Examples with RobotsTxt org.codelibs.fess.crawler.entity.RobotsTxt used on opensource projects

Example 1 with RobotsTxt

use of org.codelibs.fess.crawler.entity.RobotsTxt in project fess-crawler by codelibs.

the class HcHttpClient method processRobotsTxt.

protected void processRobotsTxt(final String url) {
    if (StringUtil.isBlank(url)) {
        throw new CrawlerSystemException("url is null or empty.");
    }
    if (robotsTxtHelper == null || !robotsTxtHelper.isEnabled()) {
        // not support robots.txt
        return;
    }
    // crawler context
    final CrawlerContext crawlerContext = CrawlingParameterUtil.getCrawlerContext();
    if (crawlerContext == null) {
        // wrong state
        return;
    }
    final int idx = url.indexOf('/', url.indexOf("://") + 3);
    String hostUrl;
    if (idx >= 0) {
        hostUrl = url.substring(0, idx);
    } else {
        hostUrl = url;
    }
    final String robotTxtUrl = hostUrl + "/robots.txt";
    // check url
    if (crawlerContext.getRobotsTxtUrlSet().contains(robotTxtUrl)) {
        if (logger.isDebugEnabled()) {
            logger.debug(robotTxtUrl + " is already visited.");
        }
        return;
    }
    if (logger.isInfoEnabled()) {
        logger.info("Checking URL: " + robotTxtUrl);
    }
    // add url to a set
    crawlerContext.getRobotsTxtUrlSet().add(robotTxtUrl);
    final HttpGet httpGet = new HttpGet(robotTxtUrl);
    // request header
    for (final Header header : requestHeaderList) {
        httpGet.addHeader(header);
    }
    HttpEntity httpEntity = null;
    try {
        // get a content
        final HttpResponse response = executeHttpClient(httpGet);
        httpEntity = response.getEntity();
        final int httpStatusCode = response.getStatusLine().getStatusCode();
        if (httpStatusCode == 200) {
            // check file size
            final Header contentLengthHeader = response.getFirstHeader("Content-Length");
            if (contentLengthHeader != null) {
                final String value = contentLengthHeader.getValue();
                final long contentLength = Long.parseLong(value);
                if (contentLengthHelper != null) {
                    final long maxLength = contentLengthHelper.getMaxLength("text/plain");
                    if (contentLength > maxLength) {
                        throw new MaxLengthExceededException("The content length (" + contentLength + " byte) is over " + maxLength + " byte. The url is " + robotTxtUrl);
                    }
                }
            }
            if (httpEntity != null) {
                final RobotsTxt robotsTxt = robotsTxtHelper.parse(httpEntity.getContent());
                if (robotsTxt != null) {
                    final String[] sitemaps = robotsTxt.getSitemaps();
                    if (sitemaps.length > 0) {
                        crawlerContext.addSitemaps(sitemaps);
                    }
                    final RobotsTxt.Directive directive = robotsTxt.getMatchedDirective(userAgent);
                    if (directive != null) {
                        if (useRobotsTxtDisallows) {
                            for (String urlPattern : directive.getDisallows()) {
                                if (StringUtil.isNotBlank(urlPattern)) {
                                    urlPattern = convertRobotsTxtPathPattern(urlPattern);
                                    crawlerContext.getUrlFilter().addExclude(hostUrl + urlPattern);
                                }
                            }
                        }
                        if (useRobotsTxtAllows) {
                            for (String urlPattern : directive.getAllows()) {
                                if (StringUtil.isNotBlank(urlPattern)) {
                                    urlPattern = convertRobotsTxtPathPattern(urlPattern);
                                    crawlerContext.getUrlFilter().addInclude(hostUrl + urlPattern);
                                }
                            }
                        }
                    }
                }
            }
        }
    } catch (final CrawlerSystemException e) {
        httpGet.abort();
        throw e;
    } catch (final Exception e) {
        httpGet.abort();
        throw new CrawlingAccessException("Could not process " + robotTxtUrl + ". ", e);
    } finally {
        EntityUtils.consumeQuietly(httpEntity);
    }
}

