site-metadata-extractor/dist/index.d.ts

web(site) resource metadata extractor

import type { Cheerio, CheerioAPI } from "cheerio";
import type { AnyNode } from "domhandler";
import { NewsArticle, Article } from "schema-dts";
import { LinkObj, VideoAttrs } from "./extractor";
export interface PageData {
    author: string[];
    canonicalLink: string;
    copyright: string;
    date: string;
    description: string;
    favicon: string;
    image: string;
    jsonld: NewsArticle | Article | null;
    keywords: string;
    lang: string;
    links?: LinkObj[];
    locale: string;
    origin: string;
    publisher: string;
    siteName: string;
    softTitle: string;
    tags: string[];
    text?: string;
    title: string;
    type: string;
    videos?: VideoAttrs[];
}
export interface LazyExtractor {
    author: () => string[];
    canonicalLink: () => string;
    copyright: () => string;
    date: () => string;
    description: () => string;
    favicon: () => string;
    image: () => string;
    jsonld: () => NewsArticle | Article | null;
    keywords: () => string;
    lang: () => string;
    links: () => LinkObj[];
    locale: () => string;
    origin: () => string;
    publisher: () => string;
    siteName: () => string;
    softTitle: () => string;
    tags: () => string[];
    text: () => string;
    title: () => string;
    type: () => string;
    videos: () => VideoAttrs[];
}
export interface ExtractOptions {
    inputUrl?: string;
    finalUrl?: string;
    lang?: string;
    maxStringLength?: number;
    maxCandidates?: number;
    maxReadableTextLength?: number;
}
export interface AssetCandidate {
    url: string;
    source: string;
    rel?: string;
    type?: string;
    sizes?: string;
    width?: number;
    height?: number;
    alt?: string;
}
export interface ExtractedLink {
    url: string;
    text: string;
    rel?: string;
    title?: string;
}
export interface ExtractedVideo {
    url: string;
    source: string;
    width?: number;
    height?: number;
    type?: string;
}
export interface TextStats {
    charCount: number;
    wordCount: number;
    sentenceCount: number;
    truncated: boolean;
}
export interface ExtractionMetadata {
    packageVersion: string;
    strategyVersion: string;
    warnings: string[];
    confidence: number;
}
export interface ExtractedResource {
    inputUrl: string;
    finalUrl: string;
    canonicalUrl: string;
    normalizedUrl: string;
    domain: string;
    title: string;
    softTitle: string;
    description: string;
    author: string[];
    publisher: string;
    siteName: string;
    lang: string;
    locale: string;
    publishedAt: string;
    modifiedAt: string;
    faviconCandidates: AssetCandidate[];
    imageCandidates: AssetCandidate[];
    primaryImage: AssetCandidate | null;
    jsonld: unknown[];
    rawMeta: Record<string, string[]>;
    links: ExtractedLink[];
    videos: ExtractedVideo[];
    readableText: string;
    textStats: TextStats;
    extraction: ExtractionMetadata;
}
export interface LazyExtractedResource {
    metadata: () => ExtractedResource;
    readableText: () => string;
    links: () => ExtractedLink[];
    videos: () => ExtractedVideo[];
    extract: () => ExtractedResource;
}
export declare function extractFromHtml(html: string, options?: ExtractOptions): ExtractedResource;
export declare function extractMetadataOnly(html: string, options?: ExtractOptions): ExtractedResource;
export declare function extractLazy(html: string, options?: ExtractOptions): LazyExtractedResource;
declare const siteMetadataExtractor: (markup: string, resourceUrl: string, lang?: string) => PageData;
export default siteMetadataExtractor;
export declare const lazy: (html: string, resourceUrl: string, language?: string) => LazyExtractor;
export declare function getCleanedDoc(html: string): CheerioAPI;
export declare function getParsedDoc(html: string): CheerioAPI;
export declare function getParsedDocForText(html: string): CheerioAPI;
export declare function getTopNode(doc: CheerioAPI, lang: string): Cheerio<AnyNode>;