@rivi-software/agentic-seo-check 0.1.0 → 0.2.0

package/dist/core/html/extract.d.ts

@@ -1,4 +1,4 @@
-import type { ExtractedPage } from '../types.js';
+import type { ExtractedPage } from "../types.js";
 export interface ExtractOptions {
     /** Absolute URL of the document; relative links are resolved against it (or against <base href>). */
     url: string;
@@ -7,4 +7,4 @@ export interface ExtractOptions {
     /** Host used to classify links as internal. Defaults to the host of `url`. */
     siteHost?: string;
 }
-export declare function extractPage(html: string, options: ExtractOptions): ExtractedPage;
+export declare const extractPage: (html: string, options: ExtractOptions) => ExtractedPage;

package/dist/core/html/extract.js

@@ -1,94 +1,120 @@
-import { load } from 'cheerio';
-import { isSameSite, resolveUrl, hostOf } from '../url.js';
-import { collapseWhitespace, wordCount } from './text.js';
-import { extractStructuredData } from './structured-data.js';
-export function extractPage(html, options) {
-    const $ = load(html);
-    const hasDoctype = /^\s*<!doctype\s+html/i.test(html);
-    const baseHref = $('base[href]').first().attr('href');
+import { isSameSite, resolveUrl, hostOf } from "../url.js";
+import { extractAnswerSignals } from "./answer.js";
+import { attr, parseDocument, queryAll, queryOne, text, visibleText, } from "./dom.js";
+import { extractStructuredData } from "./structured-data.js";
+import { collapseWhitespace, wordCount } from "./text.js";
+const relList = (rel) => (rel ?? "").toLowerCase().split(/\s+/u).filter(Boolean);
+const attrOrNull = (value) => value?.trim() || null;
+const firstNonEmpty = (values) => {
+    for (const v of values) {
+        if (v) {
+            return v;
+        }
+    }
+    return null;
+};
+const detectCharset = (doc) => {
+    const metaCharset = queryOne(doc, "meta[charset]");
+    const direct = metaCharset ? attr(metaCharset, "charset") : undefined;
+    if (direct) {
+        return direct.trim();
+    }
+    const httpEquiv = queryAll(doc, "meta[http-equiv]").find((el) => (attr(el, "http-equiv") ?? "").toLowerCase() === "content-type");
+    const content = httpEquiv ? attr(httpEquiv, "content") : undefined;
+    const match = content?.match(/charset=(?<charset>[\w-]+)/iu);
+    return match?.groups?.charset ?? null;
+};
+export const extractPage = (html, options) => {
+    const doc = parseDocument(html);
+    const hasDoctype = /^\s*<!doctype\s+html/iu.test(html);
+    const baseEl = queryOne(doc, "base[href]");
+    const baseHref = baseEl ? attr(baseEl, "href") : undefined;
     const base = (baseHref && resolveUrl(baseHref, options.url)) || options.url;
-    const siteHost = options.siteHost ?? hostOf(options.url) ?? '';
-    const titles = $('title')
-        .toArray()
-        .map((el) => collapseWhitespace($(el).text()));
-    const metaDescriptions = $('meta[name]')
-        .toArray()
-        .filter((el) => ($(el).attr('name') ?? '').trim().toLowerCase() === 'description')
-        .map((el) => collapseWhitespace($(el).attr('content') ?? ''));
-    const metaRobots = $('meta[name]')
-        .toArray()
-        .filter((el) => ['robots', 'googlebot', 'googlebot-news', 'bingbot'].includes(($(el).attr('name') ?? '').trim().toLowerCase()))
-        .map((el) => collapseWhitespace($(el).attr('content') ?? '').toLowerCase())
+    const siteHost = options.siteHost ?? hostOf(options.url) ?? "";
+    const titles = queryAll(doc, "title").map((el) => collapseWhitespace(text(el)));
+    const metaDescriptions = queryAll(doc, "meta[name]")
+        .filter((el) => (attr(el, "name") ?? "").trim().toLowerCase() === "description")
+        .map((el) => collapseWhitespace(attr(el, "content") ?? ""));
