fit, true); if (LOG.isDebugEnabled()) { LOG.debug("Denied by robots.txt: " + urlText); } output(urlText, fit.datum, null, ProtocolStatus.STATUS_ROBOTS_DENIED, CrawlDatum.STATUS_FETCH_GONE); reporter.incrCounter("FetcherStatus", "robots_denied", 1); continue; } if (rules.getCrawlDelay() > 0) { if (rules.getCrawlDelay() > maxCrawlDelay) { // unblock fetchQueues.finishFetchItem(fit, true); LOG.debug("Crawl-Delay for " + urlText + " too long (" + rules.getCrawlDelay() + "), skipping"); output(urlText, fit.datum, null, ProtocolStatus.STATUS_ROBOTS_DENIED, CrawlDatum.STATUS_FETCH_GONE); reporter.incrCounter("FetcherStatus", "robots_denied_maxcrawldelay", 1); continue; } else { FetchItemQueue fiq = fetchQueues.getFetchItemQueue(fit.queueID); fiq.crawlDelay = rules.getCrawlDelay(); } } ProtocolOutput output = protocol.getProtocolOutput(urlText, fit.datum); ProtocolStatus status = output.getStatus(); Content content = output.getContent(); ParseStatus pstatus = null; // unblock queue fetchQueues.finishFetchItem(fit); String urlString = urlText.toString(); reporter.incrCounter("FetcherStatus", status.getName(), 1); switch(status.getCode()) { case ProtocolStatus.WOULDBLOCK: // retry ? fetchQueues.addFetchItem(fit); break; case ProtocolStatus.SUCCESS: // got a page pstatus = output(urlText, fit.datum, content, status, CrawlDatum.STATUS_FETCH_SUCCESS); updateStatus(content.getContent().length); if (pstatus != null && pstatus.isSuccess() && pstatus.getMinorCode() == ParseStatus.SUCCESS_REDIRECT) { String newUrl = pstatus.getMessage(); int refreshTime = Integer.valueOf(pstatus.getArgs()[1]); Text redirUrl = handleRedirect(urlText, fit.datum, urlString, newUrl, refreshTime < Fetcher.PERM_REFRESH_TIME, Fetcher.CONTENT_REDIR); if (redirUrl != null) { CrawlDatum newDatum = new CrawlDatum(CrawlDatum.STATUS_DB_UNFETCHED, fit.datum.getFetchInterval(), fit.datum.getScore()); // transfer existing metadata to the redir newDatum.getMetaData().putAll(fit.datum.getMetaData()); scfilters.initialScore(redirUrl, newDatum); if (reprUrl != null) { newDatum.getMetaData().put(Nutch.WRITABLE_REPR_URL_KEY, new Text(reprUrl)); } fit = FetchItem.create(redirUrl, newDatum, byIP); if (fit != null) { FetchItemQueue fiq = fetchQueues.getFetchItemQueue(fit.queueID); fiq.addInProgressFetchItem(fit); } else { // stop redirecting redirecting = false; reporter.incrCounter("FetcherStatus", "FetchItem.notCreated.redirect", 1); } } } break; case ProtocolStatus.MOVED: // redirect case ProtocolStatus.TEMP_MOVED: int code; boolean temp; if (status.getCode() == ProtocolStatus.MOVED) { code = CrawlDatum.STATUS_FETCH_REDIR_PERM; temp = false; } else { code = CrawlDatum.STATUS_FETCH_REDIR_TEMP; temp = true; } output(urlText, fit.datum, content, status, code); String newUrl = status.getMessage(); Text redirUrl = handleRedirect(urlText, fit.datum, urlString, newUrl, temp, Fetcher.PROTOCOL_REDIR); if (redirUrl != null) { CrawlDatum newDatum = new CrawlDatum(CrawlDatum.STATUS_DB_UNFETCHED, fit.datum.getFetchInterval(), fit.datum.getScore()); // transfer existing metadata newDatum.getMetaData().putAll(fit.datum.getMetaData()); scfilters.initialScore(redirUrl, newDatum); if (reprUrl != null) { newDatum.getMetaData().put(Nutch.WRITABLE_REPR_URL_KEY, new Text(reprUrl)); } fit = FetchItem.create(redirUrl, newDatum, byIP); if (fit != null) { FetchItemQueue fiq = fetchQueues.getFetchItemQueue(fit.queueID); fiq.addInProgressFetchItem(fit); } else { // stop redirecting redirecting = false; reporter.incrCounter("FetcherStatus", "FetchItem.notCreated.redirect", 1); } } else { // stop redirecting redirecting = false; } break; case ProtocolStatus.EXCEPTION: logError(urlText, status.getMessage()); int killedURLs = fetchQueues.checkExceptionThreshold(fit.getQueueID()); if (killedURLs!