magpie-html 0.2.1 → 0.2.3

package/dist/index.d.cts

@@ -603,7 +603,7 @@ interface FeedItem {
  */
 interface Feed {
     /** Original feed format */
-    format: 'rss' | 'atom' | 'json-feed';
+    format: 'rss' | 'atom' | 'json-feed' | 'sitemap';
     /** Feed title (required) */
     title: string;
     /** Feed description or subtitle */
@@ -952,6 +952,7 @@ declare function gatherArticle(url: string | URL): Promise<Article>;
  * @remarks
  * This is a high-level convenience method that combines fetching and parsing.
  * It handles encoding detection, redirects, and feed format detection automatically.
+ * Falls back to sitemap parsing when standard feed formats aren't detected.
  *
  * @param url - Feed URL as string or URL object
  * @returns Normalized feed data
@@ -1042,6 +1043,11 @@ declare function gatherWebsite(url: string | URL): Promise<Website>;
  */
 declare function parseHTML(html: string, baseUrl?: string): Document;
 type HTMLDocument = Document;
+/**
+ * Input type that accepts either a parsed Document or raw HTML string.
+ * This allows extractor functions to be more forgiving.
+ */
+type DocumentInput = Document | string;
 
 /**
  * Analytics and tracking types.
@@ -1088,24 +1094,26 @@ interface AnalyticsMetadata {
  */
 
 /**
- * Extract analytics metadata from parsed HTML document.
+ * Extract analytics metadata from HTML.
  *
  * @remarks
  * Detects analytics service IDs by examining script tags and their content.
  * Only extracts identifiers, does not track or collect user data.
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @returns Analytics metadata
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const analytics = extractAnalytics(doc);
- * console.log(analytics.googleAnalytics);
- * console.log(analytics.googleTagManager);
+ *
+ * // Or directly with HTML string
+ * const analytics = extractAnalytics(htmlString);
  * ```
  */
-declare function extractAnalytics(doc: HTMLDocument): AnalyticsMetadata;
+declare function extractAnalytics(input: DocumentInput): AnalyticsMetadata;
 
 /**
  * Assets extraction types.
@@ -1189,7 +1197,7 @@ interface ConnectionHint {
  */
 
 /**
- * Extract assets metadata from parsed HTML document.
+ * Extract assets metadata from HTML.
  *
  * @remarks
  * Extracts all external assets referenced in the document, organized by type.
@@ -1205,20 +1213,21 @@ interface ConnectionHint {
  * - Preloads: `<link rel="preload">` and `<link rel="prefetch">`
  * - Connection hints: `<link rel="dns-prefetch">` and `<link rel="preconnect">`
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @param baseUrl - Optional base URL for resolving relative URLs
  * @returns Assets metadata object with categorized URLs
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const assets = extractAssets(doc, 'https://example.com');
- * console.log(assets.images);
- * console.log(assets.stylesheets);
- * console.log(assets.scripts);
+ *
+ * // Or directly with HTML string
+ * const assets = extractAssets(htmlString, 'https://example.com');
  * ```
  */
-declare function extractAssets(doc: HTMLDocument, baseUrl?: string | URL | null): AssetsMetadata;
+declare function extractAssets(input: DocumentInput, baseUrl?: string | URL | null): AssetsMetadata;
 
 /**
  * Canonical and alternate URL metadata types.
@@ -1282,24 +1291,26 @@ interface CanonicalMetadata {
  */
 
 /**
- * Extract canonical and alternate URL metadata from parsed HTML document.
+ * Extract canonical and alternate URL metadata from HTML.
  *
  * @remarks
  * Extracts canonical URLs, language alternates, AMP versions, manifests,
  * and app linking metadata.
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @returns Canonical metadata object
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const canonical = extractCanonical(doc);
- * console.log(canonical.canonical);
- * console.log(canonical.alternates);
+ *
+ * // Or directly with HTML string
+ * const canonical = extractCanonical(htmlString);
  * ```
  */
-declare function extractCanonical(doc: HTMLDocument): CanonicalMetadata;
+declare function extractCanonical(input: DocumentInput): CanonicalMetadata;
 
 /**
  * Copyright and licensing types.
@@ -1336,24 +1347,26 @@ interface CopyrightMetadata {
  */
 
 /**
- * Extract copyright metadata from parsed HTML document.
+ * Extract copyright metadata from HTML.
  *
  * @remarks
  * Extracts copyright and licensing information from meta tags, link tags,
  * and Schema.org structured data.
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @returns Copyright metadata
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const copyright = extractCopyright(doc);
- * console.log(copyright.copyright);
- * console.log(copyright.license);
+ *
+ * // Or directly with HTML string
+ * const copyright = extractCopyright(htmlString);
  * ```
  */
-declare function extractCopyright(doc: HTMLDocument): CopyrightMetadata;
+declare function extractCopyright(input: DocumentInput): CopyrightMetadata;
 