+    const metaRobots = queryAll(doc, "meta[name]")
+        .filter((el) => ["robots", "googlebot", "googlebot-news", "bingbot"].includes((attr(el, "name") ?? "").trim().toLowerCase()))
+        .map((el) => collapseWhitespace(attr(el, "content") ?? "").toLowerCase())
         .filter(Boolean);
-    const canonicals = $('link[rel]')
-        .toArray()
-        .filter((el) => relList($(el).attr('rel')).includes('canonical'))
-        .map((el) => ($(el).attr('href') ?? '').trim());
-    const headings = $('h1, h2, h3, h4, h5, h6')
-        .toArray()
-        .map((el) => ({ level: Number(el.tagName.slice(1)), text: collapseWhitespace($(el).text()) }));
+    const canonicals = queryAll(doc, "link[rel]")
+        .filter((el) => relList(attr(el, "rel")).includes("canonical"))
+        .map((el) => (attr(el, "href") ?? "").trim());
+    const headings = queryAll(doc, "h1, h2, h3, h4, h5, h6").map((el) => ({
+        level: Number(el.name.slice(1)),
+        text: collapseWhitespace(text(el)),
+    }));
     const og = {};
     const twitter = {};
-    $('meta[property], meta[name]').each((_, el) => {
-        const key = ($(el).attr('property') ?? $(el).attr('name') ?? '').trim().toLowerCase();
-        const content = collapseWhitespace($(el).attr('content') ?? '');
-        if (!key)
-            return;
-        if (key.startsWith('og:') && !(key in og))
+    for (const el of queryAll(doc, "meta[property], meta[name]")) {
+        const key = (attr(el, "property") ?? attr(el, "name") ?? "")
+            .trim()
+            .toLowerCase();
+        const content = collapseWhitespace(attr(el, "content") ?? "");
+        if (!key) {
+            continue;
+        }
+        if (key.startsWith("og:") && !(key in og)) {
             og[key.slice(3)] = content;
-        else if (key.startsWith('twitter:') && !(key in twitter))
+        }
+        else if (key.startsWith("twitter:") && !(key in twitter)) {
             twitter[key.slice(8)] = content;
-    });
-    const images = $('img')
-        .toArray()
-        .map((el) => ({
-        src: $(el).attr('src') ?? $(el).attr('data-src') ?? null,
-        alt: $(el).attr('alt') ?? null,
-        width: $(el).attr('width') ?? null,
-        height: $(el).attr('height') ?? null,
-        loading: $(el).attr('loading') ?? null,
+        }
+    }
+    const images = queryAll(doc, "img").map((el) => ({
+        src: attr(el, "src") ?? attr(el, "data-src") ?? null,
+        alt: attr(el, "alt") ?? null,
+        width: attr(el, "width") ?? null,
+        height: attr(el, "height") ?? null,
+        loading: attr(el, "loading") ?? null,
     }));
-    const links = $('a[href]')
-        .toArray()
-        .map((el) => {
-        const href = ($(el).attr('href') ?? '').trim();
+    const links = queryAll(doc, "a[href]").map((el) => {
+        const href = (attr(el, "href") ?? "").trim();
         // Fragment-only and empty hrefs are not links to other documents.
-        const url = href === '' || href.startsWith('#') ? null : resolveUrl(href, base);
-        const rel = $(el).attr('rel') ?? null;
+        const url = href === "" || href.startsWith("#") ? null : resolveUrl(href, base);
+        const rel = attr(el, "rel") ?? null;
         const relTokens = relList(rel);
-        const text = collapseWhitespace($(el).text());
-        const ariaLabel = collapseWhitespace($(el).attr('aria-label') ?? '');
-        const title = collapseWhitespace($(el).attr('title') ?? '');
-        const imgAlt = $(el)
-            .find('img[alt]')
-            .toArray()
-            .map((img) => collapseWhitespace($(img).attr('alt') ?? ''))
+        const linkText = collapseWhitespace(text(el));
