Versions in this module Expand all Collapse all v0 v0.1.1 May 31, 2026 v0.1.0 May 31, 2026 Changes in this version + const ChunkHeading + const ChunkOff + const ChunkSentence + const ChunkWindow + const DecisionBlocked + const DecisionBrowserNeeded + const DecisionNotFound + const DecisionStaticCaution + const DecisionStaticHighConfidence + const DecisionStaticOK + const DecisionUnreachable + const DecisionUnsupported + const LinkRetentionAll + const LinkRetentionFooter + const LinkRetentionNone + const LinkRetentionText + var FlattenSitemap = engine.FlattenSitemap + var ParseFeed = engine.ParseFeed + func CleanupMarkdown(md string) string + func ContentChanged(oldContent, newContent string) bool + func DetectBlocked(html string) bool + func DetectSPA(html string) (signals []string, isSPA bool) + func ExtractFromHTML(html string, targetURL string) (string, error) + func FetchBytes(ctx context.Context, rawURL string, opts FetchBytesOptions) ([]byte, http.Header, int, error) + func PreprocessHTML(html string) string + func QuickNeedsBrowser(html string) (needsBrowser bool, reason string) + func ResultToTEIXML(r Result) ([]byte, error) + func SemanticFingerprint(content string) string + type BrowserDecision = engine.BrowserDecision + type CardItem = engine.CardItem + type Chunk = engine.Chunk + func ChunkMarkdown(md string, cfg ChunkConfig) []Chunk + type ChunkConfig = engine.ChunkConfig + func ParseChunkConfig(s string) (ChunkConfig, error) + type ChunkStrategy = engine.ChunkStrategy + type DedupeOptions = engine.DedupeOptions + type DedupeResult = engine.DedupeResult + func Dedupe(content string) DedupeResult + func DedupeWithOptions(content string, opts DedupeOptions) DedupeResult + type ExtractionOutcome = engine.ExtractionOutcome + type FeedItem = engine.FeedItem + type FetchBytesOptions = engine.FetchBytesOptions + type FlattenSitemapOptions = engine.FlattenSitemapOptions + type IndexPageResult = engine.IndexPageResult + type LinkRetention = engine.LinkRetention + func ParseLinkRetention(s string) (LinkRetention, error) + type Options = engine.Options + type PageClass = engine.PageClass + type PageProfile = engine.PageProfile + func ClassifyPage(result Result) PageProfile + type ParseFeedOptions = engine.ParseFeedOptions + type RankedSection = engine.RankedSection + func RankSections(content, query string, k1, b float64, topN int) []RankedSection + type Result = engine.Result + func FromHTML(html string, targetURL string) Result + func FromHTMLWithOptions(html string, targetURL string, opts Options) Result + func FromResponse(resp *http.Response, targetURL string, start time.Time) Result + func FromURL(targetURL string) Result + func FromURLWithDedupe(targetURL string) Result + func FromURLWithOptions(targetURL string, opts Options) Result + type SecurityPolicy = engine.SecurityPolicy + func DefaultSecurityPolicy() *SecurityPolicy + type SitemapEntry = engine.SitemapEntry + type SnapshotNode = engine.SnapshotNode + func BuildSnapshot(htmlStr string) (*SnapshotNode, error) + func BuildSnapshotWithOptions(htmlStr string, opts SnapshotOptions) (*SnapshotNode, error) + type SnapshotOptions = engine.SnapshotOptions + type SplitConfig = engine.SplitConfig + type SplitFile = engine.SplitFile + func SplitResultToFiles(r Result, cfg SplitConfig) ([]SplitFile, error) + type Validation = engine.Validation + func ValidateExtraction(r *Result) Validation
Go to main page