Search Options

Display Count
Sort
Preferred Language
Advanced Search

Results 1 - 2 of 2 for addExtractor (0.04 seconds)

  1. fess-crawler-lasta/src/main/resources/crawler/extractor.xml

    		<postConstruct name="addExtractor">
    			<arg>[
    				"application/pdf"
    				]</arg>
    			<arg>pdfExtractor</arg>
    		</postConstruct>
    		<postConstruct name="addExtractor">
    			<arg>[
    				"application/x-lha",
    				"application/x-lharc"
    				]</arg>
    			<arg>lhaExtractor</arg>
    		</postConstruct>
    		<postConstruct name="addExtractor">
    			<arg>[
    				"message/rfc822"
    				]</arg>
    			<arg>emlExtractor</arg>
    Created: Sun Apr 12 03:50:13 GMT 2026
    - Last Modified: Wed Feb 11 01:15:55 GMT 2026
    - 50.4K bytes
    - Click Count (0)
  2. README.md

    // Configure content extraction
    container.singleton("tikaExtractor", TikaExtractor.class);
    container.singleton("extractorFactory", ExtractorFactory.class, factory -> {
        factory.addExtractor("text/html", container.getComponent("tikaExtractor"));
        factory.addExtractor("application/pdf", container.getComponent("tikaExtractor"));
    });
    
    Crawler crawler = container.getComponent("crawler");
    crawler.addUrl("https://example.com");
    Created: Sun Apr 12 03:50:13 GMT 2026
    - Last Modified: Sun Aug 31 05:32:52 GMT 2025
    - 15.3K bytes
    - Click Count (0)
Back to Top