 /**
  * Dublin Core metadata types.
@@ -1413,25 +1426,27 @@ interface DublinCoreMetadata {
  */
 
 /**
- * Extract Dublin Core metadata from parsed HTML document.
+ * Extract Dublin Core metadata from HTML.
  *
  * @remarks
  * Extracts Dublin Core metadata using both DC. and dcterms. prefixes.
  * Fields that can have multiple values (creator, subject, contributor)
  * are extracted as arrays.
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @returns Dublin Core metadata object
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const dc = extractDublinCore(doc);
- * console.log(dc.title);
- * console.log(dc.creator);
+ *
+ * // Or directly with HTML string
+ * const dc = extractDublinCore(htmlString);
  * ```
  */
-declare function extractDublinCore(doc: HTMLDocument): DublinCoreMetadata;
+declare function extractDublinCore(input: DocumentInput): DublinCoreMetadata;
 
 /**
  * Feed discovery types.
@@ -1475,25 +1490,27 @@ interface FeedDiscoveryMetadata {
  */
 
 /**
- * Extract feed discovery metadata from parsed HTML document.
+ * Extract feed discovery metadata from HTML.
  *
  * @remarks
  * Finds all feeds declared in <link rel="alternate"> tags and generates
  * suggestions for common feed URL patterns.
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @param documentUrl - Optional document URL for generating absolute feed suggestions
  * @returns Feed discovery metadata
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const feeds = extractFeedDiscovery(doc, 'https://example.com');
- * console.log(feeds.feeds); // Discovered feeds
- * console.log(feeds.suggestions); // Suggested feed URLs
+ *
+ * // Or directly with HTML string
+ * const feeds = extractFeedDiscovery(htmlString, 'https://example.com');
  * ```
  */
-declare function extractFeedDiscovery(doc: HTMLDocument, documentUrl?: string | URL): FeedDiscoveryMetadata;
+declare function extractFeedDiscovery(input: DocumentInput, documentUrl?: string | URL): FeedDiscoveryMetadata;
 
 /**
  * Geographic location types.
@@ -1542,24 +1559,26 @@ interface GeoMetadata {
  */
 
 /**
- * Extract geographic metadata from parsed HTML document.
+ * Extract geographic metadata from HTML.
  *
  * @remarks
  * Extracts geographic location information including coordinates,
  * place names, and region codes from meta tags.
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @returns Geographic metadata
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const geo = extractGeo(doc);
- * console.log(geo.position?.latitude);
- * console.log(geo.placename);
+ *
+ * // Or directly with HTML string
+ * const geo = extractGeo(htmlString);
  * ```
  */
-declare function extractGeo(doc: HTMLDocument): GeoMetadata;
+declare function extractGeo(input: DocumentInput): GeoMetadata;
 
 /**
  * Icons and visual assets types.
@@ -1632,24 +1651,26 @@ interface IconsMetadata {
  */
 
 /**
- * Extract icons metadata from parsed HTML document.
+ * Extract icons metadata from HTML.
  *
  * @remarks
  * Extracts all icon-related metadata including favicons, Apple touch icons,
  * Safari mask icons, and Microsoft tile configuration.
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @returns Icons metadata
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const icons = extractIcons(doc);
- * console.log(icons.favicon);
- * console.log(icons.appleTouchIcons);
+ *
+ * // Or directly with HTML string
+ * const icons = extractIcons(htmlString);
  * ```
  */
-declare function extractIcons(doc: HTMLDocument): IconsMetadata;
+declare function extractIcons(input: DocumentInput): IconsMetadata;
 
 /**
  * Language and localization types.
@@ -1691,24 +1712,26 @@ interface LanguageMetadata {
  */
 
