public void autoDetectClues(Content content, boolean filter) {
byte[] data = content.getContent();
if (minConfidence >= 0
&& DETECTABLES.contains(content.getContentType())
&& data.length > MIN_LENGTH) {
CharsetMatch[] matches = null;
// do all these in a try/catch; setText and detect/detectAll
// will sometimes throw exceptions
try {
detector.enableInputFilter(filter);
if (data.length > MIN_LENGTH) {
detector.setText(data);
matches = detector.detectAll();
}
} catch (Exception e) {
LOG.debug("Exception from ICU4J (ignoring): ");
e.printStackTrace(LogUtil.getDebugStream(LOG));
}
if (matches != null) {
for (CharsetMatch match : matches) {
addClue(match.getName(), "detect", match.getConfidence());
}
}
}
// add character encoding coming from HTTP response header
addClue(parseCharacterEncoding(content.getMetadata().get(Response.CONTENT_TYPE)), "header");
}
public SolrRecord(Content recordContent, String fileName) {
if (recordContent != null) {
this.content = recordContent.getContent();
this.contentType = recordContent.getContentType();
this.id = recordContent.getUrl();
this.fileName = new File(fileName).getName();
}
}
public ParseResult getParse(final Content content) {
String resultText = null;
String resultTitle = null;
Outlink[] outlinks = null;
List outLinksList = new ArrayList();
Properties properties = null;
try {
final String contentLen = content.getMetadata().get(Response.CONTENT_LENGTH);
final int len = Integer.parseInt(contentLen);
if (LOG.isDebugEnabled()) {
LOG.debug("ziplen: " + len);
}
final byte[] contentInBytes = content.getContent();
final ByteArrayInputStream bainput = new ByteArrayInputStream(contentInBytes);
final InputStream input = bainput;
if (contentLen != null && contentInBytes.length != len) {
return new ParseStatus(
ParseStatus.FAILED,
ParseStatus.FAILED_TRUNCATED,
"Content truncated at "
+ contentInBytes.length
+ " bytes. Parser can't handle incomplete pdf file.")
.getEmptyParseResult(content.getUrl(), getConf());
}
ZipTextExtractor extractor = new ZipTextExtractor(getConf());
// extract text
resultText =
extractor.extractText(
new ByteArrayInputStream(contentInBytes), content.getUrl(), outLinksList);
} catch (Exception e) {
return new ParseStatus(ParseStatus.FAILED, "Can't be handled as Zip document. " + e)
.getEmptyParseResult(content.getUrl(), getConf());
}
if (resultText == null) {
resultText = "";
}
if (resultTitle == null) {
resultTitle = "";
}
outlinks = (Outlink[]) outLinksList.toArray(new Outlink[0]);
final ParseData parseData =
new ParseData(ParseStatus.STATUS_SUCCESS, resultTitle, outlinks, content.getMetadata());
if (LOG.isTraceEnabled()) {
LOG.trace("Zip file parsed sucessfully !!");
}
return ParseResult.createParseResult(content.getUrl(), new ParseImpl(resultText, parseData));
}
public boolean equals(Object o) {
if (!(o instanceof Content)) {
return false;
}
Content that = (Content) o;
return this.url.equals(that.url)
&& this.base.equals(that.base)
&& Arrays.equals(this.getContent(), that.getContent())
&& this.contentType.equals(that.contentType)
&& this.metadata.equals(that.metadata);
}
@SuppressWarnings("fallthrough")
public void run() {
activeThreads.incrementAndGet(); // count threads
FetchItem fit = null;
try {
// checking for the server to be running and fetcher.parse to be true
if (parsing && NutchServer.getInstance().isRunning()) reportToNutchServer = true;
while (true) {
// creating FetchNode for storing in FetchNodeDb
if (reportToNutchServer) this.fetchNode = new FetchNode();
else this.fetchNode = null;
// check whether must be stopped
if (isHalted()) {
LOG.debug(getName() + " set to halted");
fit = null;
return;
}
fit = ((FetchItemQueues) fetchQueues).getFetchItem();
if (fit == null) {
if (feeder.isAlive() || ((FetchItemQueues) fetchQueues).getTotalSize() > 0) {
LOG.debug(getName() + " spin-waiting ...");
// spin-wait.
