spb/tendril Public
Tendril — web ingestion platform (scrape/crawl/map/search) on macOS Apple Silicon: WebKit fidelity, authenticated pages, deterministic testable extraction. A self-hosted Firecrawl alternative.
JavaScript 82.6%
TypeScript 11.8%
HTML 5.3%
1// author: simon-pierre boucher <contact@spboucher.ai>2export interface PageMetadata {3 title?: string;4 description?: string;5 author?: string;6 canonical?: string;7 lang?: string;8 image?: string;9 siteName?: string;10 type?: string;11 publishedTime?: string;12 modifiedTime?: string;13 keywords?: string[];14}1516export interface StructuredData {17 jsonld: unknown[];18 openGraph: Record<string, string>;19 twitter: Record<string, string>;20}2122export interface ExtractOptions {23 readonly url: string;24 readonly onlyMainContent?: boolean;25 readonly includeTags?: readonly string[];26 readonly excludeTags?: readonly string[];27}2829export interface ExtractResult {30 readonly markdown: string;31 readonly html: string;32 readonly links: PageLink[];33 readonly metadata: PageMetadata;34 readonly structured: StructuredData;35 readonly textLength: number;36}3738export interface PageLink {39 readonly url: string;40 readonly text: string;41 readonly rel: string | null;42 readonly isInternal: boolean;43}4445export const PIPELINE_VERSION = "0.1.0";46