@rivi-software/agentic-seo-check 0.1.0 → 0.1.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/LICENSE +1 -1
- package/README.md +65 -15
- package/dist/brand.d.ts +11 -0
- package/dist/brand.js +22 -0
- package/dist/brand.js.map +1 -0
- package/dist/cli.js +125 -80
- package/dist/cli.js.map +1 -1
- package/dist/core/audit.d.ts +16 -16
- package/dist/core/audit.js +363 -248
- package/dist/core/audit.js.map +1 -1
- package/dist/core/concurrency.d.ts +4 -4
- package/dist/core/concurrency.js +33 -23
- package/dist/core/concurrency.js.map +1 -1
- package/dist/core/crawl.d.ts +5 -5
- package/dist/core/crawl.js +250 -121
- package/dist/core/crawl.js.map +1 -1
- package/dist/core/fetch.d.ts +5 -5
- package/dist/core/fetch.js +151 -100
- package/dist/core/fetch.js.map +1 -1
- package/dist/core/html/dom.d.ts +13 -0
- package/dist/core/html/dom.js +17 -0
- package/dist/core/html/dom.js.map +1 -0
- package/dist/core/html/extract.d.ts +2 -2
- package/dist/core/html/extract.js +168 -111
- package/dist/core/html/extract.js.map +1 -1
- package/dist/core/html/structured-data.d.ts +16 -6
- package/dist/core/html/structured-data.js +180 -145
- package/dist/core/html/structured-data.js.map +1 -1
- package/dist/core/html/text.d.ts +14 -14
- package/dist/core/html/text.js +110 -107
- package/dist/core/html/text.js.map +1 -1
- package/dist/core/lighthouse.d.ts +26 -25
- package/dist/core/lighthouse.js +181 -105
- package/dist/core/lighthouse.js.map +1 -1
- package/dist/core/performance-rules.d.ts +2 -2
- package/dist/core/performance-rules.js +105 -33
- package/dist/core/performance-rules.js.map +1 -1
- package/dist/core/render-rules.d.ts +5 -4
- package/dist/core/render-rules.js +129 -62
- package/dist/core/render-rules.js.map +1 -1
- package/dist/core/render.d.ts +2 -2
- package/dist/core/render.js +29 -23
- package/dist/core/render.js.map +1 -1
- package/dist/core/report/markdown.d.ts +2 -2
- package/dist/core/report/markdown.js +110 -131
- package/dist/core/report/markdown.js.map +1 -1
- package/dist/core/robots.d.ts +5 -5
- package/dist/core/robots.js +31 -16
- package/dist/core/robots.js.map +1 -1
- package/dist/core/rules/canonical.d.ts +1 -1
- package/dist/core/rules/canonical.js +93 -57
- package/dist/core/rules/canonical.js.map +1 -1
- package/dist/core/rules/content.js +40 -26
- package/dist/core/rules/content.js.map +1 -1
- package/dist/core/rules/document.js +64 -41
- package/dist/core/rules/document.js.map +1 -1
- package/dist/core/rules/headings.js +58 -38
- package/dist/core/rules/headings.js.map +1 -1
- package/dist/core/rules/hreflang.js +70 -38
- package/dist/core/rules/hreflang.js.map +1 -1
- package/dist/core/rules/images.js +44 -26
- package/dist/core/rules/images.js.map +1 -1
- package/dist/core/rules/index.d.ts +6 -6
- package/dist/core/rules/index.js +36 -35
- package/dist/core/rules/index.js.map +1 -1
- package/dist/core/rules/indexing.d.ts +2 -2
