Versions in this module Expand all Collapse all v1 v1.5.1 Jun 26, 2023 v1.5.0 Jun 25, 2023 Changes in this version + func CreateReadableDocument(extract *ExtractResult) *html.Node + type Config struct + CacheSize int + MaxDuplicateCount int + MinDuplicateCheckSize int + MinExtractedCommentSize int + MinExtractedSize int + MinOutputCommentSize int + MinOutputSize int + func DefaultConfig() *Config + type ExtractResult struct + CommentsNode *html.Node + CommentsText string + ContentNode *html.Node + ContentText string + Metadata Metadata + func Extract(r io.Reader, opts Options) (*ExtractResult, error) + func ExtractDocument(doc *html.Node, opts Options) (*ExtractResult, error) + type FallbackConfig struct + DistillerFallback *html.Node + HasDistiller bool + HasReadability bool + OtherFallbacks []*html.Node + ReadabilityFallback *html.Node + type Metadata struct + Author string + Categories []string + Date time.Time + Description string + Fingerprint string + Hostname string + ID string + Image string + Language string + License string + PageType string + Sitename string + Tags []string + Title string + URL string + type Options struct + BlacklistedAuthors []string + Config *Config + Deduplicate bool + EnableLog bool + ExcludeComments bool + ExcludeTables bool + FallbackCandidates *FallbackConfig + FavorPrecision bool + FavorRecall bool + HasEssentialMetadata bool + HtmlDateOptions *htmldate.Options + HtmlDateOverride *htmldate.Result + IncludeImages bool + IncludeLinks bool + MaxTreeSize int + OriginalURL *nurl.URL + TargetLanguage string + type SchemaData struct + Data map[string]any + Type string