Examples with Outlink org.apache.nutch.parse.Outlink used on opensource projects

Example 11 with Outlink

use of org.apache.nutch.parse.Outlink in project nutch by apache.

the class HtmlParser method getParse.

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...");
        }
        // extract text
        utils.getText(sb, root);
        text = sb.toString();
        sb.setLength(0);
        if (LOG.isTraceEnabled()) {
            LOG.trace("Getting title...");
        }
        // extract title
        utils.getTitle(sb, root);
        title = sb.toString().trim();
    }
    if (!metaTags.getNoFollow()) {
        // okay to follow links
        // extract outlinks
        ArrayList<Outlink> l = new ArrayList<Outlink>();
        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;
}

Example 12 with Outlink

use of org.apache.nutch.parse.Outlink in project nutch by apache.

the class TestDOMContentUtils method setup.

@Before
public void setup() {
    conf = NutchConfiguration.create();
    conf.setBoolean("parser.html.form.use_action", true);
    utils = new DOMContentUtils(conf);
    DOMFragmentParser parser = new DOMFragmentParser();
    try {
        parser.setFeature("http://cyberneko.org/html/features/scanner/allow-selfclosing-iframe", true);
    } catch (SAXException e) {
    }
    for (int i = 0; i < testPages.length; i++) {
        DocumentFragment node = new HTMLDocumentImpl().createDocumentFragment();
        try {
            parser.parse(new InputSource(new ByteArrayInputStream(testPages[i].getBytes())), node);
            testBaseHrefURLs[i] = new URL(testBaseHrefs[i]);
        } catch (Exception e) {
            Assert.assertTrue("caught exception: " + e, false);
        }
        testDOMs[i] = node;
    }
    try {
        answerOutlinks = new Outlink[][] { { new Outlink("http://www.nutch.org", "anchor") }, { new Outlink("http://www.nutch.org/", "home"), new Outlink("http://www.nutch.org/docs/bot.html", "bots") }, { new Outlink("http://www.nutch.org/", "separate this"), new Outlink("http://www.nutch.org/docs/ok", "from this") }, { new Outlink("http://www.nutch.org/", "home"), new Outlink("http://www.nutch.org/docs/1", "1"), new Outlink("http://www.nutch.org/docs/2", "2") }, { new Outlink("http://www.nutch.org/frames/top.html", ""), new Outlink("http://www.nutch.org/frames/left.html", ""), new Outlink("http://www.nutch.org/frames/invalid.html", ""), new Outlink("http://www.nutch.org/frames/right.html", "") }, { new Outlink("http://www.nutch.org/maps/logo.gif", ""), new Outlink("http://www.nutch.org/index.html", ""), new Outlink("http://www.nutch.org/maps/#bottom", ""), new Outlink("http://www.nutch.org/bot.html", ""), new Outlink("http://www.nutch.org/docs/index.html", "") }, { new Outlink("http://www.nutch.org/index.html", "whitespace test") }, {}, { new Outlink("http://www.nutch.org/dummy.jsp", "test2") }, {}, { new Outlink("http://www.nutch.org/;x", "anchor1"), new Outlink("http://www.nutch.org/g;x", "anchor2"), new Outlink("http://www.nutch.org/g;x?y#s", "anchor3") }, { // this is tricky - see RFC3986 section 5.4.1 example 7
        new Outlink("http://www.nutch.org/g", "anchor1"), new Outlink("http://www.nutch.org/g?y#s", "anchor2"), new Outlink("http://www.nutch.org/;something?y=1", "anchor3"), new Outlink("http://www.nutch.org/;something?y=1#s", "anchor4"), new Outlink("http://www.nutch.org/;something?y=1;somethingelse", "anchor5") }, { new Outlink("http://www.nutch.org/g", ""), new Outlink("http://www.nutch.org/g1", ""), new Outlink("http://www.nutch.org/g2", "bla bla"), new Outlink("http://www.nutch.org/test.gif", "bla bla") }, { new Outlink("http://www.nutch.org/movie.mp4", "") } };
    } catch (MalformedURLException e) {
    }
}

Example 13 with Outlink

use of org.apache.nutch.parse.Outlink in project nutch by apache.

the class TestHtmlParser method testResolveBaseUrl.

@Test
public void testResolveBaseUrl() {
    byte[] contentBytes = resolveBaseUrlTestContent.getBytes(StandardCharsets.UTF_8);
    // parse using http://example.com/ as "fetch" URL
    Parse parse = parse(contentBytes);
    LOG.info(parse.getData().toString());
    Outlink[] outlinks = parse.getData().getOutlinks();
    Assert.assertEquals(1, outlinks.length);
    Assert.assertEquals("http://www.example.com/index.html", outlinks[0].getToUrl());
}

Example 14 with Outlink

use of org.apache.nutch.parse.Outlink in project nutch by apache.

the class JSParseFilter method getParse.

public ParseResult getParse(Content c) {
    String type = c.getContentType();
    if (type != null && !type.trim().equals("") && !type.toLowerCase().startsWith("application/x-javascript"))
        return new ParseStatus(ParseStatus.FAILED_INVALID_FORMAT, "Content not JavaScript: '" + type + "'").getEmptyParseResult(c.getUrl(), getConf());
    String script = new String(c.getContent());
    Outlink[] outlinks = getJSLinks(script, "", c.getUrl());
    if (outlinks == null)
        outlinks = new Outlink[0];
    // Title? use the first line of the script...
    String title;
    int idx = script.indexOf('\n');
    if (idx != -1) {
        if (idx > MAX_TITLE_LEN)
            idx = MAX_TITLE_LEN;
        title = script.substring(0, idx);
    } else {
        idx = Math.min(MAX_TITLE_LEN, script.length());
        title = script.substring(0, idx);
    }
    ParseData pd = new ParseData(ParseStatus.STATUS_SUCCESS, title, outlinks, c.getMetadata());
    return ParseResult.createParseResult(c.getUrl(), new ParseImpl(script, pd));
}

Example 15 with Outlink

use of org.apache.nutch.parse.Outlink in project nutch by apache.

the class JSParseFilter method filter.

public ParseResult filter(Content content, ParseResult parseResult, HTMLMetaTags metaTags, DocumentFragment doc) {
    Parse parse = parseResult.get(content.getUrl());
    String url = content.getBaseUrl();
    ArrayList<Outlink> outlinks = new ArrayList<Outlink>();
    walk(doc, parse, metaTags, url, outlinks);
    if (outlinks.size() > 0) {
        Outlink[] old = parse.getData().getOutlinks();
        String title = parse.getData().getTitle();
        List<Outlink> list = Arrays.asList(old);
        outlinks.addAll(list);
        ParseStatus status = parse.getData().getStatus();
        String text = parse.getText();
        Outlink[] newlinks = (Outlink[]) outlinks.toArray(new Outlink[outlinks.size()]);
        ParseData parseData = new ParseData(status, title, newlinks, parse.getData().getContentMeta(), parse.getData().getParseMeta());
        // replace original parse obj with new one
        parseResult.put(content.getUrl(), new ParseText(text), parseData);
    }
    return parseResult;
}