- package/dist/core/rules/indexing.js +48 -26
- package/dist/core/rules/indexing.js.map +1 -1
- package/dist/core/rules/keyword.js +84 -47
- package/dist/core/rules/keyword.js.map +1 -1
- package/dist/core/rules/links.js +72 -37
- package/dist/core/rules/links.js.map +1 -1
- package/dist/core/rules/meta.js +55 -34
- package/dist/core/rules/meta.js.map +1 -1
- package/dist/core/rules/response.js +75 -41
- package/dist/core/rules/response.js.map +1 -1
- package/dist/core/rules/rule.d.ts +6 -6
- package/dist/core/rules/rule.js +36 -36
- package/dist/core/rules/rule.js.map +1 -1
- package/dist/core/rules/social.js +86 -45
- package/dist/core/rules/social.js.map +1 -1
- package/dist/core/rules/structured-data.d.ts +6 -4
- package/dist/core/rules/structured-data.js +314 -102
- package/dist/core/rules/structured-data.js.map +1 -1
- package/dist/core/rules/title.js +48 -33
- package/dist/core/rules/title.js.map +1 -1
- package/dist/core/score.d.ts +3 -3
- package/dist/core/score.js +11 -9
- package/dist/core/score.js.map +1 -1
- package/dist/core/site-rules.d.ts +3 -3
- package/dist/core/site-rules.js +409 -198
- package/dist/core/site-rules.js.map +1 -1
- package/dist/core/sitemap.d.ts +5 -5
- package/dist/core/sitemap.js +109 -64
- package/dist/core/sitemap.js.map +1 -1
- package/dist/core/static.d.ts +2 -2
- package/dist/core/static.js +209 -112
- package/dist/core/static.js.map +1 -1
- package/dist/core/summary.d.ts +2 -2
- package/dist/core/summary.js +11 -6
- package/dist/core/summary.js.map +1 -1
- package/dist/core/types.d.ts +14 -14
- package/dist/core/types.js +15 -8
- package/dist/core/types.js.map +1 -1
- package/dist/core/url.d.ts +11 -11
- package/dist/core/url.js +122 -70
- package/dist/core/url.js.map +1 -1
- package/dist/index.d.ts +11 -11
- package/dist/index.js +9 -9
- package/dist/index.js.map +1 -1
- package/dist/mcp-bin.js +7 -4
- package/dist/mcp-bin.js.map +1 -1
- package/dist/mcp.d.ts +3 -3
- package/dist/mcp.js +312 -122
- package/dist/mcp.js.map +1 -1
- package/dist/version.d.ts +0 -1
- package/dist/version.js +4 -2
- package/dist/version.js.map +1 -1
- package/package.json +27 -9
|
@@ -1,94 +1,187 @@
|
|
|
1
|
-
import {
|
|
2
|
-
import { isSameSite, resolveUrl, hostOf } from
|
|
3
|
-
import {
|
|
4
|
-
import { extractStructuredData } from
|
|
5
|
-
|
|
6
|
-
|
|
7
|
-
|
|
8
|
-
|
|
1
|
+
import { isTag, isText, hasChildren } from "domhandler";
|
|
2
|
+
import { isSameSite, resolveUrl, hostOf } from "../url.js";
|
|
3
|
+
import { attr, parseDocument, queryAll, queryOne, text } from "./dom.js";
|
|
4
|
+
import { extractStructuredData } from "./structured-data.js";
|
|
5
|
+
import { collapseWhitespace, wordCount } from "./text.js";
|
|
6
|
+
const relList = (rel) => (rel ?? "").toLowerCase().split(/\s+/u).filter(Boolean);
|
|
7
|
+
const attrOrNull = (value) => value?.trim() || null;
|
|
8
|
+
const firstNonEmpty = (values) => {
|
|
9
|
+
for (const v of values) {
|
|