=0) reporter.incrCounter("FetcherStatus", "AboveExceptionThresholdInQueue", killedURLs); /* FALLTHROUGH */ case ProtocolStatus.RETRY: // retry case ProtocolStatus.BLOCKED: output(urlText, fit.datum, null, status, CrawlDatum.STATUS_FETCH_RETRY); break; case ProtocolStatus.GONE: // gone case ProtocolStatus.NOTFOUND: case ProtocolStatus.ACCESS_DENIED: case ProtocolStatus.ROBOTS_DENIED: output(urlText, fit.datum, null, status, CrawlDatum.STATUS_FETCH_GONE); break; case ProtocolStatus.NOTMODIFIED: output(urlText, fit.datum, null, status, CrawlDatum.STATUS_FETCH_NOTMODIFIED); break; default: if (LOG.isWarnEnabled()) { LOG.warn("Unknown ProtocolStatus: " + status.getCode()); } output(urlText, fit.datum, null, status, CrawlDatum.STATUS_FETCH_RETRY); } if (redirecting && redirectCount >= maxRedirect) { fetchQueues.finishFetchItem(fit); if (LOG.isInfoEnabled()) { LOG.info(" - redirect count exceeded " + urlText); } output(urlText, fit.datum, null, ProtocolStatus.STATUS_REDIR_EXCEEDED, CrawlDatum.STATUS_FETCH_GONE); } } while (redirecting && (redirectCount < maxRedirect)); } catch (Throwable t) { // unexpected exception // unblock fetchQueues.finishFetchItem(fit); logError(urlText, t.toString()); output(urlText, fit.datum, null, ProtocolStatus.STATUS_FAILED, CrawlDatum.STATUS_FETCH_RETRY); } } } catch (Throwable e) { if (LOG.isFatalEnabled()) { e.printStackTrace(LogUtil.getFatalStream(LOG)); LOG.fatal("fetcher caught:"+e.toString()); } } finally { if (fit != null) fetchQueues.finishFetchItem(fit); activeThreads.decrementAndGet(); // count threads LOG.info("-finishing thread " + getName() + ", activeThreads=" + activeThreads); } } private Text handleRedirect(Text url, CrawlDatum datum, String urlString, String newUrl, boolean temp, String redirType) throws MalformedURLException, URLFilterException { newUrl = normalizers.normalize(newUrl, URLNormalizers.SCOPE_FETCHER); newUrl = urlFilters.filter(newUrl); if (ignoreExternalLinks) { try { String origHost = new URL(urlString).getHost().toLowerCase(); String newHost = new URL(newUrl).getHost().toLowerCase(); if (!origHost.equals(newHost)) { if (LOG.isDebugEnabled()) { LOG.debug(" - ignoring redirect " + redirType + " from " + urlString + " to " + newUrl + " because external links are ignored"); } return null; } } catch (MalformedURLException e) { } } if (newUrl != null && !newUrl.equals(urlString)) { reprUrl = URLUtil.chooseRepr(reprUrl, newUrl, temp); url = new Text(newUrl); if (maxRedirect > 0) { redirecting = true; redirectCount++; if (LOG.isDebugEnabled()) { LOG.debug(" - " + redirType + " redirect to " + url + " (fetching now)"); } return url; } else { CrawlDatum newDatum = new CrawlDatum(CrawlDatum.STATUS_LINKED, datum.getFetchInterval()); // transfer existing metadata newDatum.getMetaData().putAll(datum.getMetaData()); try { scfilters.initialScore(url, newDatum); } catch (ScoringFilterException e) { e.printStackTrace(); } if (reprUrl != null) { newDatum.getMetaData().put(Nutch.WRITABLE_REPR_URL_KEY, new