 /**
- * Extract language and localization metadata from parsed HTML document.
+ * Extract language and localization metadata from HTML.
  *
  * @remarks
  * Extracts language information from HTML lang attribute, meta tags,
  * and OpenGraph locale. Normalizes to provide a primary language and region.
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @returns Language metadata
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const lang = extractLanguage(doc);
- * console.log(lang.primary); // 'en'
- * console.log(lang.region); // 'US'
+ *
+ * // Or directly with HTML string
+ * const lang = extractLanguage(htmlString);
  * ```
  */
-declare function extractLanguage(doc: HTMLDocument): LanguageMetadata;
+declare function extractLanguage(input: DocumentInput): LanguageMetadata;
 
 /**
  * Links extraction types.
@@ -1855,7 +1878,7 @@ interface LinksMetadata {
  */
 
 /**
- * Extract links from parsed HTML document.
+ * Extract links from HTML.
  *
  * @remarks
  * Extracts all `<a href>` links with comprehensive metadata and filtering options.
@@ -1870,21 +1893,25 @@ interface LinksMetadata {
  * - Deduplication
  * - Link text extraction
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @param baseUrl - Base URL for resolving relative links and determining internal/external
  * @param options - Extraction options for filtering and categorization
  * @returns Links metadata with categorized links
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const links = extractLinks(doc, 'https://example.com');
  *
+ * // Or directly with HTML string
+ * const links = extractLinks(htmlString, 'https://example.com');
+ *
  * // Get all internal links (same origin)
  * console.log(links.internal);
  *
  * // Get external links excluding nofollow
- * const linksNoFollow = extractLinks(doc, 'https://example.com', {
+ * const linksNoFollow = extractLinks(htmlString, 'https://example.com', {
  *   scope: 'external',
  *   excludeRel: ['nofollow']
  * });
@@ -1893,13 +1920,13 @@ interface LinksMetadata {
  * @example
  * ```typescript
  * // Crawler use case - get follow-able links
- * const links = extractLinks(doc, baseUrl, {
+ * const links = extractLinks(html, baseUrl, {
  *   excludeRel: ['nofollow', 'ugc', 'sponsored'],
  *   includeHashLinks: false
  * });
  * ```
  */
-declare function extractLinks(doc: HTMLDocument, baseUrl?: string | URL | null, options?: LinksExtractionOptions): LinksMetadata;
+declare function extractLinks(input: DocumentInput, baseUrl?: string | URL | null, options?: LinksExtractionOptions): LinksMetadata;
 
 /**
  * Monetization and payment types.
@@ -1940,24 +1967,26 @@ interface MonetizationMetadata {
  */
 
 /**
- * Extract monetization metadata from parsed HTML document.
+ * Extract monetization metadata from HTML.
  *
  * @remarks
  * Extracts web monetization, payment verification, and cryptocurrency
  * addresses from meta tags and link tags.
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @returns Monetization metadata
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const monetization = extractMonetization(doc);
- * console.log(monetization.webMonetization);
- * console.log(monetization.bitcoin);
+ *
+ * // Or directly with HTML string
+ * const monetization = extractMonetization(htmlString);
  * ```
  */
-declare function extractMonetization(doc: HTMLDocument): MonetizationMetadata;
+declare function extractMonetization(input: DocumentInput): MonetizationMetadata;
 
 /**
  * News and press types.
@@ -1994,24 +2023,26 @@ interface NewsMetadata {
  */
 
 /**
- * Extract news metadata from parsed HTML document.
+ * Extract news metadata from HTML.
  *
  * @remarks
  * Extracts news-specific metadata including keywords, standout tags,
  * and syndication information.
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @returns News metadata
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const news = extractNews(doc);
- * console.log(news.keywords);
- * console.log(news.standout);
+ *
+ * // Or directly with HTML string
+ * const news = extractNews(htmlString);
  * ```
  */
-declare function extractNews(doc: HTMLDocument): NewsMetadata;
+declare function extractNews(input: DocumentInput): NewsMetadata;
 
 /**
  * OpenGraph metadata types.
@@ -2179,7 +2210,7 @@ interface OpenGraphMetadata {
  * console.log(og.article?.publishedTime);
  * ```
  */
-declare function extractOpenGraph(doc: HTMLDocument): OpenGraphMetadata;
+declare function extractOpenGraph(input: DocumentInput): OpenGraphMetadata;
 
 /**
  * Pagination metadata types.
@@ -2220,24 +2251,26 @@ interface PaginationMetadata {
  */
 