10
|
+
if (v) {
|
|
11
|
+
return v;
|
|
12
|
+
}
|
|
13
|
+
}
|
|
14
|
+
return null;
|
|
15
|
+
};
|
|
16
|
+
const detectCharset = (doc) => {
|
|
17
|
+
const metaCharset = queryOne(doc, "meta[charset]");
|
|
18
|
+
const direct = metaCharset ? attr(metaCharset, "charset") : undefined;
|
|
19
|
+
if (direct) {
|
|
20
|
+
return direct.trim();
|
|
21
|
+
}
|
|
22
|
+
const httpEquiv = queryAll(doc, "meta[http-equiv]").find((el) => (attr(el, "http-equiv") ?? "").toLowerCase() === "content-type");
|
|
23
|
+
const content = httpEquiv ? attr(httpEquiv, "content") : undefined;
|
|
24
|
+
const match = content?.match(/charset=(?<charset>[\w-]+)/iu);
|
|
25
|
+
return match?.groups?.charset ?? null;
|
|
26
|
+
};
|
|
27
|
+
/** Elements whose content is never visible page text. */
|
|
28
|
+
const HIDDEN_ELEMENTS = new Set([
|
|
29
|
+
"script",
|
|
30
|
+
"style",
|
|
31
|
+
"noscript",
|
|
32
|
+
"template",
|
|
33
|
+
"svg",
|
|
34
|
+
"iframe",
|
|
35
|
+
"head",
|
|
36
|
+
]);
|
|
37
|
+
/** Elements that break words apart; padded with spaces so adjacent words don't fuse. */
|
|
38
|
+
const BLOCK_ELEMENTS = new Set([
|
|
39
|
+
"p",
|
|
40
|
+
"div",
|
|
41
|
+
"li",
|
|
42
|
+
"h1",
|
|
43
|
+
"h2",
|
|
44
|
+
"h3",
|
|
45
|
+
"h4",
|
|
46
|
+
"h5",
|
|
47
|
+
"h6",
|
|
48
|
+
"br",
|
|
49
|
+
"tr",
|
|
50
|
+
"td",
|
|
51
|
+
"th",
|
|
52
|
+
"section",
|
|
53
|
+
"article",
|
|
54
|
+
"header",
|
|
55
|
+
"footer",
|
|
56
|
+
"nav",
|
|
57
|
+
"blockquote",
|
|
58
|
+
"pre",
|
|
59
|
+
"dd",
|
|
60
|
+
"dt",
|
|
61
|
+
"figcaption",
|
|
62
|
+
]);
|
|
63
|
+
const visibleText = (doc) => {
|
|
64
|
+
const body = queryOne(doc, "body");
|
|
65
|
+
if (!body) {
|
|
66
|
+
return "";
|
|
67
|
+
}
|
|
68
|
+
const parts = [];
|
|
69
|
+
const walk = (nodes) => {
|
|
70
|
+
for (const node of nodes) {
|
|
71
|
+
if (isText(node)) {
|
|
72
|
+
parts.push(node.data);
|
|
73
|
+
}
|
|
74
|
+
else if (isTag(node)) {
|
|
75
|
+
if (HIDDEN_ELEMENTS.has(node.name)) {
|
|
76
|
+
continue;
|
|
77
|
+
}
|
|
78
|
+
const block = BLOCK_ELEMENTS.has(node.name);
|
|
79
|
+
if (block) {
|
|
80
|
+
parts.push(" ");
|
|
81
|
+
}
|
|
82
|
+
walk(node.children);
|
|
83
|
+
if (block) {
|
|
84
|
+
parts.push(" ");
|
|
85
|
+
}
|
|
86
|
+
}
|
|
87
|
+
else if (hasChildren(node)) {
|
|
88
|
+
walk(node.children);
|
|
89
|
+
}
|
|
90
|
+
}
|
|
91
|
+
};
|
|
92
|
+
walk(body.children);
|
|
93
|
+
return collapseWhitespace(parts.join(""));
|
|
94
|
+
};
|
|
95
|
+
export const extractPage = (html, options) => {
|
|
96
|
+
const doc = parseDocument(html);
|
|
97
|
+
const hasDoctype = /^\s*<!doctype\s+html/iu.test(html);
|
|
98
|
+
const baseEl = queryOne(doc, "base[href]");
|
|
99
|
+
const baseHref = baseEl ? attr(baseEl, "href") : undefined;
|
|
9
100
|
const base = (baseHref && resolveUrl(baseHref, options.url)) || options.url;
|
|
10
|
-
const siteHost = options.siteHost ?? hostOf(options.url) ??