Text(reprUrl)); } output(url, newDatum, null, null, CrawlDatum.STATUS_LINKED); if (LOG.isDebugEnabled()) { LOG.debug(" - " + redirType + " redirect to " + url + " (fetching later)"); } return null; } } else { if (LOG.isDebugEnabled()) { LOG.debug(" - " + redirType + " redirect skipped: " + (newUrl != null ? "to same url" : "filtered")); } return null; } } private void logError(Text url, String message) { if (LOG.isInfoEnabled()) { LOG.info("fetch of " + url + " failed with: " + message); } errors.incrementAndGet(); } private ParseStatus output(Text key, CrawlDatum datum, Content content, ProtocolStatus pstatus, int status) { datum.setStatus(status); datum.setFetchTime(System.currentTimeMillis()); if (pstatus != null) datum.getMetaData().put(Nutch.WRITABLE_PROTO_STATUS_KEY, pstatus); ParseResult parseResult = null; if (content != null) { Metadata metadata = content.getMetadata(); // add segment to metadata metadata.set(Nutch.SEGMENT_NAME_KEY, segmentName); // add score to content metadata so that ParseSegment can pick it up. try { scfilters.passScoreBeforeParsing(key, datum, content); } catch (Exception e) { if (LOG.isWarnEnabled()) { e.printStackTrace(LogUtil.getWarnStream(LOG)); LOG.warn("Couldn't pass score, url " + key + " (" + e + ")"); } } /* Note: Fetcher will only follow meta-redirects coming from the * original URL. */ if (parsing && status == CrawlDatum.STATUS_FETCH_SUCCESS) { try { parseResult = this.parseUtil.parse(content); } catch (Exception e) { LOG.warn("Error parsing: " + key + ": " + StringUtils.stringifyException(e)); } if (parseResult == null) { byte[] signature = SignatureFactory.getSignature(getConf()).calculate(content, new ParseStatus().getEmptyParse(conf)); datum.setSignature(signature); } } /* Store status code in content So we can read this value during * parsing (as a separate job) and decide to parse or not. */ content.getMetadata().add(Nutch.FETCH_STATUS_KEY, Integer.toString(status)); } try { output.collect(key, new NutchWritable(datum)); if (content != null && storingContent) output.collect(key, new NutchWritable(content)); if (parseResult != null) { for (Entry<Text, Parse> entry : parseResult) { Text url = entry.getKey(); Parse parse = entry.getValue(); ParseStatus parseStatus = parse.getData().getStatus(); if (!parseStatus.isSuccess()) { LOG.warn("Error parsing: " + key + ": " + parseStatus); parse = parseStatus.getEmptyParse(getConf()); } // Calculate page signature. For non-parsing fetchers this will // be done in ParseSegment byte[] signature = SignatureFactory.getSignature(getConf()).calculate(content, parse); // Ensure segment name and score are in parseData metadata parse.getData().getContentMeta().set(Nutch.SEGMENT_NAME_KEY, segmentName); parse.getData().getContentMeta().set(Nutch.SIGNATURE_KEY, StringUtil.toHexString(signature)); // Pass fetch time to content meta parse.getData().getContentMeta().set(Nutch.FETCH_TIME_KEY, Long.toString(datum.getFetchTime())); if (url.equals(key)) datum.setSignature(signature); try { scfilters.passScoreAfterParsing(url, content, parse); } catch (Exception e) { if (LOG.isWarnEnabled()) { e.printStackTrace(LogUtil.getWarnStream(LOG)); LOG.warn("Couldn't pass score, url " + key + " (" + e + ")"); } } output.collect(url, new NutchWritable( new ParseImpl(new ParseText(parse.getText()), parse.getData(), parse.isCanonical()))); } } } catch (IOException e) { if (LOG.isFatalEnabled()) { e.printStackTrace(LogUtil.getFatalStream(LOG)); LOG.fatal("fetcher