# XPath to extract canonical URL from HTML documents.
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

:0,html:!1,selector:!1,placement:"top",offset:0,container:!1,fallbackPlacement:"flip",boundary:"scrollParent",customClass:"",sanitize:!0,sanitizeFn:null,whiteList:{"*":["class","dir","id","lang","role",/^aria-[\w-]*$/i],a:["target","href","title","rel"],area:[],b:[],br:[],col:[],code:[],div:[],em:[],hr:[],h1:[],h2:[],h3:[],h4:[],h5:[],h6:[],i:[],img:["src","srcset","alt","title","width","height"],li:[],ol:[],p:[],pre:[],s:[],small:[],span:[],sub:[],sup:[],strong:[],u:[],ul:[]},popperConfig:null}...