+        const ariaLabel = collapseWhitespace(attr(el, "aria-label") ?? "");
+        const title = collapseWhitespace(attr(el, "title") ?? "");
+        const imgAlt = queryAll(el, "img[alt]")
+            .map((img) => collapseWhitespace(attr(img, "alt") ?? ""))
             .find(Boolean);
         return {
             href,
             url,
-            text,
+            text: linkText,
             rel,
-            internal: url ? isSameSite(url, siteHost, options.includeSubdomains) : false,
-            nofollow: relTokens.includes('nofollow'),
-            hasAccessibleName: Boolean(text || ariaLabel || title || imgAlt),
+            internal: url
+                ? isSameSite(url, siteHost, options.includeSubdomains)
+                : false,
+            nofollow: relTokens.includes("nofollow"),
+            hasAccessibleName: Boolean(linkText || ariaLabel || title || imgAlt),
         };
     });
-    const hreflang = $('link[rel]')
-        .toArray()
-        .filter((el) => relList($(el).attr('rel')).includes('alternate') && $(el).attr('hreflang'))
+    const hreflang = queryAll(doc, "link[rel]")
+        .filter((el) => relList(attr(el, "rel")).includes("alternate") && attr(el, "hreflang"))
         .map((el) => {
-        const href = ($(el).attr('href') ?? '').trim();
-        return { lang: ($(el).attr('hreflang') ?? '').trim(), href, url: resolveUrl(href, base) };
+        const href = (attr(el, "href") ?? "").trim();
+        return {
+            lang: (attr(el, "hreflang") ?? "").trim(),
+            href,
+            url: resolveUrl(href, base),
+        };
     });
-    const structured = extractStructuredData($);
-    const text = visibleText($);
+    const structured = extractStructuredData(doc);
+    const body = queryOne(doc, "body");
+    const bodyText = body ? visibleText(body) : "";
+    const htmlEl = queryOne(doc, "html");
+    const viewportEl = queryOne(doc, 'meta[name="viewport" i]');
     return {
         url: options.url,
         hasDoctype,
-        lang: attrOrNull($('html').attr('lang')),
-        charset: detectCharset($),
-        viewport: attrOrNull($('meta[name="viewport" i]').first().attr('content')),
+        lang: attrOrNull(htmlEl ? attr(htmlEl, "lang") : undefined),
+        charset: detectCharset(doc),
+        viewport: attrOrNull(viewportEl ? attr(viewportEl, "content") : undefined),
         titles,
         title: firstNonEmpty(titles),
         metaDescriptions,
@@ -97,7 +123,7 @@ export function extractPage(html, options) {
         canonicals,
         canonical: canonicals[0] ? resolveUrl(canonicals[0], base) : null,
         headings,
-        h1s: headings.filter((h) => h.level === 1).map((h) => h.text),
+        h1s: headings.flatMap((h) => (h.level === 1 ? [h.text] : [])),
         og,
         twitter,
         images,
@@ -105,46 +131,11 @@ export function extractPage(html, options) {
         hreflang,
         structuredData: structured.items,
         structuredDataErrors: structured.errors,
-        text,
-        wordCount: wordCount(text),
-        htmlBytes: Buffer.byteLength(html, 'utf8'),
+        text: bodyText,
+        wordCount: wordCount(bodyText),
+        htmlBytes: Buffer.byteLength(html, "utf-8"),
         hasBaseHref: Boolean(baseHref),
+        answer: extractAnswerSignals(doc, bodyText),
     };
-}
-function relList(rel) {
-    return (rel ?? '')
-        .toLowerCase()
-        .split(/\s+/)
-        .filter(Boolean);
-}
-function attrOrNull(value) {
-    const v = value?.trim();
-    return v ? v : null;
-}
-function firstNonEmpty(values) {
-    for (const v of values)
-        if (v)
-            return v;
-    return null;
-}
-function detectCharset($) {