|
|
11
|
-
const titles =
|
|
12
|
-
|
|
13
|
-
.
|
|
14
|
-
|
|
15
|
-
|
|
16
|
-
.filter((el) => (
|
|
17
|
-
.map((el) => collapseWhitespace(
|
|
18
|
-
const metaRobots = $('meta[name]')
|
|
19
|
-
.toArray()
|
|
20
|
-
.filter((el) => ['robots', 'googlebot', 'googlebot-news', 'bingbot'].includes(($(el).attr('name') ?? '').trim().toLowerCase()))
|
|
21
|
-
.map((el) => collapseWhitespace($(el).attr('content') ?? '').toLowerCase())
|
|
101
|
+
const siteHost = options.siteHost ?? hostOf(options.url) ?? "";
|
|
102
|
+
const titles = queryAll(doc, "title").map((el) => collapseWhitespace(text(el)));
|
|
103
|
+
const metaDescriptions = queryAll(doc, "meta[name]")
|
|
104
|
+
.filter((el) => (attr(el, "name") ?? "").trim().toLowerCase() === "description")
|
|
105
|
+
.map((el) => collapseWhitespace(attr(el, "content") ?? ""));
|
|
106
|
+
const metaRobots = queryAll(doc, "meta[name]")
|
|
107
|
+
.filter((el) => ["robots", "googlebot", "googlebot-news", "bingbot"].includes((attr(el, "name") ?? "").trim().toLowerCase()))
|
|
108
|
+
.map((el) => collapseWhitespace(attr(el, "content") ?? "").toLowerCase())
|
|
22
109
|
.filter(Boolean);
|
|
23
|
-
const canonicals =
|
|
24
|
-
.
|
|
25
|
-
.
|
|
26
|
-
|
|
27
|
-
|
|
28
|
-
|
|
29
|
-
|
|
110
|
+
const canonicals = queryAll(doc, "link[rel]")
|
|
111
|
+
.filter((el) => relList(attr(el, "rel")).includes("canonical"))
|
|
112
|
+
.map((el) => (attr(el, "href") ?? "").trim());
|
|
113
|
+
const headings = queryAll(doc, "h1, h2, h3, h4, h5, h6").map((el) => ({
|
|
114
|
+
level: Number(el.name.slice(1)),
|
|
115
|
+
text: collapseWhitespace(text(el)),
|
|
116
|
+
}));
|
|
30
117
|
const og = {};
|
|
31
118
|
const twitter = {};
|
|
32
|
-
|
|
33
|
-
const key = (
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
|
|
37
|
-
if (key
|
|
119
|
+
for (const el of queryAll(doc, "meta[property], meta[name]")) {
|
|
120
|
+
const key = (attr(el, "property") ?? attr(el, "name") ?? "")
|
|
121
|
+
.trim()
|
|
122
|
+
.toLowerCase();
|
|
123
|
+
const content = collapseWhitespace(attr(el, "content") ?? "");
|
|
124
|
+
if (!key) {
|
|
125
|
+
continue;
|
|
126
|
+
}
|
|
127
|
+
if (key.startsWith("og:") && !(key in og)) {
|
|
38
128
|
og[key.slice(3)] = content;
|
|
39
|
-
|
|
129
|
+
}
|
|
130
|
+
else if (key.startsWith("twitter:") && !(key in twitter)) {
|
|
40
131
|
twitter[key.slice(8)] = content;
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
|
|
46
|
-
|
|
47
|
-
|
|
48
|
-
|
|
49
|
-
loading: $(el).attr('loading') ?? null,
|
|
132
|
+
}
|
|
133
|
+
}
|
|
134
|
+
const images = queryAll(doc, "img").map((el) => ({
|
|
135
|
+
src: attr(el, "src") ?? attr(el, "data-src") ?? null,
|
|
136
|
+
alt: attr(el, "alt") ?? null,
|
|
137
|
+
width: attr(el, "width") ?? null,
|
|
138
|
+
height: attr(el, "height") ?? null,
|
|
139
|
+
loading: attr(el, "loading") ?? null,
|
|
50
140
|
}));
|
|
51
|
-
const links =
|
|
52
|
-
.
