href - Code Search

fess-crawler-opensearch/src/test/java/org/codelibs/fess/crawler/util/CrawlerWebServer.java

        buf.append(count);
        buf.append("</title></head><body><h1>Content ");
        buf.append(count);
        buf.append("</h1><br>");
        buf.append("<a href=\"index.html\">Index</a><br>");
        for (int i = 1; i <= 10; i++) {
            buf.append("<a href=\"file");
            buf.append(count);
            buf.append("-");
            buf.append(i);
            buf.append(".html\">File ");

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sat Mar 15 06:52:00 UTC 2025

- 5K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/resources/html/test1.html

<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
<title>タイトル</title>
</head>
<body>
<h1>第一章</h1>
<h2>第一節</h2>
<p>ほげほげ<br>ふがふが</p>
<p>
<a href="test2.html">LINK</a>
</p>
<h1>第2章</h1>
<h2>第2節</h2>
</body>

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Oct 11 02:16:55 UTC 2015

- 289 bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/transformer/impl/HtmlTransformerTest.java

        Map<String, String> childUrlRuleMap = newHashMap();
        childUrlRuleMap.put("//A", "href");
        childUrlRuleMap.put("//AREA", "href");
        childUrlRuleMap.put("//FRAME", "src");
        childUrlRuleMap.put("//IFRAME", "src");
        childUrlRuleMap.put("//IMG", "src");
        childUrlRuleMap.put("//LINK", "href");
        childUrlRuleMap.put("//SCRIPT", "src");
        htmlTransformer.setChildUrlRuleMap(childUrlRuleMap);

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sat Mar 15 06:52:00 UTC 2025

- 13.8K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/util/CrawlerWebServer.java

        buf.append(count);
        buf.append("</title></head><body><h1>Content ");
        buf.append(count);
        buf.append("</h1><br>");
        buf.append("<a href=\"index.html\">Index</a><br>");
        for (int i = 1; i <= 10; i++) {
            buf.append("<a href=\"file");
            buf.append(count);
            buf.append("-");
            buf.append(i);
            buf.append(".html\">File ");

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sat Mar 15 06:52:00 UTC 2025

- 6.3K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/HtmlTransformer.java

        }

        return parser;
    }

    /**
     * Gets the base href from the document's BASE tag.
     *
     * @param document the document to extract base href from
     * @return the base href URL, or null if not found
     */
    protected String getBaseHref(final Document document) {
        try {

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Jul 06 02:13:03 UTC 2025

- 28.5K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/CrawlerTest.java

        final Map<String, String> childUrlRuleMap = newHashMap();
        childUrlRuleMap.put("//A", "href");
        childUrlRuleMap.put("//AREA", "href");
        childUrlRuleMap.put("//FRAME", "src");
        childUrlRuleMap.put("//IFRAME", "src");
        childUrlRuleMap.put("//IMG", "src");
        childUrlRuleMap.put("//LINK", "href");
        childUrlRuleMap.put("//SCRIPT", "src");

        container = new StandardCrawlerContainer();

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sat Sep 06 04:15:37 UTC 2025

- 19.1K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/RobotsTxtHelper.java

import org.codelibs.fess.crawler.entity.RobotsTxt.Directive;
import org.codelibs.fess.crawler.exception.RobotsTxtException;

/**
 * Robots.txt Specifications:
 * <ul>
 * <li><a href=
 * "https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt"
 * >https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt
 * </a></li>
 * </ul>
 *
 * @author bowez

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Jul 06 02:13:03 UTC 2025

- 7.7K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/resources/ajax/js/jquery-2.1.1.min.js

ode)||b),e},c.sortStable=u.split("").sort(B).join("")===u,c.detectDuplicates=!!l,m(),c.sortDetached=ib(function(a){return 1&a.compareDocumentPosition(n.createElement("div"))}),ib(function(a){return a.innerHTML="<a href='#'></a>","#"===a.firstChild.getAttribute("href")})||jb("type|href|height|width",function(a,b,c){return c?void 0:a.getAttribute(b,"type"===b.toLowerCase()?1:2)}),c.attributes&&ib(function(a){return a.innerHTML="<input/>",a.firstChild.setAttribute("value",""),""===a.firstChild.getA...

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Oct 11 02:16:55 UTC 2015

- 82.3K bytes

- Viewed (0)

github.com/codelibs/fess-suggest

.github/workflows/maven.yml

        restore-keys: |
          ${{ runner.os }}-maven-
    - name: Checkout fess-parent
      uses: actions/checkout@v4
      with:
        repository: codelibs/fess-parent
        ref: ${{ env.PARENT_BRANCH }}
        path: fess-parent
    - name: Install fess-parent
      run: |
        cd fess-parent
        mvn install -Dgpg.skip=true
    - name: Build with Maven

Registered: Fri Sep 19 09:08:11 UTC 2025

- Last Modified: Sun May 18 02:59:16 UTC 2025

- 1.1K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

.github/workflows/maven.yml

        restore-keys: |
          ${{ runner.os }}-maven-
    - name: Checkout fess-parent
      uses: actions/checkout@v4
      with:
        repository: codelibs/fess-parent
        ref: ${{ env.PARENT_BRANCH }}
        path: fess-parent
    - name: Install fess-parent
      run: |
        cd fess-parent
        mvn install -Dgpg.skip=true
    - name: Build with Maven

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun May 18 03:08:24 UTC 2025

- 1.1K bytes

- Viewed (0)

Search Options