 /**
- * Extract pagination metadata from parsed HTML document.
+ * Extract pagination metadata from HTML.
  *
  * @remarks
  * Extracts pagination navigation links including prev, next, first, last,
  * up (parent), and index links.
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @returns Pagination metadata
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const pagination = extractPagination(doc);
- * console.log(pagination.prev); // Previous page URL
- * console.log(pagination.next); // Next page URL
+ *
+ * // Or directly with HTML string
+ * const pagination = extractPagination(htmlString);
  * ```
  */
-declare function extractPagination(doc: HTMLDocument): PaginationMetadata;
+declare function extractPagination(input: DocumentInput): PaginationMetadata;
 
 /**
  * Robots and crawling directives types.
@@ -2299,24 +2332,26 @@ interface RobotsMetadata {
  */
 
 /**
- * Extract robots metadata from parsed HTML document.
+ * Extract robots metadata from HTML.
  *
  * @remarks
  * Extracts robot directives from meta tags for general robots,
  * Googlebot, Bingbot, and Google News bot.
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @returns Robots metadata
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const robots = extractRobots(doc);
- * console.log(robots.robots?.index); // true/false
- * console.log(robots.robots?.follow); // true/false
+ *
+ * // Or directly with HTML string
+ * const robots = extractRobots(htmlString);
  * ```
  */
-declare function extractRobots(doc: HTMLDocument): RobotsMetadata;
+declare function extractRobots(input: DocumentInput): RobotsMetadata;
 
 /**
  * Schema.org / JSON-LD metadata types.
@@ -2381,24 +2416,26 @@ interface SchemaOrgMetadata {
  */
 
 /**
- * Extract Schema.org metadata from parsed HTML document.
+ * Extract Schema.org metadata from HTML.
  *
  * @remarks
  * Finds all <script type="application/ld+json"> tags, parses the JSON-LD,
  * and organizes by type for easy access.
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @returns Schema.org metadata object
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const schema = extractSchemaOrg(doc);
- * console.log(schema.jsonLd.length);
- * console.log(schema.articles);
+ *
+ * // Or directly with HTML string
+ * const schema = extractSchemaOrg(htmlString);
  * ```
  */
-declare function extractSchemaOrg(doc: HTMLDocument): SchemaOrgMetadata;
+declare function extractSchemaOrg(input: DocumentInput): SchemaOrgMetadata;
 
 /**
  * Security and privacy types.
@@ -2435,24 +2472,26 @@ interface SecurityMetadata {
  */
 
 /**
- * Extract security metadata from parsed HTML document.
+ * Extract security metadata from HTML.
  *
  * @remarks
  * Extracts security and privacy-related meta tags including referrer policy,
  * content security policy, and browser compatibility directives.
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @returns Security metadata
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const security = extractSecurity(doc);
- * console.log(security.referrerPolicy);
- * console.log(security.contentSecurityPolicy);
+ *
+ * // Or directly with HTML string
+ * const security = extractSecurity(htmlString);
  * ```
  */
-declare function extractSecurity(doc: HTMLDocument): SecurityMetadata;
+declare function extractSecurity(input: DocumentInput): SecurityMetadata;
 
 /**
  * SEO metadata types.
@@ -2506,24 +2545,26 @@ interface SEOMetadata {
  */
 
 /**
- * Extract SEO metadata from parsed HTML document.
+ * Extract SEO metadata from HTML.
  *
  * @remarks
  * Extracts standard SEO meta tags including title, description, keywords,
  * and browser-specific configuration. All fields are optional.
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @returns SEO metadata object
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const seo = extractSEO(doc);
- * console.log(seo.title); // Page title
- * console.log(seo.description); // Meta description
+ *
+ * // Or directly with HTML string
+ * const seo = extractSEO(htmlString);
  * ```
  */
-declare function extractSEO(doc: HTMLDocument): SEOMetadata;
+declare function extractSEO(input: DocumentInput): SEOMetadata;
 
 /**
  * Sitemap discovery types.
@@ -2556,25 +2597,27 @@ interface SitemapDiscoveryMetadata {
  */
 
 /**
- * Extract sitemap discovery metadata from parsed HTML document.
+ * Extract sitemap discovery metadata from HTML.
  *
  * @remarks
  * Finds all sitemaps declared in <link rel="sitemap"> tags and generates
  * suggestions for common sitemap URL patterns.
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @param documentUrl - Optional document URL for generating absolute sitemap suggestions
  * @returns Sitemap discovery metadata
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const sitemaps = extractSitemapDiscovery(doc, 'https://example.com');
- * console.log(sitemaps.sitemaps); // Discovered sitemaps
- * console.log(sitemaps.suggestions); // Suggested sitemap URLs
+ *
+ * // Or directly with HTML string
+ * const sitemaps = extractSitemapDiscovery(htmlString, 'https://example.com');
  * ```
  */
-declare function extractSitemapDiscovery(doc: HTMLDocument, documentUrl?: string | URL): SitemapDiscoveryMetadata;
+declare function extractSitemapDiscovery(input: DocumentInput, documentUrl?: string | URL): SitemapDiscoveryMetadata;
 