|
|
53
|
-
.map((el) => {
|
|
54
|
-
const href = ($(el).attr('href') ?? '').trim();
|
|
141
|
+
const links = queryAll(doc, "a[href]").map((el) => {
|
|
142
|
+
const href = (attr(el, "href") ?? "").trim();
|
|
55
143
|
// Fragment-only and empty hrefs are not links to other documents.
|
|
56
|
-
const url = href ===
|
|
57
|
-
const rel =
|
|
144
|
+
const url = href === "" || href.startsWith("#") ? null : resolveUrl(href, base);
|
|
145
|
+
const rel = attr(el, "rel") ?? null;
|
|
58
146
|
const relTokens = relList(rel);
|
|
59
|
-
const
|
|
60
|
-
const ariaLabel = collapseWhitespace(
|
|
61
|
-
const title = collapseWhitespace(
|
|
62
|
-
const imgAlt =
|
|
63
|
-
.
|
|
64
|
-
.toArray()
|
|
65
|
-
.map((img) => collapseWhitespace($(img).attr('alt') ?? ''))
|
|
147
|
+
const linkText = collapseWhitespace(text(el));
|
|
148
|
+
const ariaLabel = collapseWhitespace(attr(el, "aria-label") ?? "");
|
|
149
|
+
const title = collapseWhitespace(attr(el, "title") ?? "");
|
|
150
|
+
const imgAlt = queryAll(el, "img[alt]")
|
|
151
|
+
.map((img) => collapseWhitespace(attr(img, "alt") ?? ""))
|
|
66
152
|
.find(Boolean);
|
|
67
153
|
return {
|
|
68
154
|
href,
|
|
69
155
|
url,
|
|
70
|
-
text,
|
|
156
|
+
text: linkText,
|
|
71
157
|
rel,
|
|
72
|
-
internal: url
|
|
73
|
-
|
|
74
|
-
|
|
158
|
+
internal: url
|
|
159
|
+
? isSameSite(url, siteHost, options.includeSubdomains)
|
|
160
|
+
: false,
|
|
161
|
+
nofollow: relTokens.includes("nofollow"),
|
|
162
|
+
hasAccessibleName: Boolean(linkText || ariaLabel || title || imgAlt),
|
|
75
163
|
};
|
|
76
164
|
});
|
|
77
|
-
const hreflang =
|
|
78
|
-
.
|
|
79
|
-
.filter((el) => relList($(el).attr('rel')).includes('alternate') && $(el).attr('hreflang'))
|
|
165
|
+
const hreflang = queryAll(doc, "link[rel]")
|
|
166
|
+
.filter((el) => relList(attr(el, "rel")).includes("alternate") && attr(el, "hreflang"))
|
|
80
167
|
.map((el) => {
|
|
81
|
-
const href = (
|
|
82
|
-
return {
|
|
168
|
+
const href = (attr(el, "href") ?? "").trim();
|
|
169
|
+
return {
|
|
170
|
+
lang: (attr(el, "hreflang") ?? "").trim(),
|
|
171
|
+
href,
|
|
172
|
+
url: resolveUrl(href, base),
|
|
173
|
+
};
|
|
83
174
|
});
|
|
84
|
-
const structured = extractStructuredData(
|
|
85
|
-
const
|
|
175
|
+
const structured = extractStructuredData(doc);
|
|
176
|
+
const bodyText = visibleText(doc);
|
|
177
|
+
const htmlEl = queryOne(doc, "html");
|
|
178
|
+
const viewportEl = queryOne(doc, 'meta[name="viewport" i]');
|
|
86
179
|
return {
|
|
87
180
|
url: options.url,
|
|
88
181
|
hasDoctype,
|
|
89
|
-
lang: attrOrNull(
|
|
90
|
-
charset: detectCharset(
|
|
91
|
-
viewport: attrOrNull(
|
|
182
|
+
lang: attrOrNull(htmlEl ? attr(htmlEl, "lang") : undefined),
|
|
183
|
+
charset: detectCharset(doc),
|
|
184
|
+
viewport: attrOrNull(viewportEl ? attr(viewportEl, "content") : undefined),
|
|
92
185
|
titles,
|
|
93
186
|
title: firstNonEmpty(titles),
|
|
94
187
|
metaDescriptions,
|
|
@@ -97,7 +190,7 @@ export function extractPage(html, options) {
|
|
|
97
190
|
canonicals,
|
|
98
191
|
canonical: canonicals[0] ? resolveUrl(canonicals[0], base) : null,
|
|
99
192
|
headings,
|
|
100
|
-
h1s: headings.