-    const direct = $('meta[charset]').first().attr('charset');
-    if (direct)
-        return direct.trim();
-    const httpEquiv = $('meta[http-equiv]')
-        .toArray()
-        .find((el) => ($(el).attr('http-equiv') ?? '').toLowerCase() === 'content-type');
-    const content = httpEquiv ? $(httpEquiv).attr('content') : undefined;
-    const match = content?.match(/charset=([\w-]+)/i);
-    return match?.[1] ?? null;
-}
-function visibleText($) {
-    const body = $('body').clone();
-    body.find('script, style, noscript, template, svg, iframe, head').remove();
-    // Insert spaces at block boundaries so words don't fuse.
-    body.find('p, div, li, h1, h2, h3, h4, h5, h6, br, tr, td, th, section, article, header, footer, nav, blockquote, pre, dd, dt, figcaption').each((_, el) => {
-        $(el).prepend(' ').append(' ');
-    });
-    return collapseWhitespace(body.text());
-}
+};
 //# sourceMappingURL=extract.js.map

package/dist/core/html/extract.js.map

@@ -1 +1 @@
-{"version":3,"file":"extract.js","sourceRoot":"","sources":["../../../src/core/html/extract.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,IAAI,EAAmB,MAAM,SAAS,CAAC;AAEhD,OAAO,EAAE,UAAU,EAAE,UAAU,EAAE,MAAM,EAAE,MAAM,WAAW,CAAC;AAC3D,OAAO,EAAE,kBAAkB,EAAE,SAAS,EAAE,MAAM,WAAW,CAAC;AAC1D,OAAO,EAAE,qBAAqB,EAAE,MAAM,sBAAsB,CAAC;AAW7D,MAAM,UAAU,WAAW,CAAC,IAAY,EAAE,OAAuB;IAC/D,MAAM,CAAC,GAAG,IAAI,CAAC,IAAI,CAAC,CAAC;IACrB,MAAM,UAAU,GAAG,uBAAuB,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IACtD,MAAM,QAAQ,GAAG,CAAC,CAAC,YAAY,CAAC,CAAC,KAAK,EAAE,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;IACtD,MAAM,IAAI,GAAG,CAAC,QAAQ,IAAI,UAAU,CAAC,QAAQ,EAAE,OAAO,CAAC,GAAG,CAAC,CAAC,IAAI,OAAO,CAAC,GAAG,CAAC;IAC5E,MAAM,QAAQ,GAAG,OAAO,CAAC,QAAQ,IAAI,MAAM,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC;IAE/D,MAAM,MAAM,GAAG,CAAC,CAAC,OAAO,CAAC;SACtB,OAAO,EAAE;SACT,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,kBAAkB,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC;IAEjD,MAAM,gBAAgB,GAAG,CAAC,CAAC,YAAY,CAAC;SACrC,OAAO,EAAE;SACT,MAAM,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,KAAK,aAAa,CAAC;SACjF,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,kBAAkB,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,SAAS,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC;IAEhE,MAAM,UAAU,GAAG,CAAC,CAAC,YAAY,CAAC;SAC/B,OAAO,EAAE;SACT,MAAM,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,QAAQ,EAAE,WAAW,EAAE,gBAAgB,EAAE,SAAS,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAC,CAAC;SAC9H,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,kBAAkB,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,SAAS,CAAC,IAAI,EAAE,CAAC,CAAC,WAAW,EAAE,CAAC;SAC1E,MAAM,CAAC,OAAO,CAAC,CAAC;IAEnB,MAAM,UAAU,GAAG,CAAC,CAAC,WAAW,CAAC;SAC9B,OAAO,EAAE;SACT,MAAM,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,QAAQ,CAAC,WAAW,CAAC,CAAC;SAChE,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC;IAElD,MAAM,QAAQ,GAAkB,CAAC,CAAC,wBAAwB,CAAC;SACxD,OAAO,EAAE;SACT,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,EAAE,KAAK,EAAE,MAAM,CAAC,EAAE,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,kBAAkB,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC,EAAE,CAAC,CAAC,CAAC;IAEjG,MAAM,EAAE,GAA2B,EAAE,CAAC;IACtC,MAAM,OAAO,GAA2B,EAAE,CAAC;IAC3C,CAAC,CAAC,4BAA4B,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,EAAE;QAC7C,MAAM,GAAG,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,UAAU,CAAC,IAAI,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAC;QACtF,MAAM,OAAO,GAAG,kBAAkB,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,SAAS,CAAC,IAAI,EAAE,CAAC,CAAC;QAChE,IAAI,CAAC,GAAG;YAAE,OAAO;QACjB,IAAI,GAAG,CAAC,UAAU,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,GAAG,IAAI,EAAE,CAAC;YAAE,EAAE