crawler.document.html.canonical.xpath=//LINK[@rel='canonical'][1]/@href
# HTML tags to prune (remove) during document processing.
crawler.document.html.pruned.tags=noscript,script,style,header,footer,aside,nav,a[rel=nofollow]
# Maximum length of digest extracted from HTML documents.
crawler.document.html.max.digest.length=120
# Default language for HTML documents.
crawler.document.html.default.lang=

    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] */
    String CRAWLER_DOCUMENT_HTML_PRUNED_TAGS = "crawler.document.html.pruned.tags";

    /** The key of the configuration. e.g. 120 */