in src/plugin/parse-html/src/java/org/apache/nutch/parse/html/HtmlParser.java [147:265]
public ParseResult getParse(Content content) {
HTMLMetaTags metaTags = new HTMLMetaTags();
URL base;
try {
base = new URL(content.getBaseUrl());
} catch (MalformedURLException e) {
return new ParseStatus(e)
.getEmptyParseResult(content.getUrl(), getConf());
}
String text = "";
String title = "";
Outlink[] outlinks = new Outlink[0];
Metadata metadata = new Metadata();
// parse the content
DocumentFragment root;
try {
byte[] contentInOctets = content.getContent();
InputSource input = new InputSource(new ByteArrayInputStream(
contentInOctets));
EncodingDetector detector = new EncodingDetector(conf);
detector.autoDetectClues(content, true);
detector.addClue(sniffCharacterEncoding(contentInOctets), "sniffed");
String encoding = detector.guessEncoding(content, defaultCharEncoding);
metadata.set(Metadata.ORIGINAL_CHAR_ENCODING, encoding);
metadata.set(Metadata.CHAR_ENCODING_FOR_CONVERSION, encoding);
input.setEncoding(encoding);
if (LOG.isTraceEnabled()) {
LOG.trace("Parsing...");
}
root = parse(input);
} catch (IOException e) {
return new ParseStatus(e)
.getEmptyParseResult(content.getUrl(), getConf());
} catch (DOMException e) {
return new ParseStatus(e)
.getEmptyParseResult(content.getUrl(), getConf());
} catch (SAXException e) {
return new ParseStatus(e)
.getEmptyParseResult(content.getUrl(), getConf());
} catch (Exception e) {
LOG.error("Error: ", e);
return new ParseStatus(e)
.getEmptyParseResult(content.getUrl(), getConf());
}
// get meta directives
HTMLMetaProcessor.getMetaTags(metaTags, root, base);
// populate Nutch metadata with HTML meta directives
metadata.addAll(metaTags.getGeneralTags());
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 = base;
String baseTagHref = utils.getBase(root);
if (baseTagHref != null) {
try {
baseTag = new URL(base, baseTagHref);
} catch (MalformedURLException e) {
baseTag = base;
}
}
if (LOG.isTraceEnabled()) {
LOG.trace("Getting links...");
}
utils.getOutlinks(baseTag, l, root);
outlinks = l.toArray(new Outlink[l.size()]);
if (LOG.isTraceEnabled()) {
LOG.trace("found " + outlinks.length + " outlinks in "
+ content.getUrl());
}
}
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(), metadata);
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;
}