private FetchItem queueRedirect(Text redirUrl, FetchItem fit) throws ScoringFilterException {
CrawlDatum newDatum =
new CrawlDatum(
CrawlDatum.STATUS_DB_UNFETCHED, fit.datum.getFetchInterval(), fit.datum.getScore());
// transfer all existing metadata to the redirect
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, queueMode);
if (fit != null) {
FetchItemQueue fiq = ((FetchItemQueues) fetchQueues).getFetchItemQueue(fit.queueID);
fiq.addInProgressFetchItem(fit);
} else {
// stop redirecting
redirecting = false;
reporter.incrCounter("FetcherStatus", "FetchItem.notCreated.redirect", 1);
}
return fit;
}
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String url = value.toString().trim(); // value is line of text
if (url != null && (url.length() == 0 || url.startsWith("#"))) {
/* Ignore line that start with # */
return;
}
// if tabs : metadata that could be stored
// must be name=value and separated by \t
float customScore = -1f;
int customInterval = interval;
Map<String, String> metadata = new TreeMap<String, String>();
if (url.indexOf("\t") != -1) {
String[] splits = url.split("\t");
url = splits[0];
for (int s = 1; s < splits.length; s++) {
// find separation between name and value
int indexEquals = splits[s].indexOf("=");
if (indexEquals == -1) {
// skip anything without a =
continue;
}
String metaname = splits[s].substring(0, indexEquals);
String metavalue = splits[s].substring(indexEquals + 1);
if (metaname.equals(nutchScoreMDName)) {
try {
customScore = Float.parseFloat(metavalue);
} catch (NumberFormatException nfe) {
}
} else if (metaname.equals(nutchFetchIntervalMDName)) {
try {
customInterval = Integer.parseInt(metavalue);
} catch (NumberFormatException nfe) {
}
} else metadata.put(metaname, metavalue);
}
}
try {
url = urlNormalizers.normalize(url, URLNormalizers.SCOPE_INJECT);
url = filters.filter(url); // filter the url
} catch (Exception e) {
LOG.warn("Skipping " + url + ":" + e);
url = null;
}
if (url == null) {
context.getCounter("injector", "urls_filtered").increment(1);
return;
} else { // if it passes
String reversedUrl = TableUtil.reverseUrl(url); // collect it
WebPage row = new WebPage();
row.setFetchTime(curTime);
row.setFetchInterval(customInterval);
// now add the metadata
Iterator<String> keysIter = metadata.keySet().iterator();
while (keysIter.hasNext()) {
String keymd = keysIter.next();
String valuemd = metadata.get(keymd);
row.putToMetadata(new Utf8(keymd), ByteBuffer.wrap(valuemd.getBytes()));
}
if (customScore != -1) row.setScore(customScore);
else row.setScore(scoreInjected);
try {
scfilters.injectedScore(url, row);
} catch (ScoringFilterException e) {
if (LOG.isWarnEnabled()) {
LOG.warn(
"Cannot filter injected score for url "
+ url
+ ", using default ("
+ e.getMessage()
+ ")");
}
}
context.getCounter("injector", "urls_injected").increment(1);
row.putToMarkers(DbUpdaterJob.DISTANCE, new Utf8(String.valueOf(0)));
Mark.INJECT_MARK.putMark(row, YES_STRING);
context.write(reversedUrl, row);
}
}
private ParseStatus output(
Text key,
CrawlDatum datum,
Content content,
ProtocolStatus pstatus,
int status,
int outlinkDepth) {
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();
// store the guessed content type in the crawldatum
if (content.getContentType() != null)
datum
.getMetaData()
.put(new Text(Metadata.CONTENT_TYPE), new Text(content.getContentType()));
// 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()) {
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) {
if (!skipTruncated || (skipTruncated && !ParseSegment.isTruncated(content))) {
try {
parseResult = this.parseUtil.parse(content);
} catch (Exception e) {
LOG.warn("Error parsing: " + key + ": " + StringUtils.stringifyException(e));
}
}
if (parseResult == null) {
byte[] signature =
SignatureFactory.getSignature(conf)
.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();
ParseData parseData = parse.getData();
if (!parseStatus.isSuccess()) {
LOG.warn("Error parsing: " + key + ": " + parseStatus);
parse = parseStatus.getEmptyParse(conf);
}
// Calculate page signature. For non-parsing fetchers this will
// be done in ParseSegment
byte[] signature = SignatureFactory.getSignature(conf).calculate(content, parse);
// Ensure segment name and score are in parseData metadata
parseData.getContentMeta().set(Nutch.SEGMENT_NAME_KEY, segmentName);
parseData.getContentMeta().set(Nutch.SIGNATURE_KEY, StringUtil.toHexString(signature));
// Pass fetch time to content meta
parseData.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()) {
LOG.warn("Couldn't pass score, url " + key + " (" + e + ")");
}
}
String origin = null;
// collect outlinks for subsequent db update
Outlink[] links = parseData.getOutlinks();
int outlinksToStore = Math.min(maxOutlinks, links.length);
if (ignoreExternalLinks || ignoreInternalLinks) {
URL originURL = new URL(url.toString());
// based on domain?