Example 2 with RobotsTxt

use of org.codelibs.fess.crawler.entity.RobotsTxt in project fess-crawler by codelibs.

the class RobotsTxtHelper method parse.

public RobotsTxt parse(final InputStream stream, final String charsetName) {
    if (!enabled) {
        return null;
    }
    try {
        @SuppressWarnings("resource") final BufferedReader reader = new BufferedReader(new InputStreamReader(new BOMInputStream(stream), charsetName));
        String line;
        final RobotsTxt robotsTxt = new RobotsTxt();
        final List<Directive> currentDirectiveList = new ArrayList<>();
        boolean isGroupRecodeStarted = false;
        while ((line = reader.readLine()) != null) {
            line = stripComment(line).trim();
            if (StringUtil.isEmpty(line)) {
                continue;
            }
            String value;
            if ((value = getValue(USER_AGENT_RECORD, line)) != null) {
                if (isGroupRecodeStarted) {
                    currentDirectiveList.clear();
                    isGroupRecodeStarted = false;
                }
                final String userAgent = value.toLowerCase(Locale.ENGLISH);
                Directive currentDirective = robotsTxt.getDirective(userAgent);
                if (currentDirective == null) {
                    currentDirective = new Directive(userAgent);
                    robotsTxt.addDirective(currentDirective);
                    currentDirectiveList.add(currentDirective);
                }
            } else {
                isGroupRecodeStarted = true;
                if ((value = getValue(DISALLOW_RECORD, line)) != null) {
                    if (!currentDirectiveList.isEmpty() && value.length() > 0) {
                        for (final Directive directive : currentDirectiveList) {
                            directive.addDisallow(value);
                        }
                    }
                } else if ((value = getValue(ALLOW_RECORD, line)) != null) {
                    if (!currentDirectiveList.isEmpty() && value.length() > 0) {
                        for (final Directive directive : currentDirectiveList) {
                            directive.addAllow(value);
                        }
                    }
                } else if ((value = getValue(CRAWL_DELAY_RECORD, line)) != null) {
                    if (!currentDirectiveList.isEmpty()) {
                        try {
                            final int crawlDelay = Integer.parseInt(value);
                            for (final Directive directive : currentDirectiveList) {
                                directive.setCrawlDelay(Math.max(0, crawlDelay));
                            }
                        } catch (final NumberFormatException e) {
                        // ignore
                        }
                    }
                } else if ((value = getValue(SITEMAP_RECORD, line)) != null) {
                    if (value.length() > 0) {
                        robotsTxt.addSitemap(value);
                    }
                }
            }
        }
        return robotsTxt;
    } catch (final Exception e) {
        throw new RobotsTxtException("Failed to parse robots.txt.", e);
    }
}

Example 3 with RobotsTxt

use of org.codelibs.fess.crawler.entity.RobotsTxt in project fess-crawler by codelibs.

the class RobotsTxtHelperTest method testParse.

