- Sort Score
- Result 10 results
- Languages All
Results 1 - 5 of 5 for canonical (0.25 sec)
-
src/main/java/org/codelibs/fess/es/config/exentity/CrawlingConfig.java
public static final String CLEANUP_URL_FILTERS = "cleanup.urlFilters"; public static final String JCIFS_PREFIX = "jcifs."; public static final String HTML_CANONICAL_XPATH = "html.canonical.xpath"; public static final String HTML_PRUNED_TAGS = "html.pruned.tags"; public static final String PIPELINE = "pipeline";
Java - Registered: Mon Apr 29 08:04:11 GMT 2024 - Last Modified: Thu Feb 22 01:37:57 GMT 2024 - 5.5K bytes - Viewed (0) -
src/main/resources/fess_config.properties
# html crawler.document.html.content.xpath=//BODY crawler.document.html.lang.xpath=//HTML/@lang crawler.document.html.digest.xpath=//META[@name='description']/@content crawler.document.html.canonical.xpath=//LINK[@rel='canonical'][1]/@href crawler.document.html.pruned.tags=noscript,script,style,header,footer,aside,nav,a[rel=nofollow] crawler.document.html.max.digest.length=120 crawler.document.html.default.lang=
Properties - Registered: Mon Apr 29 08:04:11 GMT 2024 - Last Modified: Thu Apr 11 02:34:53 GMT 2024 - 30.6K bytes - Viewed (1) -
src/test/java/org/codelibs/fess/crawler/transformer/FessXpathTransformerTest.java
data = "<html><head><link rel=\"canonical\" href=\"http://example.com/\"></head><body>aaa</body></html>"; document = getDocument(data); value = transformer.getCanonicalUrl(responseData, document); assertEquals("http://example.com/", value); data = "<html><head><link rel=\"canonical\" href=\"http://example1.com/\"><link rel=\"canonical\" href=\"http://example2.com/\"></head><body>aaa</body></html>";
Java - Registered: Mon Apr 29 08:04:11 GMT 2024 - Last Modified: Thu Feb 22 01:37:57 GMT 2024 - 38.6K bytes - Viewed (0) -
src/main/java/org/codelibs/fess/crawler/transformer/FessXpathTransformer.java
logger.debug("Invalid Canonical Url(https->http): {} -> {}", url, canonicalUrl); } return false; } return true; } protected void putAdditionalData(final Map<String, Object> dataMap, final ResponseData responseData, final Document document) { // canonical final String canonicalUrl = getCanonicalUrl(responseData, document);
Java - Registered: Mon Apr 29 08:04:11 GMT 2024 - Last Modified: Thu Feb 22 01:37:57 GMT 2024 - 41.9K bytes - Viewed (0) -
src/main/java/org/codelibs/fess/mylasta/direction/FessConfig.java
String CRAWLER_DOCUMENT_HTML_DIGEST_XPATH = "crawler.document.html.digest.xpath"; /** The key of the configuration. e.g. //LINK[@rel='canonical'][1]/@href */ String CRAWLER_DOCUMENT_HTML_CANONICAL_XPATH = "crawler.document.html.canonical.xpath"; /** The key of the configuration. e.g. noscript,script,style,header,footer,aside,nav,a[rel=nofollow] */
Java - Registered: Mon Apr 29 08:04:11 GMT 2024 - Last Modified: Thu Apr 11 02:34:53 GMT 2024 - 459.2K bytes - Viewed (4)