Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 5 of 5 for getDomParser (0.08 sec)

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

        private final ThreadLocal<XPathAPI> xpathAPI = new ThreadLocal<>();
    
        @Override
        protected ExtractData createExtractData(final String content) {
            final DOMParser parser = getDomParser();
            try (final Reader reader = new StringReader(content)) {
                parser.parse(new InputSource(reader));
            } catch (final Exception e) {
                logger.warn("Failed to parse the content.", e);
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 6.9K bytes
    - Viewed (0)
  2. 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 Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:47:32 UTC 2024
    - 7K bytes
    - Viewed (0)
  3. 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 Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Oct 24 12:16:00 UTC 2024
    - 19.4K bytes
    - Viewed (0)
  4. fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/XpathTransformer.java

         * of 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 Nov 10 03:50:12 UTC 2024
    - Last Modified: Sat Oct 12 01:40:57 UTC 2024
    - 8.8K bytes
    - Viewed (0)
  5. src/main/java/org/codelibs/fess/crawler/transformer/FessXpathTransformer.java

        public Logger getLogger() {
            return logger;
        }
    
        @Override
        protected void storeData(final ResponseData responseData, final ResultData resultData) {
            final DOMParser parser = getDomParser();
            try (final BufferedInputStream bis = new BufferedInputStream(responseData.getResponseBody())) {
                final byte[] bomBytes = new byte[UTF8_BOM_SIZE];
                bis.mark(UTF8_BOM_SIZE);
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Thu Oct 24 13:01:38 UTC 2024
    - 42.9K bytes
    - Viewed (0)
Back to top