caught:"+e.toString()); } } // return parse status if it exits if (parseResult != null && !parseResult.isEmpty()) { Parse p = parseResult.get(content.getUrl()); if (p != null) { reporter.incrCounter("ParserStatus", ParseStatus.majorCodes[p.getData().getStatus().getMajorCode()], 1); return p.getData().getStatus(); } } return null; } } public Fetcher() { super(null); } public Fetcher(Configuration conf) { super(conf); } private void updateStatus(int bytesInPage) throws IOException { pages.incrementAndGet(); bytes.addAndGet(bytesInPage); } private void reportStatus() throws IOException { String status; long elapsed = (System.currentTimeMillis() - start)/1000; status = activeThreads + " threads, " + pages+" pages, "+errors+" errors, " + Math.round(((float)pages.get()*10)/elapsed)/10.0+" pages/s, " + Math.round(((((float)bytes.get())*8)/1024)/elapsed)+" kb/s, "; reporter.setStatus(status); } public void configure(JobConf job) { setConf(job); this.segmentName = job.get(Nutch.SEGMENT_NAME_KEY); this.storingContent = isStoringContent(job); this.parsing = isParsing(job); // if (job.getBoolean("fetcher.verbose", false)) { // LOG.setLevel(Level.FINE); // } } public void close() {} public static boolean isParsing(Configuration conf) { return conf.getBoolean("fetcher.parse", true); } public static boolean isStoringContent(Configuration conf) { return conf.getBoolean("fetcher.store.content", true); } public void run(RecordReader<Text, CrawlDatum> input, OutputCollector<Text, NutchWritable> output, Reporter reporter) throws IOException { this.output = output; this.reporter = reporter; this.fetchQueues = new FetchItemQueues(getConf()); int threadCount = getConf().getInt("fetcher.threads.fetch", 10); if (LOG.isInfoEnabled()) { LOG.info("Fetcher: threads: " + threadCount); } feeder = new QueueFeeder(input, fetchQueues, threadCount * 50); //feeder.setPriority((Thread.MAX_PRIORITY + Thread.NORM_PRIORITY) / 2); // the value of the time limit is either -1 or the time where it should finish long timelimit = getConf().getLong("fetcher.timelimit.mins", -1); if (timelimit != -1) feeder.setTimeLimit(timelimit); feeder.start(); // set non-blocking & no-robots mode for HTTP protocol plugins. getConf().setBoolean(Protocol.CHECK_BLOCKING, false); getConf().setBoolean(Protocol.CHECK_ROBOTS, false); for (int i = 0; i < threadCount; i++) { // spawn threads new FetcherThread(getConf()).start(); } // select a timeout that avoids a task timeout long timeout = getConf().getInt("mapred.task.timeout", 10*60*1000)/2; do { // wait for threads to exit try { Thread.sleep(1000); } catch (InterruptedException e) {} reportStatus(); LOG.info("-activeThreads=" + activeThreads + ", spinWaiting=" + spinWaiting.get() + ", fetchQueues.totalSize=" + fetchQueues.getTotalSize()); if (!feeder.isAlive() && fetchQueues.getTotalSize() < 5) { fetchQueues.dump(); } // check timelimit if (!feeder.isAlive()) { int hitByTimeLimit = fetchQueues.checkTimelimit(); if (hitByTimeLimit != 0) reporter.incrCounter("FetcherStatus", "hitByTimeLimit", hitByTimeLimit); } // some requests seem to hang, despite all intentions if ((System.currentTimeMillis() - lastRequestStart.get()) > timeout) { if (LOG.isWarnEnabled()) { LOG.warn("Aborting with "+activeThreads+" hung threads."); } return; } } while (activeThreads.get() > 0); LOG.info("-activeThreads=" + activeThreads); } public