((AtomicInteger) spinWaiting).incrementAndGet();
try {
Thread.sleep(500);
} catch (Exception e) {
}
((AtomicInteger) spinWaiting).decrementAndGet();
continue;
} else {
// all done, finish this thread
LOG.info("Thread " + getName() + " has no more work available");
return;
}
}
lastRequestStart.set(System.currentTimeMillis());
Text reprUrlWritable = (Text) fit.datum.getMetaData().get(Nutch.WRITABLE_REPR_URL_KEY);
if (reprUrlWritable == null) {
setReprUrl(fit.url.toString());
} else {
setReprUrl(reprUrlWritable.toString());
}
try {
// fetch the page
redirecting = false;
redirectCount = 0;
do {
if (LOG.isInfoEnabled()) {
LOG.info(
"fetching "
+ fit.url
+ " (queue crawl delay="
+ ((FetchItemQueues) fetchQueues).getFetchItemQueue(fit.queueID).crawlDelay
+ "ms)");
}
if (LOG.isDebugEnabled()) {
LOG.debug("redirectCount=" + redirectCount);
}
redirecting = false;
Protocol protocol = this.protocolFactory.getProtocol(fit.url.toString());
BaseRobotRules rules = protocol.getRobotRules(fit.url, fit.datum);
if (!rules.isAllowed(fit.u.toString())) {
// unblock
((FetchItemQueues) fetchQueues).finishFetchItem(fit, true);
if (LOG.isDebugEnabled()) {
LOG.debug("Denied by robots.txt: " + fit.url);
}
output(
fit.url,
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 && maxCrawlDelay >= 0) {
// unblock
((FetchItemQueues) fetchQueues).finishFetchItem(fit, true);
LOG.debug(
"Crawl-Delay for "
+ fit.url
+ " too long ("
+ rules.getCrawlDelay()
+ "), skipping");
output(
fit.url,
fit.datum,
null,
ProtocolStatus.STATUS_ROBOTS_DENIED,
CrawlDatum.STATUS_FETCH_GONE);
reporter.incrCounter("FetcherStatus", "robots_denied_maxcrawldelay", 1);
continue;
} else {
FetchItemQueue fiq = ((FetchItemQueues) fetchQueues).getFetchItemQueue(fit.queueID);
fiq.crawlDelay = rules.getCrawlDelay();
if (LOG.isDebugEnabled()) {
LOG.debug(
"Crawl delay for queue: "
+ fit.queueID
+ " is set to "
+ fiq.crawlDelay
+ " as per robots.txt. url: "
+ fit.url);
}
}
}
ProtocolOutput output = protocol.getProtocolOutput(fit.url, fit.datum);
ProtocolStatus status = output.getStatus();
Content content = output.getContent();
ParseStatus pstatus = null;
// unblock queue
((FetchItemQueues) fetchQueues).finishFetchItem(fit);
String urlString = fit.url.toString();
// used for FetchNode
if (fetchNode != null) {
fetchNode.setStatus(status.getCode());
fetchNode.setFetchTime(System.currentTimeMillis());
fetchNode.setUrl(fit.url);
}
reporter.incrCounter("FetcherStatus", status.getName(), 1);
switch (status.getCode()) {
case ProtocolStatus.WOULDBLOCK:
// retry ?
