Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 3 of 3 for getDomParser (0.04 sec)

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

            }
            try {
                final BufferedInputStream bis = new BufferedInputStream(in);
                final String enc = getEncoding(bis);
    
                final DOMParser parser = getDomParser();
                final InputSource inputSource = new InputSource(bis);
                inputSource.setEncoding(enc);
                parser.parse(inputSource);
                final Document document = parser.getDocument();
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 10.3K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/HtmlTransformer.java

         */
        protected void storeChildUrls(final ResponseData responseData, final ResultData resultData) {
            try (final InputStream is = responseData.getResponseBody()) {
                final DOMParser parser = getDomParser();
                parser.parse(new InputSource(is));
                final Document document = parser.getDocument();
                // base href
                final String baseHref = getBaseHref(document);
                URI uri;
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 28.5K bytes
    - Viewed (0)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/XpathTransformer.java

         * as a String.
         */
        protected Class<?> dataClass = null;
    
        @Override
        protected void storeData(final ResponseData responseData, final ResultData resultData) {
            final DOMParser parser = getDomParser();
            try (final InputStream in = responseData.getResponseBody()) {
                final InputSource is = new InputSource(in);
                if (responseData.getCharSet() != null) {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 13.1K bytes
    - Viewed (0)
Back to top