public NutchDocument filter(
NutchDocument doc, Parse parse, Text url, CrawlDatum datum, Inlinks inlinks)
throws IndexingException {
Text reprUrl = (Text) datum.getMetaData().get(Nutch.WRITABLE_REPR_URL_KEY);
String reprUrlString = reprUrl != null ? reprUrl.toString() : null;
String urlString = url.toString();
String host = null;
try {
URL u;
if (reprUrlString != null) {
u = new URL(reprUrlString);
} else {
u = new URL(urlString);
}
host = u.getHost();
} catch (MalformedURLException e) {
throw new IndexingException(e);
}
if (host != null) {
doc.add("host", host);
}
doc.add("url", reprUrlString == null ? urlString : reprUrlString);
// content
String content = parse.getText();
if (MAX_CONTENT_LENGTH > -1 && content.length() > MAX_CONTENT_LENGTH) {
content = content.substring(0, MAX_CONTENT_LENGTH);
}
doc.add("content", content);
// title
String title = parse.getData().getTitle();
if (title.length() > MAX_TITLE_LENGTH) { // truncate title if needed
title = title.substring(0, MAX_TITLE_LENGTH);
}
if (title.length() > 0) {
// NUTCH-1004 Do not index empty values for title field
doc.add("title", title);
}
// add cached content/summary display policy, if available
String caching = parse.getData().getMeta(Nutch.CACHING_FORBIDDEN_KEY);
if (caching != null && !caching.equals(Nutch.CACHING_FORBIDDEN_NONE)) {
doc.add("cache", caching);
}
// add timestamp when fetched, for deduplication
doc.add("tstamp", new Date(datum.getFetchTime()));
return doc;
}
public void testIt() throws ProtocolException, ParseException {
String urlString;
Content content;
Parse parse;
Configuration conf = NutchConfiguration.create();
Protocol protocol;
ProtocolFactory factory = new ProtocolFactory(conf);
OOParser parser = new OOParser();
parser.setConf(conf);
for (int i = 0; i < sampleFiles.length; i++) {
urlString = "file:" + sampleDir + fileSeparator + sampleFiles[i];
protocol = factory.getProtocol(urlString);
content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum()).getContent();
parse = parser.getParse(content).get(content.getUrl());
String text = parse.getText().replaceAll("[ \t\r\n]+", " ");
assertTrue(expectedText.equals(text));
}
}
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;
}