,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,GAAG,OAAO,CAAC;aACjE,IAAI,GAAG,CAAC,UAAU,CAAC,UAAU,CAAC,IAAI,CAAC,CAAC,GAAG,IAAI,OAAO,CAAC;YAAE,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,GAAG,OAAO,CAAC;IAC5F,CAAC,CAAC,CAAC;IAEH,MAAM,MAAM,GAAgB,CAAC,CAAC,KAAK,CAAC;SACjC,OAAO,EAAE;SACT,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC;QACZ,GAAG,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,UAAU,CAAC,IAAI,IAAI;QACxD,GAAG,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,IAAI;QAC9B,KAAK,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,IAAI;QAClC,MAAM,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,IAAI;QACpC,OAAO,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,SAAS,CAAC,IAAI,IAAI;KACvC,CAAC,CAAC,CAAC;IAEN,MAAM,KAAK,GAAe,CAAC,CAAC,SAAS,CAAC;SACnC,OAAO,EAAE;SACT,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE;QACV,MAAM,IAAI,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC;QAC/C,kEAAkE;QAClE,MAAM,GAAG,GAAG,IAAI,KAAK,EAAE,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,UAAU,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;QAChF,MAAM,GAAG,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,IAAI,CAAC;QACtC,MAAM,SAAS,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC;QAC/B,MAAM,IAAI,GAAG,kBAAkB,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC;QAC9C,MAAM,SAAS,GAAG,kBAAkB,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,YAAY,CAAC,IAAI,EAAE,CAAC,CAAC;QACrE,MAAM,KAAK,GAAG,kBAAkB,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC;QAC5D,MAAM,MAAM,GAAG,CAAC,CAAC,EAAE,CAAC;aACjB,IAAI,CAAC,UAAU,CAAC;aAChB,OAAO,EAAE;aACT,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,kBAAkB,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC,CAAC;aAC1D,IAAI,CAAC,OAAO,CAAC,CAAC;QACjB,OAAO;YACL,IAAI;YACJ,GAAG;YACH,IAAI;YACJ,GAAG;YACH,QAAQ,EAAE,GAAG,CAAC,CAAC,CAAC,UAAU,CAAC,GAAG,EAAE,QAAQ,EAAE,OAAO,CAAC,iBAAiB,CAAC,CAAC,CAAC,CAAC,KAAK;YAC5E,QAAQ,EAAE,SAAS,CAAC,QAAQ,CAAC,UAAU,CAAC;YACxC,iBAAiB,EAAE,OAAO,CAAC,IAAI,IAAI,SAAS,IAAI,KAAK,IAAI,MAAM,CAAC;SACjE,CAAC;IACJ,CAAC,CAAC,CAAC;IAEL,MAAM,QAAQ,GAAmB,CAAC,CAAC,WAAW,CAAC;SAC5C,OAAO,EAAE;SACT,MAAM,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,QAAQ,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,UAAU,CAAC,CAAC;SAC1F,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE;QACV,MAAM,IAAI,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC;QAC/C,OAAO,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,UAAU,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,UAAU,CAAC,IAAI,EAAE,IAAI,CAAC,EAAE,CAAC;IAC5F,CAAC,CAAC,CAAC;IAEL,MAAM,UAAU,GAAG,qBAAqB,CAAC,CAAC,CAAC,CAAC;IAE5C,MAAM,IAAI,GAAG,WAAW,CAAC,CAAC,CAAC,CAAC;IAE5B,OAAO;QACL,GAAG,EAAE,OAAO,CAAC,GAAG;QAChB,UAAU;QACV,IAAI,EAAE,UAAU,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;QACxC,OAAO,EAAE,aAAa,CAAC,CAAC,CAAC;QACzB,QAAQ,EAAE,UAAU,CAAC,CAAC,CAAC,yBAAyB,CAAC,CAAC,KAAK,EAAE,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;QAC1E,MAAM;QACN,KAAK,EAAE,aAAa,CAAC,MAAM,CAAC;QAC5B,gBAAgB;QAChB,eAAe,EAAE,aAAa,CAAC,gBAAgB,CAAC;QAChD,UAAU;QACV,UAAU;QACV,SAAS,EAAE,UAAU,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,UAAU,CAAC,UAAU,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI;QACjE,QAAQ;QACR,GAAG,EAAE,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,KAAK,KAAK,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC;QAC7D,EAAE;QACF,OAAO;QACP,MAAM;QACN,KAAK;QACL,QAAQ;QACR,cAAc,EAAE,UAAU,CAAC,KAAK;QAChC,oBAAoB,EAAE,UAAU,CAAC,MAAM;QACvC,IAAI;QACJ,SAAS,EAAE,SAAS,CAAC,IAAI,CAAC;QAC1B,SAAS,EAAE,MAAM,CAAC,UAAU,CAAC,IAAI,EAAE,MAAM,CAAC;QAC1C,WAAW,EAAE,OAAO,CAAC,QAAQ,CAAC;KAC/B,CAAC;AACJ,CAAC;AAED,SAAS,OAAO,CAAC,GAA8B;IAC7C,OAAO,CAAC,GAAG,IAAI,EAAE,CAAC;SACf,WAAW,EAAE;SACb,KAAK