|
|
193
|
+
h1s: headings.flatMap((h) => (h.level === 1 ? [h.text] : [])),
|
|
101
194
|
og,
|
|
102
195
|
twitter,
|
|
103
196
|
images,
|
|
@@ -105,46 +198,10 @@ export function extractPage(html, options) {
|
|
|
105
198
|
hreflang,
|
|
106
199
|
structuredData: structured.items,
|
|
107
200
|
structuredDataErrors: structured.errors,
|
|
108
|
-
text,
|
|
109
|
-
wordCount: wordCount(
|
|
110
|
-
htmlBytes: Buffer.byteLength(html,
|
|
201
|
+
text: bodyText,
|
|
202
|
+
wordCount: wordCount(bodyText),
|
|
203
|
+
htmlBytes: Buffer.byteLength(html, "utf-8"),
|
|
111
204
|
hasBaseHref: Boolean(baseHref),
|
|
112
205
|
};
|
|
113
|
-
}
|
|
114
|
-
function relList(rel) {
|
|
115
|
-
return (rel ?? '')
|
|
116
|
-
.toLowerCase()
|
|
117
|
-
.split(/\s+/)
|
|
118
|
-
.filter(Boolean);
|
|
119
|
-
}
|
|
120
|
-
function attrOrNull(value) {
|
|
121
|
-
const v = value?.trim();
|
|
122
|
-
return v ? v : null;
|
|
123
|
-
}
|
|
124
|
-
function firstNonEmpty(values) {
|
|
125
|
-
for (const v of values)
|
|
126
|
-
if (v)
|
|
127
|
-
return v;
|
|
128
|
-
return null;
|
|
129
|
-
}
|
|
130
|
-
function detectCharset($) {
|
|
131
|
-
const direct = $('meta[charset]').first().attr('charset');
|
|
132
|
-
if (direct)
|
|
133
|
-
return direct.trim();
|
|
134
|
-
const httpEquiv = $('meta[http-equiv]')
|
|
135
|
-
.toArray()
|
|
136
|
-
.find((el) => ($(el).attr('http-equiv') ?? '').toLowerCase() === 'content-type');
|
|
137
|
-
const content = httpEquiv ? $(httpEquiv).attr('content') : undefined;
|
|
138
|
-
const match = content?.match(/charset=([\w-]+)/i);
|
|
139
|
-
return match?.[1] ?? null;
|
|
140
|
-
}
|
|
141
|
-
function visibleText($) {
|
|
142
|
-
const body = $('body').clone();
|
|
143
|
-
body.find('script, style, noscript, template, svg, iframe, head').remove();
|
|
144
|
-
// Insert spaces at block boundaries so words don't fuse.