 /**
  * Social profiles types.
@@ -2625,23 +2668,25 @@ interface SocialProfilesMetadata {
  */
 
 /**
- * Extract social profiles metadata from parsed HTML document.
+ * Extract social profiles metadata from HTML.
  *
  * @remarks
  * Extracts social media profile URLs and handles from meta tags and structured data.
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @returns Social profiles metadata
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const profiles = extractSocialProfiles(doc);
- * console.log(profiles.twitter);
- * console.log(profiles.facebook);
+ *
+ * // Or directly with HTML string
+ * const profiles = extractSocialProfiles(htmlString);
  * ```
  */
-declare function extractSocialProfiles(doc: HTMLDocument): SocialProfilesMetadata;
+declare function extractSocialProfiles(input: DocumentInput): SocialProfilesMetadata;
 
 /**
  * Twitter Card metadata types.
@@ -2724,24 +2769,26 @@ interface TwitterCardMetadata {
  */
 
 /**
- * Extract Twitter Card metadata from parsed HTML document.
+ * Extract Twitter Card metadata from HTML.
  *
  * @remarks
  * Extracts Twitter Card metadata including card type, site/creator info,
  * title/description, images, app cards, and player cards.
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @returns Twitter Card metadata object
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const twitter = extractTwitterCard(doc);
- * console.log(twitter.card);
- * console.log(twitter.title);
+ *
+ * // Or directly with HTML string
+ * const twitter = extractTwitterCard(htmlString);
  * ```
  */
-declare function extractTwitterCard(doc: HTMLDocument): TwitterCardMetadata;
+declare function extractTwitterCard(input: DocumentInput): TwitterCardMetadata;
 
 /**
  * Verification tags types.
@@ -2786,23 +2833,25 @@ interface VerificationMetadata {
  */
 
 /**
- * Extract verification metadata from parsed HTML document.
+ * Extract verification metadata from HTML.
  *
  * @remarks
  * Extracts verification tags used by various platforms for domain and ownership verification.
  *
- * @param doc - Parsed HTML document
+ * @param input - Parsed HTML document or raw HTML string
  * @returns Verification metadata
  *
  * @example
  * ```typescript
+ * // With parsed document (recommended for multiple extractions)
  * const doc = parseHTML(htmlString);
  * const verification = extractVerification(doc);
- * console.log(verification.googleSiteVerification);
- * console.log(verification.facebookDomainVerification);
+ *
+ * // Or directly with HTML string
+ * const verification = extractVerification(htmlString);
  * ```
  */
-declare function extractVerification(doc: HTMLDocument): VerificationMetadata;
+declare function extractVerification(input: DocumentInput): VerificationMetadata;
 
 /**
  * Enhanced fetch types for web scraping.
@@ -3253,4 +3302,4 @@ interface SwoopResult {
  */
 declare function swoop(url: string | URL, init?: SwoopInit): Promise<SwoopResult>;
 