,CAAC,KAAK,CAAC;SACZ,MAAM,CAAC,OAAO,CAAC,CAAC;AACrB,CAAC;AAED,SAAS,UAAU,CAAC,KAAyB;IAC3C,MAAM,CAAC,GAAG,KAAK,EAAE,IAAI,EAAE,CAAC;IACxB,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC;AACtB,CAAC;AAED,SAAS,aAAa,CAAC,MAAgB;IACrC,KAAK,MAAM,CAAC,IAAI,MAAM;QAAE,IAAI,CAAC;YAAE,OAAO,CAAC,CAAC;IACxC,OAAO,IAAI,CAAC;AACd,CAAC;AAED,SAAS,aAAa,CAAC,CAAa;IAClC,MAAM,MAAM,GAAG,CAAC,CAAC,eAAe,CAAC,CAAC,KAAK,EAAE,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;IAC1D,IAAI,MAAM;QAAE,OAAO,MAAM,CAAC,IAAI,EAAE,CAAC;IACjC,MAAM,SAAS,GAAG,CAAC,CAAC,kBAAkB,CAAC;SACpC,OAAO,EAAE;SACT,IAAI,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,YAAY,CAAC,IAAI,EAAE,CAAC,CAAC,WAAW,EAAE,KAAK,cAAc,CAAC,CAAC;IACnF,MAAM,OAAO,GAAG,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;IACrE,MAAM,KAAK,GAAG,OAAO,EAAE,KAAK,CAAC,mBAAmB,CAAC,CAAC;IAClD,OAAO,KAAK,EAAE,CAAC,CAAC,CAAC,IAAI,IAAI,CAAC;AAC5B,CAAC;AAED,SAAS,WAAW,CAAC,CAAa;IAChC,MAAM,IAAI,GAAG,CAAC,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,CAAC;IAC/B,IAAI,CAAC,IAAI,CAAC,sDAAsD,CAAC,CAAC,MAAM,EAAE,CAAC;IAC3E,yDAAyD;IACzD,IAAI,CAAC,IAAI,CAAC,gIAAgI,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,EAAE;QACzJ,CAAC,CAAC,EAAE,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;IACjC,CAAC,CAAC,CAAC;IACH,OAAO,kBAAkB,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC,CAAC;AACzC,CAAC"}
+{"version":3,"file":"extract.js","sourceRoot":"","sources":["../../../src/core/html/extract.ts"],"names":[],"mappings":"AAOA,OAAO,EAAE,UAAU,EAAE,UAAU,EAAE,MAAM,EAAE,MAAM,WAAW,CAAC;AAC3D,OAAO,EAAE,oBAAoB,EAAE,MAAM,aAAa,CAAC;AACnD,OAAO,EACL,IAAI,EACJ,aAAa,EACb,QAAQ,EACR,QAAQ,EACR,IAAI,EACJ,WAAW,GACZ,MAAM,UAAU,CAAC;AAElB,OAAO,EAAE,qBAAqB,EAAE,MAAM,sBAAsB,CAAC;AAC7D,OAAO,EAAE,kBAAkB,EAAE,SAAS,EAAE,MAAM,WAAW,CAAC;AAW1D,MAAM,OAAO,GAAG,CAAC,GAA8B,EAAY,EAAE,CAC3D,CAAC,GAAG,IAAI,EAAE,CAAC,CAAC,WAAW,EAAE,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC;AAE1D,MAAM,UAAU,GAAG,CAAC,KAAyB,EAAiB,EAAE,CAC9D,KAAK,EAAE,IAAI,EAAE,IAAI,IAAI,CAAC;AAExB,MAAM,aAAa,GAAG,CAAC,MAAgB,EAAiB,EAAE;IACxD,KAAK,MAAM,CAAC,IAAI,MAAM,EAAE,CAAC;QACvB,IAAI,CAAC,EAAE,CAAC;YACN,OAAO,CAAC,CAAC;QACX,CAAC;IACH,CAAC;IAED,OAAO,IAAI,CAAC;AACd,CAAC,CAAC;AAEF,MAAM,aAAa,GAAG,CAAC,GAAa,EAAiB,EAAE;IACrD,MAAM,WAAW,GAAG,QAAQ,CAAC,GAAG,EAAE,eAAe,CAAC,CAAC;IACnD,MAAM,MAAM,GAAG,WAAW,CAAC,CAAC,CAAC,IAAI,CAAC,WAAW,EAAE,SAAS,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;IAEtE,IAAI,MAAM,EAAE,CAAC;QACX,OAAO,MAAM,CAAC,IAAI,EAAE,CAAC;IACvB,CAAC;IAED,MAAM,SAAS,GAAG,QAAQ,CAAC,GAAG,EAAE,kBAAkB,CAAC,CAAC,IAAI,CACtD,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,IAAI,CAAC,EAAE,EAAE,YAAY,CAAC,IAAI,EAAE,CAAC,CAAC,WAAW,EAAE,KAAK,cAAc,CACxE,CAAC;IAEF,MAAM,OAAO,GAAG,SAAS,CAAC,CAAC,CAAC,IAAI,CAAC,SAAS,EAAE,SAAS,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;IACnE,MAAM,KAAK,GAAG,OAAO,EAAE,KAAK,CAAC,8BAA8B,CAAC,CAAC;IAE7D,OAAO,KAAK,EAAE,MAAM,EAAE,OAAO,IAAI,IAAI,CAAC;AACxC,CAAC,CAAC;AAEF,MAAM,CAAC,MAAM,WAAW,GAAG,CACzB,IAAY,EACZ,OAAuB,EACR,EAAE;IACjB,MAAM,GAAG,GAAG,aAAa,CAAC,IAAI,CAAC,CAAC;IAChC,MAAM,UAAU,GAAG,wBAAwB,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IACvD,MAAM,MAAM,GAAG,QAAQ,CAAC,GAAG,EAAE,YAAY,CAAC,CAAC;IAC3C,MAAM,QAAQ,GAAG,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;IAC3D,MAAM,IAAI,GAAG,CAAC,QAAQ,IAAI,UAAU,CAAC,QAAQ,EAAE,OAAO,CAAC,GAAG,CAAC,CAAC,IAAI,OAAO,CAAC,GAAG,CAAC;IAC5E,MAAM,QAAQ,GAAG,OAAO,CAAC,QAAQ,IAAI,MAAM,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC;IAE/D,MAAM,MAAM,GAAG,QAAQ,CAAC,GAAG,EAAE,OAAO,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE,CAC/C,kBAAkB,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAC7B,CAAC;IAEF,MAAM,gBAAgB,GAAG,QAAQ,CAAC,GAAG,EAAE,YAAY,CAAC;SACjD,MAAM,CACL,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