Body - Code Search

fess-crawler/src/main/java/org/codelibs/fess/crawler/util/ResponseDataUtil.java

    }

    /**
     * Creates a temporary file containing the response body from the given ResponseData.
     *
     * @param responseData the response data containing the response body
     * @return a temporary file containing the response body
     * @throws CrawlingAccessException if an error occurs while reading the response body
     */
    public static File createResponseBodyFile(final ResponseData responseData) {

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

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

- 2.4K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

 *
 * <p>
 * This transformer extracts the binary content from the response body of a web resource,
 * stores it as a byte array in the ResultData, and provides a method to retrieve this data
 * as a ByteArrayInputStream.
 * </p>
 *
 * <p>
 * The transform method takes a ResponseData object, checks if it has a response body,
 * and then reads the body into a byte array. This byte array is then set as the data
 * in the ResultData object.

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

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

- 3.8K 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/resources/ajax/index.html

    <title>Ajax Test</title>
    <script language="javascript" src="js/jquery-2.1.1.min.js" type="text/javascript"></script>
    <script language="javascript" src="js/test.js" type="text/javascript"></script>
</head>
<body>
    <div id="header">
        <h1>Ajax Test Site</h1>
    </div>
    <div id="menubar">
        <ul>
            <li><a id="home" href="javascript:void(0)">Home</a></li>

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

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

- 1.5K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

    private static String getHtmlContent(final int count) {
        final StringBuilder buf = new StringBuilder();
        buf.append("<html><head><title>Title ");
        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");

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/XpathTransformer.java

 * transformer.addFieldRule("title", "//title/text()");
 * transformer.addFieldRule("body", "//body/p/text()");
 *
 * ResponseData responseData = new ResponseData();
 * responseData.setBody(new ByteArrayInputStream("&lt;html&gt;&lt;head&gt;&lt;title&gt;Example&lt;/title&gt;&lt;/head&gt;&lt;body&gt;&lt;p&gt;Hello World&lt;/p&gt;&lt;/body&gt;&lt;/html&gt;".getBytes()));
 * responseData.setUrl("http://example.com");
 *

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

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

- 13.1K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

import jakarta.annotation.Resource;

/**
 * TextTransformer is a class that transforms a ResponseData object into a ResultData object containing the extracted text content.
 * It uses an Extractor to extract the text from the response body based on the MIME type.
 * The extracted text is then converted into a byte array using the specified charset encoding.
 * It also provides a method to retrieve the extracted data as a String from an AccessResultData object.
 *

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

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

- 6.5K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/EmlExtractor.java

    public void setMailProperties(final Properties mailProperties) {
        this.mailProperties = mailProperties;
    }

    /**
     * Extracts the body text from a MIME message.
     *
     * @param message the MIME message to extract text from
     * @return the extracted body text
     * @throws ExtractException if extraction fails
     */
    protected String getBodyText(final MimeMessage message) {

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

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

- 12.6K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

        assertEquals("xyz", new String(resultData.getData(), resultData.getEncoding()));
    }

    public void test_transform_html() throws Exception {
        final byte[] data = new String("<html><body>xyz</body></html>").getBytes();
        final ResponseData responseData = new ResponseData();
        responseData.setUrl("file:/test.html");
        responseData.setCharSet(Constants.UTF_8);
        responseData.setResponseBody(data);

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

- Last Modified: Thu Aug 07 02:55:08 UTC 2025

- 4.6K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/processor/impl/SitemapsResponseProcessor.java

import org.codelibs.fess.crawler.processor.ResponseProcessor;

import jakarta.annotation.Resource;

/**
 * A response processor implementation that handles sitemaps.
 * It parses the response body as a SitemapSet, extracts URLs from the sitemaps,
 * and adds them as child URLs to be crawled.
 *
 * <p>
 * This class uses a {@link SitemapsHelper} to parse the sitemap XML or text.

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

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

- 3.4K bytes

- Viewed (0)

Search Options