((FetchItemQueues) fetchQueues).addFetchItem(fit);
break;
case ProtocolStatus.SUCCESS: // got a page
pstatus =
output(
fit.url,
fit.datum,
content,
status,
CrawlDatum.STATUS_FETCH_SUCCESS,
fit.outlinkDepth);
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(
fit.url,
fit.datum,
urlString,
newUrl,
refreshTime < Fetcher.PERM_REFRESH_TIME,
Fetcher.CONTENT_REDIR);
if (redirUrl != null) {
fit = queueRedirect(redirUrl, fit);
}
}
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(fit.url, fit.datum, content, status, code);
String newUrl = status.getMessage();
Text redirUrl =
handleRedirect(
fit.url, fit.datum, urlString, newUrl, temp, Fetcher.PROTOCOL_REDIR);
if (redirUrl != null) {
fit = queueRedirect(redirUrl, fit);
} else {
// stop redirecting
redirecting = false;
}
break;
case ProtocolStatus.EXCEPTION:
logError(fit.url, status.getMessage());
int killedURLs =
((FetchItemQueues) fetchQueues).checkExceptionThreshold(fit.getQueueID());
if (killedURLs != 0)
reporter.incrCounter(
"FetcherStatus", "AboveExceptionThresholdInQueue", killedURLs);
/* FALLTHROUGH */
case ProtocolStatus.RETRY: // retry
case ProtocolStatus.BLOCKED:
output(fit.url, 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(fit.url, fit.datum, null, status, CrawlDatum.STATUS_FETCH_GONE);
break;
case ProtocolStatus.NOTMODIFIED:
output(fit.url, fit.datum, null, status, CrawlDatum.STATUS_FETCH_NOTMODIFIED);
break;
default:
if (LOG.isWarnEnabled()) {
LOG.warn("Unknown ProtocolStatus: " + status.getCode());
}
output(fit.url, fit.datum, null, status, CrawlDatum.STATUS_FETCH_RETRY);
}
if (redirecting && redirectCount > maxRedirect) {
((FetchItemQueues) fetchQueues).finishFetchItem(fit);
if (LOG.isInfoEnabled()) {
LOG.info(" - redirect count exceeded " + fit.url);
}
output(
fit.url,
fit.datum,
null,
ProtocolStatus.STATUS_REDIR_EXCEEDED,
CrawlDatum.STATUS_FETCH_GONE);
}
} while (redirecting && (redirectCount <= maxRedirect));
} catch (Throwable t) { // unexpected exception
// unblock
((FetchItemQueues) fetchQueues).finishFetchItem(fit);
logError(fit.url, StringUtils.stringifyException(t));
output(
fit.url,
fit.datum,
null,
ProtocolStatus.STATUS_FAILED,
CrawlDatum.STATUS_FETCH_RETRY);
}
}
} catch (Throwable e) {
if (LOG.isErrorEnabled()) {
LOG.error("fetcher caught:" + e.toString());
}
} finally {
if (fit != null) ((FetchItemQueues) fetchQueues).finishFetchItem(fit);
activeThreads.decrementAndGet(); // count threads
LOG.info("-finishing thread " + getName() + ", activeThreads=" + activeThreads);
}
}
public ParseResult getParse(Content content) {
String mimeType = content.getContentType();
URL base;
try {
base = new URL(content.getBaseUrl());
} catch (MalformedURLException e) {
return new ParseStatus(e).getEmptyParseResult(content.getUrl(), getConf());
}
// get the right parser using the mime type as a clue
Parser parser = tikaConfig.getParser(MediaType.parse(mimeType));
byte[] raw = content.getContent();
if (parser == null) {
String message = "Can't retrieve Tika parser for mime-type " + mimeType;
LOG.error(message);
return new ParseStatus(ParseStatus.FAILED, message)
.getEmptyParseResult(content.getUrl(), getConf());
}
LOG.debug("Using Tika parser " + parser.getClass().getName() + " for mime-type " + mimeType);
Metadata tikamd = new Metadata();
HTMLDocumentImpl doc = new HTMLDocumentImpl();
doc.setErrorChecking(false);
DocumentFragment root = doc.createDocumentFragment();
DOMBuilder domhandler = new DOMBuilder(doc, root);
ParseContext context = new ParseContext();
try {
parser.parse(new ByteArrayInputStream(raw), domhandler, tikamd, context);
} catch (Exception e) {
LOG.error("Error parsing " + content.getUrl(), e);
return new ParseStatus(ParseStatus.FAILED, e.getMessage())
.getEmptyParseResult(content.getUrl(), getConf());
}
HTMLMetaTags metaTags = new HTMLMetaTags();
String text = "";
String title = "";
Outlink[] outlinks = new Outlink[0];
org.apache.nutch.metadata.Metadata nutchMetadata = new org.apache.nutch.metadata.Metadata();
// we have converted the sax events generated by Tika into a DOM object
// so we can now use the usual HTML resources from Nutch
// get meta directives
HTMLMetaProcessor.getMetaTags(metaTags, root, base);
if (LOG.isTraceEnabled()) {
LOG.trace("Meta tags for " + base + ": " + metaTags.toString());
}
// check meta directives
if (!metaTags.getNoIndex()) { // okay to index
StringBuffer sb = new StringBuffer();
if (LOG.isTraceEnabled()) {
LOG.trace("Getting text...");
}
utils.getText(sb, root); // extract text
text = sb.toString();
sb.setLength(0);
if (LOG.isTraceEnabled()) {
LOG.trace("Getting title...");
}
utils.getTitle(sb, root); // extract title
title = sb.toString().trim();
}
if (!metaTags.getNoFollow()) { // okay to follow links
ArrayList<Outlink> l = new ArrayList<Outlink>(); // extract outlinks
URL baseTag = utils.getBase(root);
if (LOG.isTraceEnabled()) {
LOG.trace("Getting links...");
}
utils.getOutlinks(baseTag != null ? baseTag : base, l, root);
outlinks = l.toArray(new Outlink[l.size()]);
if (LOG.isTraceEnabled()) {
LOG.trace("found " + outlinks.length + " outlinks in " + content.getUrl());
}
}
// populate Nutch metadata with Tika metadata
String[] TikaMDNames = tikamd.names();
for (String tikaMDName : TikaMDNames) {
if (tikaMDName.equalsIgnoreCase(Metadata.TITLE)) continue;
// TODO what if multivalued?