public void testParse() {
    RobotsTxt robotsTxt;
    final InputStream in = RobotsTxtHelperTest.class.getResourceAsStream("robots.txt");
    try {
        robotsTxt = robotsTxtHelper.parse(in);
    } finally {
        CloseableUtil.closeQuietly(in);
    }
    for (String userAgent : new String[] { "FessCrawler", "FessCrawler/1.0", "Mozilla FessCrawler" }) {
        assertTrue(robotsTxt.allows("/aaa", userAgent));
        assertTrue(robotsTxt.allows("/private/", userAgent));
        assertTrue(robotsTxt.allows("/private/index.html", userAgent));
        assertTrue(robotsTxt.allows("/help/", userAgent));
        assertTrue(robotsTxt.allows("/help.html", userAgent));
        assertTrue(robotsTxt.allows("/help/faq.html", userAgent));
        assertTrue(robotsTxt.allows("/foo/bar/", userAgent));
        assertTrue(robotsTxt.allows("/foo/bar/index.html", userAgent));
        assertEquals(0, robotsTxt.getCrawlDelay(userAgent));
    }
    for (String userAgent : new String[] { "BruteBot", "FOO BruteBot/1.0" }) {
        assertFalse(robotsTxt.allows("/aaa", userAgent));
        assertFalse(robotsTxt.allows("/private/", userAgent));
        assertFalse(robotsTxt.allows("/private/index.html", userAgent));
        assertFalse(robotsTxt.allows("/help/", userAgent));
        assertFalse(robotsTxt.allows("/help.html", userAgent));
        assertFalse(robotsTxt.allows("/help/faq.html", userAgent));
        assertTrue(robotsTxt.allows("/foo/bar/", userAgent));
        assertTrue(robotsTxt.allows("/foo/bar/index.html", userAgent));
        assertEquals(1314000, robotsTxt.getCrawlDelay(userAgent));
    }
    for (String userAgent : new String[] { "GOOGLEBOT", "GoogleBot", "googlebot" }) {
        assertTrue(robotsTxt.allows("/aaa", userAgent));
        assertTrue(robotsTxt.allows("/private/", userAgent));
        assertTrue(robotsTxt.allows("/private/index.html", userAgent));
        assertTrue(robotsTxt.allows("/help/", userAgent));
        assertTrue(robotsTxt.allows("/help.html", userAgent));
        assertTrue(robotsTxt.allows("/help/faq.html", userAgent));
        assertTrue(robotsTxt.allows("/foo/bar/", userAgent));
        assertTrue(robotsTxt.allows("/foo/bar/index.html", userAgent));
        assertEquals(1, robotsTxt.getCrawlDelay(userAgent));
    }
    for (String userAgent : new String[] { "UnknownBot", "", " ", null }) {
        assertTrue(robotsTxt.allows("/aaa", userAgent));
        assertFalse(robotsTxt.allows("/private/", userAgent));
        assertFalse(robotsTxt.allows("/private/index.html", userAgent));
        assertFalse(robotsTxt.allows("/help/", userAgent));
        assertFalse(robotsTxt.allows("/help.html", userAgent));
        assertTrue(robotsTxt.allows("/help/faq.html", userAgent));
        assertTrue(robotsTxt.allows("/foo/bar/", userAgent));
        assertTrue(robotsTxt.allows("/foo/bar/index.html", userAgent));
        assertEquals(3, robotsTxt.getCrawlDelay(userAgent));
    }
    assertFalse(robotsTxt.allows("/aaa", "Crawler"));
    assertTrue(robotsTxt.allows("/bbb", "Crawler"));
    assertTrue(robotsTxt.allows("/ccc", "Crawler"));
    assertTrue(robotsTxt.allows("/ddd", "Crawler"));
    assertTrue(robotsTxt.allows("/aaa", "Crawler/1.0"));
    assertFalse(robotsTxt.allows("/bbb", "Crawler/1.0"));
    assertTrue(robotsTxt.allows("/ccc", "Crawler/1.0"));
    assertTrue(robotsTxt.allows("/ddd", "Crawler/1.0"));
    assertTrue(robotsTxt.allows("/aaa", "Crawler/2.0"));
    assertTrue(robotsTxt.allows("/bbb", "Crawler/2.0"));
    assertFalse(robotsTxt.allows("/ccc", "Crawler/2.0"));
    assertTrue(robotsTxt.allows("/ddd", "Crawler/2.0"));
    assertTrue(robotsTxt.allows("/aaa", "Hoge Crawler"));
    assertTrue(robotsTxt.allows("/bbb", "Hoge Crawler"));
    assertTrue(robotsTxt.allows("/ccc", "Hoge Crawler"));
    assertFalse(robotsTxt.allows("/ddd", "Hoge Crawler"));
    String[] sitemaps = robotsTxt.getSitemaps();
    assertEquals(2, sitemaps.length);
    assertEquals("http://www.example.com/sitmap.xml", sitemaps[0]);
    assertEquals("http://www.example.net/sitmap.xml", sitemaps[1]);
}