Package org.apache.tika.parser.html

Examples of org.apache.tika.parser.html.HtmlParser

189
190
191
192
193
194
195
196
197
198
199
200
                 data = ((ByteChunk)htmlChunk).getValue();
              } else if(htmlChunk instanceof StringChunk) {
                 data = ((StringChunk)htmlChunk).getRawValue();
              }
              if(data != null) {
                 HtmlParser htmlParser = new HtmlParser();
                 htmlParser.parse(
                       new ByteArrayInputStream(data),
                       new EmbeddedContentHandler(new BodyContentHandler(xhtml)),
                       new Metadata(), new ParseContext()
                 );
                 doneBody = true;
View Full Code Here
70
71
72
73
74
75
76
77
78
79
80
  public static AutoDetectParser createParser() {
    final AutoDetectParser parser = new AutoDetectParser();

    Map<MediaType,Parser> parsers = parser.getParsers();
    parsers.put(MediaType.APPLICATION_XML, new HtmlParser());
    parser.setParsers(parsers);

    parser.setFallback(new Parser() {
      public Set<MediaType> getSupportedTypes(ParseContext parseContext) {
        return parser.getSupportedTypes(parseContext);
View Full Code Here
190
191
192
193
194
195
196
197
198
199
200
201
              } else if(htmlChunk instanceof StringChunk) {
                 data = ((StringChunk)htmlChunk).getRawValue();
              }
              if(data != null) {
                  // nocommit same problem here?
                 HtmlParser htmlParser = new HtmlParser();
                 htmlParser.parse(
                       new ByteArrayInputStream(data),
                       new EmbeddedContentHandler(new BodyContentHandler(xhtml)),
                       new Metadata(), new ParseContext()
                 );
                 doneBody = true;
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
  public static AutoDetectParser createParser() {
    final AutoDetectParser parser = new AutoDetectParser();

    Map<MediaType,Parser> parsers = parser.getParsers();
    parsers.put(MediaType.APPLICATION_XML, new HtmlParser());
    parser.setParsers(parsers);

    parser.setFallback(new Parser() {
      public Set<MediaType> getSupportedTypes(ParseContext parseContext) {
        return parser.getSupportedTypes(parseContext);
View Full Code Here
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
     */
    private String extract(byte[][] byteObject) {// throws IOException
        StringBuilder wBuf = new StringBuilder();
        InputStream stream = null;
        Metadata metadata = new Metadata();
        HtmlParser htmlParser = new HtmlParser();
        BodyContentHandler handler = new BodyContentHandler(-1);// -1
        ParseContext parser = new ParseContext();
        try {
            for (int i = 0; i < byteObject.length; i++) {
                stream = new ByteArrayInputStream(byteObject[i]);
                try {
                    htmlParser.parse(stream, handler, metadata, parser);
                } catch (TikaException e) {
                    wBuf.append(new String(byteObject[i]));
//                    System.err.println("\n"
//                            + CHMDocumentInformation.class.getName()
//                            + " extract " + e.getMessage());
View Full Code Here
91
92
93
94
95
96
97
98
99
100
101
  @SuppressWarnings("serial")
  public static AutoDetectParser createParser(TikaConfig tikaConfig) {
    final AutoDetectParser parser = new AutoDetectParser(tikaConfig);

    Map<MediaType,Parser> parsers = parser.getParsers();
    parsers.put(MediaType.APPLICATION_XML, new HtmlParser());
    parser.setParsers(parsers);

    parser.setFallback(new Parser() {
      public Set<MediaType> getSupportedTypes(ParseContext parseContext) {
        return parser.getSupportedTypes(parseContext);
View Full Code Here
190
191
192
193
194
195
196
197
198
199
200
201
                 data = ((ByteChunk)htmlChunk).getValue();
              } else if(htmlChunk instanceof StringChunk) {
                 data = ((StringChunk)htmlChunk).getRawValue();
              }
              if(data != null) {
                 HtmlParser htmlParser = new HtmlParser();
                 htmlParser.parse(
                       new ByteArrayInputStream(data),
                       new EmbeddedContentHandler(new BodyContentHandler(xhtml)),
                       new Metadata(), new ParseContext()
                 );
                 doneBody = true;
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
     */
    private String extract(byte[] byteObject) throws TikaException {// throws IOException
        StringBuilder wBuf = new StringBuilder();
        InputStream stream = null;
        Metadata metadata = new Metadata();
        HtmlParser htmlParser = new HtmlParser();
        BodyContentHandler handler = new BodyContentHandler(-1);// -1
        ParseContext parser = new ParseContext();
        try {
            stream = new ByteArrayInputStream(byteObject);
            htmlParser.parse(stream, handler, metadata, parser);
            wBuf.append(handler.toString()
                    + System.getProperty("line.separator"));
        } catch (SAXException e) {
            throw new RuntimeException(e);
        } catch (IOException e) {
View Full Code Here
TOP

Related Classes of org.apache.tika.parser.html.HtmlParser

  • bixo.examples.webmining.DemoWebMiningTool
  • com.scaleunlimited.helpful.operations.ParseModMboxPageFunction
  • com.tamingtext.tika.TikaTest
  • edu.uci.ics.crawler4j.parser.Parser
  • org.apache.commons.io.input.CloseShieldInputStream
  • org.apache.jackrabbit.core.query.lucene.JackrabbitParser
  • org.apache.oodt.cas.protocol.imaps.ImapsProtocol
  • org.apache.oodt.cas.pushpull.protocol.http.HttpClient
  • org.apache.oodt.cas.pushpull.protocol.imaps.ImapsClient
  • org.apache.tika.detect.AutoDetectReader
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.