if ("bydomain".equalsIgnoreCase(ignoreExternalLinksMode)) {
origin = URLUtil.getDomainName(originURL).toLowerCase();
}
// use host
else {
origin = originURL.getHost().toLowerCase();
}
}
// used by fetchNode
if (fetchNode != null) {
fetchNode.setOutlinks(links);
fetchNode.setTitle(parseData.getTitle());
FetchNodeDb.getInstance().put(fetchNode.getUrl().toString(), fetchNode);
}
int validCount = 0;
// Process all outlinks, normalize, filter and deduplicate
List<Outlink> outlinkList = new ArrayList<Outlink>(outlinksToStore);
HashSet<String> outlinks = new HashSet<String>(outlinksToStore);
for (int i = 0; i < links.length && validCount < outlinksToStore; i++) {
String toUrl = links[i].getToUrl();
toUrl =
ParseOutputFormat.filterNormalize(
url.toString(),
toUrl,
origin,
ignoreInternalLinks,
ignoreExternalLinks,
ignoreExternalLinksMode,
urlFilters,
urlExemptionFilters,
normalizers);
if (toUrl == null) {
continue;
}
validCount++;
links[i].setUrl(toUrl);
outlinkList.add(links[i]);
outlinks.add(toUrl);
}
// Only process depth N outlinks
if (maxOutlinkDepth > 0 && outlinkDepth < maxOutlinkDepth) {
reporter.incrCounter("FetcherOutlinks", "outlinks_detected", outlinks.size());
// Counter to limit num outlinks to follow per page
int outlinkCounter = 0;
// Calculate variable number of outlinks by depth using the
// divisor (outlinks = Math.floor(divisor / depth * num.links))
int maxOutlinksByDepth =
(int)
Math.floor(outlinksDepthDivisor / (outlinkDepth + 1) * maxOutlinkDepthNumLinks);
String followUrl;
// Walk over the outlinks and add as new FetchItem to the queues
Iterator<String> iter = outlinks.iterator();
while (iter.hasNext() && outlinkCounter < maxOutlinkDepthNumLinks) {
followUrl = iter.next();
// Check whether we'll follow external outlinks
if (outlinksIgnoreExternal) {
if (!URLUtil.getHost(url.toString()).equals(URLUtil.getHost(followUrl))) {
continue;
}
}
reporter.incrCounter("FetcherOutlinks", "outlinks_following", 1);
// Create new FetchItem with depth incremented
FetchItem fit =
FetchItem.create(
new Text(followUrl),
new CrawlDatum(CrawlDatum.STATUS_LINKED, interval),
queueMode,
outlinkDepth + 1);
((FetchItemQueues) fetchQueues).addFetchItem(fit);
outlinkCounter++;
}
}
// Overwrite the outlinks in ParseData with the normalized and
// filtered set
parseData.setOutlinks(outlinkList.toArray(new Outlink[outlinkList.size()]));
output.collect(
url,
new NutchWritable(
new ParseImpl(new ParseText(parse.getText()), parseData, parse.isCanonical())));
}
}
} catch (IOException e) {
if (LOG.isErrorEnabled()) {
LOG.error("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;
}
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);
try {
String origHost = new URL(urlString).getHost().toLowerCase();
String newHost = new URL(newUrl).getHost().toLowerCase();
if (ignoreExternalLinks) {
if (!origHost.equals(newHost)) {
if (LOG.isDebugEnabled()) {
LOG.debug(
" - ignoring redirect "
+ redirType
+ " from "
+ urlString
+ " to "
+ newUrl
+ " because external links are ignored");
}
return null;
}
}
if (ignoreInternalLinks) {
if (origHost.equals(newHost)) {