,IAAI,CAAC,EAAE,EAAE,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,KAAK,aAAa,CACxE;SACA,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,kBAAkB,CAAC,IAAI,CAAC,EAAE,EAAE,SAAS,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC;IAE9D,MAAM,UAAU,GAAG,QAAQ,CAAC,GAAG,EAAE,YAAY,CAAC;SAC3C,MAAM,CAAC,CAAC,EAAE,EAAE,EAAE,CACb,CAAC,QAAQ,EAAE,WAAW,EAAE,gBAAgB,EAAE,SAAS,CAAC,CAAC,QAAQ,CAC3D,CAAC,IAAI,CAAC,EAAE,EAAE,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAC9C,CACF;SACA,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,kBAAkB,CAAC,IAAI,CAAC,EAAE,EAAE,SAAS,CAAC,IAAI,EAAE,CAAC,CAAC,WAAW,EAAE,CAAC;SACxE,MAAM,CAAC,OAAO,CAAC,CAAC;IAEnB,MAAM,UAAU,GAAG,QAAQ,CAAC,GAAG,EAAE,WAAW,CAAC;SAC1C,MAAM,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,OAAO,CAAC,IAAI,CAAC,EAAE,EAAE,KAAK,CAAC,CAAC,CAAC,QAAQ,CAAC,WAAW,CAAC,CAAC;SAC9D,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,IAAI,CAAC,EAAE,EAAE,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC;IAEhD,MAAM,QAAQ,GAAkB,QAAQ,CAAC,GAAG,EAAE,wBAAwB,CAAC,CAAC,GAAG,CACzE,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC;QACP,KAAK,EAAE,MAAM,CAAC,EAAE,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;QAC/B,IAAI,EAAE,kBAAkB,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;KACnC,CAAC,CACH,CAAC;IAEF,MAAM,EAAE,GAA2B,EAAE,CAAC;IACtC,MAAM,OAAO,GAA2B,EAAE,CAAC;IAE3C,KAAK,MAAM,EAAE,IAAI,QAAQ,CAAC,GAAG,EAAE,4BAA4B,CAAC,EAAE,CAAC;QAC7D,MAAM,GAAG,GAAG,CAAC,IAAI,CAAC,EAAE,EAAE,UAAU,CAAC,IAAI,IAAI,CAAC,EAAE,EAAE,MAAM,CAAC,IAAI,EAAE,CAAC;aACzD,IAAI,EAAE;aACN,WAAW,EAAE,CAAC;QAEjB,MAAM,OAAO,GAAG,kBAAkB,CAAC,IAAI,CAAC,EAAE,EAAE,SAAS,CAAC,IAAI,EAAE,CAAC,CAAC;QAE9D,IAAI,CAAC,GAAG,EAAE,CAAC;YACT,SAAS;QACX,CAAC;QAED,IAAI,GAAG,CAAC,UAAU,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,GAAG,IAAI,EAAE,CAAC,EAAE,CAAC;YAC1C,EAAE,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,GAAG,OAAO,CAAC;QAC7B,CAAC;aAAM,IAAI,GAAG,CAAC,UAAU,CAAC,UAAU,CAAC,IAAI,CAAC,CAAC,GAAG,IAAI,OAAO,CAAC,EAAE,CAAC;YAC3D,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,GAAG,OAAO,CAAC;QAClC,CAAC;IACH,CAAC;IAED,MAAM,MAAM,GAAgB,QAAQ,CAAC,GAAG,EAAE,KAAK,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC;QAC5D,GAAG,EAAE,IAAI,CAAC,EAAE,EAAE,KAAK,CAAC,IAAI,IAAI,CAAC,EAAE,EAAE,UAAU,CAAC,IAAI,IAAI;QACpD,GAAG,EAAE,IAAI,CAAC,EAAE,EAAE,KAAK,CAAC,IAAI,IAAI;QAC5B,KAAK,EAAE,IAAI,CAAC,EAAE,EAAE,OAAO,CAAC,IAAI,IAAI;QAChC,MAAM,EAAE,IAAI,CAAC,EAAE,EAAE,QAAQ,CAAC,IAAI,IAAI;QAClC,OAAO,EAAE,IAAI,CAAC,EAAE,EAAE,SAAS,CAAC,IAAI,IAAI;KACrC,CAAC,CAAC,CAAC;IAEJ,MAAM,KAAK,GAAe,QAAQ,CAAC,GAAG,EAAE,SAAS,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE;QAC5D,MAAM,IAAI,GAAG,CAAC,IAAI,CAAC,EAAE,EAAE,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC;QAE7C,kEAAkE;QAClE,MAAM,GAAG,GACP,IAAI,KAAK,EAAE,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,UAAU,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;QAEtE,MAAM,GAAG,GAAG,IAAI,CAAC,EAAE,EAAE,KAAK,CAAC,IAAI,IAAI,CAAC;QACpC,MAAM,SAAS,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC;QAC/B,MAAM,QAAQ,GAAG,kBAAkB,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;QAC9C,MAAM,SAAS,GAAG,kBAAkB,CAAC,IAAI,CAAC,EAAE,EAAE,YAAY,CAAC,IAAI,EAAE,CAAC,CAAC;QACnE,MAAM,KAAK,GAAG,kBAAkB,CAAC,IAAI,CAAC,EAAE,EAAE,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC;QAE1D,MAAM,MAAM,GAAG,QAAQ,CAAC,EAAE,EAAE,UAAU,CAAC;aACpC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,kBAAkB,CAAC,IAAI,CAAC,GAAG,EAAE,KAAK,CAAC,IAAI,EAAE,CAAC,CAAC;aACxD,IAAI,CAAC,OAAO,CAAC,CAAC;QAEjB,OAAO;YACL,IAAI;YACJ,GAAG;YACH,IAAI,EAAE,QAAQ;YACd,GAAG;YACH,QAAQ,EAAE,GAAG;gBACX,CAAC,CAAC,UAAU,CAAC,GAAG,EAAE,QAAQ,EAAE,OAAO,CAAC,iBAAiB,CAAC;gBACtD,CAAC,CAAC,KAAK;YACT,QAAQ,EAAE,SAAS,CAAC,QAAQ,CAAC,UAAU,CAAC;YACxC,iBAAiB,EAAE,OAAO,CAAC,QAAQ,IAAI,SAAS,IAAI,KAAK,IAAI,MAAM,CAAC;SACrE,CAAC;IACJ,CAAC,CAAC,CAAC;IAEH,MAAM,QAAQ,GAAmB,QAAQ,CAAC,GAAG,EAAE,WAAW,CAAC;SACxD,MAAM,CACL,CAAC,EAAE,EAAE,EAAE,CACL,OAAO,CAAC,IAAI,CAAC,EAAE,EAAE,KAAK,CAAC,CAAC,CAAC,QAAQ,CAAC,WAAW,CAAC,IAAI,IAAI,CAAC,EAAE,EAAE,UAAU,CAAC,CACzE;SACA,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE;QACV,MAAM,IAAI,GAAG,CAAC,IAAI,CAAC,EAAE,EAAE,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC;QAE7C,OAAO;YACL,IAAI,EAAE,CAAC,IAAI,CAAC,EAAE,EAAE,UAAU,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE;YACzC,IAAI;YACJ,GAAG,EAAE,UAAU,CAAC,IAAI,EAAE,IAAI,CAAC;SAC5B,CAAC;IACJ,CAAC,CAAC,CAAC;IAEL,MAAM,UAAU,GAAG,qBAAqB,CAAC,GAAG,CAAC,CAAC;IAE9C,MAAM,IAAI,GAAG,QAAQ,CAAC,GAAG,EAAE,MAAM,CAAC,CAAC;IACnC,MAAM,QAAQ,GAAG,IAAI,CAAC,CAAC,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;IAE/C,MAAM,MAAM,GAAG,QAAQ,CAAC,GAAG,EAAE,MAAM,CAAC,CAAC;IACrC,MAAM,UAAU,GAAG,QAAQ,CAAC,GAAG,EAAE,yBAAyB,CAAC,CAAC;IAE5D,OAAO;QACL,GAAG,EAAE,OAAO,CAAC,GAAG;QAChB,UAAU;QACV,IAAI,EAAE,UAAU,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QAC3D,OAAO,EAAE,aAAa,CAAC,GAAG,CAAC;QAC3B,QAAQ,EAAE,UAAU,CAAC,UAAU,CAAC,CAAC,CAAC,IAAI,CAAC,UAAU,EAAE,SAAS,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;QAC1E,MAAM;QACN,KAAK,EAAE,aAAa,CAAC,MAAM,CAAC;QAC5B,gBAAgB;QAChB,eAAe,EAAE,aAAa,CAAC,gBAAgB,CAAC;QAChD,UAAU;QACV,UAAU;QACV,SAAS,EAAE,UAAU,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,UAAU,CAAC,UAAU,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI;QACjE,QAAQ;QACR,GAAG,EAAE,QAAQ,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,KAAK,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;QAC7D,EAAE;QACF,OAAO;QACP,MAAM;QACN,KAAK;QACL,QAAQ;QACR,cAAc,EAAE,UAAU,CAAC,KAAK;QAChC,oBAAoB,EAAE,UAAU,CAAC,MAAM;QACvC,IAAI,EAAE,QAAQ;QACd,SAAS,EAAE,SAAS,CAAC,QAAQ,CAAC;QAC9B,SAAS,EAAE,MAAM,CAAC,UAAU,CAAC,IAAI,EAAE,OAAO,CAAC;QAC3C,WAAW,EAAE,OAAO,CAAC,QAAQ,CAAC;QAC9B,MAAM,EAAE,oBAAoB,CAAC,GAAG,EAAE,QAAQ,CAAC;KAC5C,CAAC;AACJ,CAAC,CAAC"}

package/dist/core/html/structured-data.d.ts

@@ -1,11 +1,21 @@
-import type { CheerioAPI } from 'cheerio';
-import type { StructuredDataError, StructuredDataItem } from '../types.js';
+import type { StructuredDataError, StructuredDataItem } from "../types.js";
+import type { Document } from "./dom.js";
+/** A value JSON.parse returns: all that a JSON-LD block or a microdata item can hold. */
+export type JsonValue = string | number | boolean | null | JsonValue[] | JsonObject;
+/** A JSON-LD node or a microdata item: whatever properties the page gave it. */
+export interface JsonObject {
+    [property: string]: JsonValue;
+}
+/** Whether a structured-data value is a string. */
+export declare const isString: (value: JsonValue | undefined) => value is string;
+/** Whether a structured-data value is an object with properties, rather than a list or a scalar. */
+export declare const isJsonObject: (value: JsonValue | undefined) => value is JsonObject;
 export interface StructuredDataExtraction {
     items: StructuredDataItem[];
     errors: StructuredDataError[];
 }
-export declare function extractStructuredData($: CheerioAPI): StructuredDataExtraction;
-export declare function contextString(value: unknown): string | null;
-export declare function typesOf(value: unknown): string[];
 /** `https://schema.org/Article` -> `Article`, `schema:Article` -> `Article`. */
-export declare function shortType(type: string): string;
+export declare const shortType: (type: string) => string;
+export declare const contextString: (value: JsonValue | undefined) => string | null;
+export declare const typesOf: (value: JsonValue | undefined) => string[];
+export declare const extractStructuredData: (doc: Document) => StructuredDataExtraction;