-export { type AlternateLink, type AnalyticsMetadata, type AppLinks, type AppleTouchIcon, type Article, type AssetsMetadata, type CanonicalMetadata, type ConnectionHint, type ContentExtractionOptions, type ContentQuality, type ContentResult, type CopyrightMetadata, type DiscoveredFeed, type DublinCoreMetadata, type ExtractedContent, type ExtractedLink, type ExtractionErrorType, type ExtractionFailure, type Feed, type FeedAuthor, type FeedDiscoveryMetadata, type FeedEnclosure, type FeedFormat, type FeedItem, type GeoMetadata, type GeoPosition, type HTMLDocument, type HtmlToTextOptions, type IconsMetadata, type JsonLdBlock, type LanguageMetadata, type LinksExtractionOptions, type LinksMetadata, type MSTile, type MaskIcon, type MonetizationMetadata, type NewsMetadata, type OpenGraphArticle, type OpenGraphAudio, type OpenGraphBook, type OpenGraphImage, type OpenGraphMetadata, type OpenGraphProfile, type OpenGraphVideo, type PaginationMetadata, type ParseResult, PluckContentTypeError, PluckEncodingError, PluckError, PluckHttpError, type PluckInit, PluckNetworkError, PluckRedirectError, type PluckResponse, PluckSizeError, PluckTimeoutError, type PreloadResource, type RobotDirectives, type RobotsMetadata, type SEOMetadata, type SchemaOrgMetadata, type SecurityMetadata, type SitemapDiscoveryMetadata, type SocialProfilesMetadata, SwoopEnvironmentError, SwoopError, SwoopExecutionError, type SwoopInit, type SwoopResult, SwoopSecurityError, SwoopTimeoutError, type SwoopWaitStrategy, type TwitterApp, type TwitterAppPlatform, type TwitterCardMetadata, type TwitterPlayer, type VerificationMetadata, type Website, assessContentQuality, calculateReadingTime, countWords, detectFormat, extractAnalytics, extractAssets, extractCanonical, extractContent, extractCopyright, extractDublinCore, extractFeedDiscovery, extractGeo, extractIcons, extractLanguage, extractLinks, extractMonetization, extractNews, extractOpenGraph, extractPagination, extractRobots, extractSEO, extractSchemaOrg, extractSecurity, extractSitemapDiscovery, extractSocialProfiles, extractTwitterCard, extractVerification, gatherArticle, gatherFeed, gatherWebsite, htmlToText, isAtom, isFeed, isJSONFeed, isProbablyReaderable, isRSS, parseFeed, parseHTML, pluck, swoop };
+export { type AlternateLink, type AnalyticsMetadata, type AppLinks, type AppleTouchIcon, type Article, type AssetsMetadata, type CanonicalMetadata, type ConnectionHint, type ContentExtractionOptions, type ContentQuality, type ContentResult, type CopyrightMetadata, type DiscoveredFeed, type DocumentInput, type DublinCoreMetadata, type ExtractedContent, type ExtractedLink, type ExtractionErrorType, type ExtractionFailure, type Feed, type FeedAuthor, type FeedDiscoveryMetadata, type FeedEnclosure, type FeedFormat, type FeedItem, type GeoMetadata, type GeoPosition, type HTMLDocument, type HtmlToTextOptions, type IconsMetadata, type JsonLdBlock, type LanguageMetadata, type LinksExtractionOptions, type LinksMetadata, type MSTile, type MaskIcon, type MonetizationMetadata, type NewsMetadata, type OpenGraphArticle, type OpenGraphAudio, type OpenGraphBook, type OpenGraphImage, type OpenGraphMetadata, type OpenGraphProfile, type OpenGraphVideo, type PaginationMetadata, type ParseResult, PluckContentTypeError, PluckEncodingError, PluckError, PluckHttpError, type PluckInit, PluckNetworkError, PluckRedirectError, type PluckResponse, PluckSizeError, PluckTimeoutError, type PreloadResource, type RobotDirectives, type RobotsMetadata, type SEOMetadata, type SchemaOrgMetadata, type SecurityMetadata, type SitemapDiscoveryMetadata, type SocialProfilesMetadata, SwoopEnvironmentError, SwoopError, SwoopExecutionError, type SwoopInit, type SwoopResult, SwoopSecurityError, SwoopTimeoutError, type SwoopWaitStrategy, type TwitterApp, type TwitterAppPlatform, type TwitterCardMetadata, type TwitterPlayer, type VerificationMetadata, type Website, assessContentQuality, calculateReadingTime, countWords, detectFormat, extractAnalytics, extractAssets, extractCanonical, extractContent, extractCopyright, extractDublinCore, extractFeedDiscovery, extractGeo, extractIcons, extractLanguage, extractLinks, extractMonetization, extractNews, extractOpenGraph, extractPagination, extractRobots, extractSEO, extractSchemaOrg, extractSecurity, extractSitemapDiscovery, extractSocialProfiles, extractTwitterCard, extractVerification, gatherArticle, gatherFeed, gatherWebsite, htmlToText, isAtom, isFeed, isJSONFeed, isProbablyReaderable, isRSS, parseFeed, parseHTML, pluck, swoop };