nutchMetadata.add(tikaMDName, tikamd.get(tikaMDName));
}
// no outlinks? try OutlinkExtractor e.g works for mime types where no
// explicit markup for anchors
if (outlinks.length == 0) {
outlinks = OutlinkExtractor.getOutlinks(text, getConf());
}
ParseStatus status = new ParseStatus(ParseStatus.SUCCESS);
if (metaTags.getRefresh()) {
status.setMinorCode(ParseStatus.SUCCESS_REDIRECT);
status.setArgs(
new String[] {
metaTags.getRefreshHref().toString(), Integer.toString(metaTags.getRefreshTime())
});
}
ParseData parseData =
new ParseData(status, title, outlinks, content.getMetadata(), nutchMetadata);
ParseResult parseResult =
ParseResult.createParseResult(content.getUrl(), new ParseImpl(text, parseData));
// run filters on parse
ParseResult filteredParse = this.htmlParseFilters.filter(content, parseResult, metaTags, root);
if (metaTags.getNoCache()) { // not okay to cache
for (Map.Entry<org.apache.hadoop.io.Text, Parse> entry : filteredParse)
entry.getValue().getData().getParseMeta().set(Nutch.CACHING_FORBIDDEN_KEY, cachingPolicy);
}
return filteredParse;
}
/** For debugging. */
public static void main(String[] args) throws Exception {
int timeout = Integer.MIN_VALUE;
int maxContentLength = Integer.MIN_VALUE;
String logLevel = "info";
boolean followTalk = false;
boolean keepConnection = false;
boolean dumpContent = false;
String urlString = null;
String usage =
"Usage: Ftp [-logLevel level] [-followTalk] [-keepConnection] [-timeout N] [-maxContentLength L] [-dumpContent] url";
if (args.length == 0) {
System.err.println(usage);
System.exit(-1);
}
for (int i = 0; i < args.length; i++) {
if (args[i].equals("-logLevel")) {
logLevel = args[++i];
} else if (args[i].equals("-followTalk")) {
followTalk = true;
} else if (args[i].equals("-keepConnection")) {
keepConnection = true;
} else if (args[i].equals("-timeout")) {
timeout = Integer.parseInt(args[++i]) * 1000;
} else if (args[i].equals("-maxContentLength")) {
maxContentLength = Integer.parseInt(args[++i]);
} else if (args[i].equals("-dumpContent")) {
dumpContent = true;
} else if (i != args.length - 1) {
System.err.println(usage);
System.exit(-1);
} else {
urlString = args[i];
}
}
Ftp ftp = new Ftp();
ftp.setFollowTalk(followTalk);
ftp.setKeepConnection(keepConnection);
if (timeout != Integer.MIN_VALUE) // set timeout
ftp.setTimeout(timeout);
if (maxContentLength != Integer.MIN_VALUE) // set maxContentLength
ftp.setMaxContentLength(maxContentLength);
// set log level
// LOG.setLevel(Level.parse((new String(logLevel)).toUpperCase()));
Content content = ftp.getProtocolOutput(new Text(urlString), new CrawlDatum()).getContent();
System.err.println("Content-Type: " + content.getContentType());
System.err.println("Content-Length: " + content.getMetadata().get(Response.CONTENT_LENGTH));
System.err.println("Last-Modified: " + content.getMetadata().get(Response.LAST_MODIFIED));
if (dumpContent) {
System.out.print(new String(content.getContent()));
}
ftp = null;
}
public int run(String[] args) throws Exception {
boolean dumpText = false;
boolean force = false;
String contentType = null;
String url = null;
String usage = "Usage: ParserChecker [-dumpText] [-forceAs mimeType] url";
if (args.length == 0) {