void fetch(Path segment, int threads, boolean parsing) throws IOException { checkConfiguration(); if (LOG.isInfoEnabled()) { LOG.info("Fetcher: starting"); LOG.info("Fetcher: segment: " + segment); } // set the actual time for the timelimit relative // to the beginning of the whole job and not of a specific task // otherwise it keeps trying again if a task fails long timelimit = getConf().getLong("fetcher.timelimit.mins", -1); if (timelimit != -1) { timelimit = System.currentTimeMillis() + (timelimit * 60 * 1000); LOG.info("Fetcher Timelimit set for : " + timelimit); getConf().setLong("fetcher.timelimit.mins", timelimit); } JobConf job = new NutchJob(getConf()); job.setJobName("fetch " + segment); job.setInt("fetcher.threads.fetch", threads); job.set(Nutch.SEGMENT_NAME_KEY, segment.getName()); job.setBoolean("fetcher.parse", parsing); // for politeness, don't permit parallel execution of a single task job.setSpeculativeExecution(false); FileInputFormat.addInputPath(job, new Path(segment, CrawlDatum.GENERATE_DIR_NAME)); job.setInputFormat(InputFormat.class); job.setMapRunnerClass(Fetcher.class); FileOutputFormat.setOutputPath(job, segment); job.setOutputFormat(FetcherOutputFormat.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(NutchWritable.class); JobClient.runJob(job); if (LOG.isInfoEnabled()) { LOG.info("Fetcher: done"); } } /** Run the fetcher. */ public static void main(String[] args) throws Exception { int res = ToolRunner.run(NutchConfiguration.create(), new Fetcher(), args); System.exit(res); } public int run(String[] args) throws Exception { String usage = "Usage: Fetcher <segment> [-threads n] [-noParsing]"; if (args.length < 1) { System.err.println(usage); return -1; } Path segment = new Path(args[0]); int threads = getConf().getInt("fetcher.threads.fetch", 10); boolean parsing = true; for (int i = 1; i < args.length; i++) { // parse command line if (args[i].equals("-threads")) { // found -threads option threads = Integer.parseInt(args[++i]); } else if (args[i].equals("-noParsing")) parsing = false; } getConf().setInt("fetcher.threads.fetch", threads); if (!parsing) { getConf().setBoolean("fetcher.parse", parsing); } try { fetch(segment, threads, parsing); return 0; } catch (Exception e) { LOG.fatal("Fetcher: " + StringUtils.stringifyException(e)); return -1; } } private void checkConfiguration() { // ensure that a value has been set for the agent name and that that // agent name is the first value in the agents we advertise for robot // rules parsing String agentName = getConf().get("http.agent.name"); if (agentName == null || agentName.trim().length() == 0) { String message = "Fetcher: No agents listed in 'http.agent.name'" + " property."; if (LOG.isFatalEnabled()) { LOG.fatal(message); } throw new IllegalArgumentException(message); } else { // get all of the agents that we advertise String agentNames = getConf().get("http.robots.agents"); StringTokenizer tok = new StringTokenizer(agentNames, ","); ArrayList<String> agents = new ArrayList<String>(); while (tok.hasMoreTokens()) { agents.add(tok.nextToken().trim()); } // if the first one is not equal to our agent name, log fatal and throw // an exception if (!(agents.get(0)).equalsIgnoreCase(agentName)) { String message = "Fetcher: Your 'http.agent.name' value should be " + "listed first in 'http.robots.agents' property."; if (LOG.isWarnEnabled()) { LOG.warn(message); } } } } }