if (LOG.isDebugEnabled()) {
LOG.debug(
" - ignoring redirect "
+ redirType
+ " from "
+ urlString
+ " to "
+ newUrl
+ " because internal 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(), datum.getScore());
// 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;
}
}
public void map(
WritableComparable<?> key,
Text value,
OutputCollector<Text, CrawlDatum> output,
Reporter reporter)
throws IOException {
String url = value.toString(); // value is line of text
if (url != null && url.trim().startsWith("#")) {
/* Ignore line that start with # */
return;
}
// if tabs : metadata that could be stored
// must be name=value and separated by \t
float customScore = -1f;
int customInterval = interval;
int fixedInterval = -1;
Map<String, String> metadata = new TreeMap<String, String>();
if (url.indexOf("\t") != -1) {
String[] splits = url.split("\t");
url = splits[0];
for (int s = 1; s < splits.length; s++) {
// find separation between name and value
int indexEquals = splits[s].indexOf("=");
if (indexEquals == -1) {
// skip anything without a =
continue;
}
String metaname = splits[s].substring(0, indexEquals);
String metavalue = splits[s].substring(indexEquals + 1);
if (metaname.equals(nutchScoreMDName)) {
try {
customScore = Float.parseFloat(metavalue);
} catch (NumberFormatException nfe) {
}
} else if (metaname.equals(nutchFetchIntervalMDName)) {
try {
customInterval = Integer.parseInt(metavalue);
} catch (NumberFormatException nfe) {
}
} else if (metaname.equals(nutchFixedFetchIntervalMDName)) {
try {
fixedInterval = Integer.parseInt(metavalue);
} catch (NumberFormatException nfe) {
}
} else metadata.put(metaname, metavalue);
}
}
try {
url = urlNormalizers.normalize(url, URLNormalizers.SCOPE_INJECT);
url = filters.filter(url); // filter the url
} catch (Exception e) {
if (LOG.isWarnEnabled()) {
LOG.warn("Skipping " + url + ":" + e);
}
url = null;
}
if (url == null) {
reporter.getCounter("injector", "urls_filtered").increment(1);
} else { // if it passes
value.set(url); // collect it
CrawlDatum datum = new CrawlDatum();
datum.setStatus(CrawlDatum.STATUS_INJECTED);
// Is interval custom? Then set as meta data
if (fixedInterval > -1) {
// Set writable using float. Flaot is used by AdaptiveFetchSchedule
datum
.getMetaData()
.put(Nutch.WRITABLE_FIXED_INTERVAL_KEY, new FloatWritable(fixedInterval));
datum.setFetchInterval(fixedInterval);
} else {
datum.setFetchInterval(customInterval);
}
datum.setFetchTime(curTime);
// now add the metadata
Iterator<String> keysIter = metadata.keySet().iterator();
while (keysIter.hasNext()) {
String keymd = keysIter.next();
String valuemd = metadata.get(keymd);
datum.getMetaData().put(new Text(keymd), new Text(valuemd));
}
if (customScore != -1) datum.setScore(customScore);
else datum.setScore(scoreInjected);
try {
scfilters.injectedScore(value, datum);
} catch (ScoringFilterException e) {
if (LOG.isWarnEnabled()) {
LOG.warn(
"Cannot filter injected score for url "
+ url
+ ", using default ("
+ e.getMessage()
+ ")");
}
}
reporter.getCounter("injector", "urls_injected").increment(1);
output.collect(value, datum);
}
}