LOG.error(usage);
return (-1);
}
for (int i = 0; i < args.length; i++) {
if (args[i].equals("-forceAs")) {
force = true;
contentType = args[++i];
} else if (args[i].equals("-dumpText")) {
dumpText = true;
} else if (i != args.length - 1) {
LOG.error(usage);
System.exit(-1);
} else {
url = URLUtil.toASCII(args[i]);
}
}
if (LOG.isInfoEnabled()) {
LOG.info("fetching: " + url);
}
ProtocolFactory factory = new ProtocolFactory(conf);
Protocol protocol = factory.getProtocol(url);
WebPage page = WebPage.newBuilder().build();
ProtocolOutput protocolOutput = protocol.getProtocolOutput(url, page);
if (!protocolOutput.getStatus().isSuccess()) {
LOG.error(
"Fetch failed with protocol status: "
+ ProtocolStatusUtils.getName(protocolOutput.getStatus().getCode())
+ ": "
+ ProtocolStatusUtils.getMessage(protocolOutput.getStatus()));
return (-1);
}
Content content = protocolOutput.getContent();
if (content == null) {
LOG.error("No content for " + url);
return (-1);
}
page.setBaseUrl(new org.apache.avro.util.Utf8(url));
page.setContent(ByteBuffer.wrap(content.getContent()));
if (force) {
content.setContentType(contentType);
} else {
contentType = content.getContentType();
}
if (contentType == null) {
LOG.error("Failed to determine content type!");
return (-1);
}
page.setContentType(new Utf8(contentType));
if (ParserJob.isTruncated(url, page)) {
LOG.warn("Content is truncated, parse may fail!");
}
Parse parse = new ParseUtil(conf).parse(url, page);
if (parse == null) {
LOG.error("Problem with parse - check log");
return (-1);
}
// Calculate the signature
byte[] signature = SignatureFactory.getSignature(getConf()).calculate(page);
if (LOG.isInfoEnabled()) {
LOG.info("parsing: " + url);
LOG.info("contentType: " + contentType);
LOG.info("signature: " + StringUtil.toHexString(signature));
}
LOG.info("---------\nUrl\n---------------\n");
System.out.print(url + "\n");
LOG.info("---------\nMetadata\n---------\n");
Map<CharSequence, ByteBuffer> metadata = page.getMetadata();
StringBuffer sb = new StringBuffer();
if (metadata != null) {
Iterator<Entry<CharSequence, ByteBuffer>> iterator = metadata.entrySet().iterator();
while (iterator.hasNext()) {
Entry<CharSequence, ByteBuffer> entry = iterator.next();
sb.append(entry.getKey().toString())
.append(" : \t")
.append(Bytes.toString(entry.getValue()))
.append("\n");
}
System.out.print(sb.toString());
}
LOG.info("---------\nOutlinks\n---------\n");
sb = new StringBuffer();
for (Outlink l : parse.getOutlinks()) {
sb.append(" outlink: ").append(l).append('\n');
}
System.out.print(sb.toString());
if (page.getHeaders() != null) {
LOG.info("---------\nHeaders\n---------\n");
Map<CharSequence, CharSequence> headers = page.getHeaders();
StringBuffer headersb = new StringBuffer();
if (metadata != null) {
Iterator<Entry<CharSequence, CharSequence>> iterator = headers.entrySet().iterator();
while (iterator.hasNext()) {
Entry<CharSequence, CharSequence> entry = iterator.next();
headersb
.append(entry.getKey().toString())
.append(" : \t")
.append(entry.getValue())
.append("\n");
}
System.out.print(headersb.toString());
}
}
if (dumpText) {
LOG.info("---------\nParseText\n---------\n");
System.out.print(parse.getText());
}
return 0;
}