|
|
145
|
-
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) => {
|
|
146
|
-
$(el).prepend(' ').append(' ');
|
|
147
|
-
});
|
|
148
|
-
return collapseWhitespace(body.text());
|
|
149
|
-
}
|
|
206
|
+
};
|
|
150
207
|
//# sourceMappingURL=extract.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"extract.js","sourceRoot":"","sources":["../../../src/core/html/extract.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"extract.js","sourceRoot":"","sources":["../../../src/core/html/extract.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,KAAK,EAAE,MAAM,EAAE,WAAW,EAAE,MAAM,YAAY,CAAC;AASxD,OAAO,EAAE,UAAU,EAAE,UAAU,EAAE,MAAM,EAAE,MAAM,WAAW,CAAC;AAC3D,OAAO,EAAE,IAAI,EAAE,aAAa,EAAE,QAAQ,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,UAAU,CAAC;AAEzE,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,yDAAyD;AACzD,MAAM,eAAe,GAAG,IAAI,GAAG,CAAC;IAC9B,QAAQ;IACR,OAAO;IACP,UAAU;IACV,UAAU;IACV,KAAK;IACL,QAAQ;IACR,MAAM;CACP,CAAC,CAAC;AAEH,wFAAwF;AACxF,MAAM,cAAc,GAAG,IAAI,GAAG,CAAC;IAC7B,GAAG;IACH,KAAK;IACL,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,SAAS;IACT,SAAS;IACT,QAAQ;IACR,QAAQ;IACR,KAAK;IACL,YAAY;IACZ,KAAK;IACL,IAAI;IACJ,IAAI;IACJ,YAAY;CACb,CAAC,CAAC;AAEH,MAAM,WAAW,GAAG,CAAC,GAAa,EAAU,EAAE;IAC5C,MAAM,IAAI,GAAG,QAAQ,CAAC,GAAG,EAAE,MAAM,CAAC,CAAC;IAEnC,IAAI,CAAC,IAAI,EAAE,CAAC;QACV,OAAO,EAAE,CAAC;IACZ,CAAC;IAED,MAAM,KAAK,GAAa,EAAE,CAAC;IAE3B,MAAM,IAAI,GAAG,CAAC,KAAgB,EAAQ,EAAE;QACtC,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;YACzB,IAAI,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC;gBACjB,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;YACxB,CAAC;iBAAM,IAAI,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC;gBACvB,IAAI,eAAe,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;oBACnC,SAAS;gBACX,CAAC;gBAED,MAAM,KAAK,GAAG,cAAc,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;gBAE5C,IAAI,KAAK,EAAE,CAAC;oBACV,KAAK,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;gBAClB,CAAC;gBAED,IAAI,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;gBAEpB,IAAI,KAAK,EAAE,CAAC;oBACV,KAAK,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;gBAClB,CAAC;YACH,CAAC;iBAAM,IAAI,WAAW,CAAC,IAAI,CAAC,EAAE,CAAC;gBAC7B,IAAI,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;YACtB,CAAC;QACH,CAAC;IACH,CAAC,CAAC;IAEF,IAAI,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;IAEpB,OAAO,kBAAkB,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;AAC5C,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,QAAQ,GAAG,WAAW,CAAC,GAAG,CAAC,CAAC;IAElC,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;KAC/B,CAAC;AACJ,CAAC,CAAC"}
|
|
@@ -1,11 +1,21 @@
|
|
|
1
|
-
import type {
|
|
2
|
-
import type {
|
|
1
|
+
import type { StructuredDataError, StructuredDataItem } from "../types.js";
|
|
2
|
+
import type { Document } from "./dom.js";
|
|
3
|
+
/** A value JSON.parse returns: all that a JSON-LD block or a microdata item can hold. */
|
|
4
|
+
export type JsonValue = string | number | boolean | null | JsonValue[] | JsonObject;
|
|
5
|
+
/** A JSON-LD node or a microdata item: whatever properties the page gave it. */
|
|
6
|
+
export interface JsonObject {
|
|
7
|
+
[property: string]: JsonValue;
|
|
8
|
+
}
|
|
9
|
+
/** Whether a structured-data value is a string. */
|
|
10
|
+
export declare const isString: (value: JsonValue | undefined) => value is string;
|
|
11
|
+
/** Whether a structured-data value is an object with properties, rather than a list or a scalar. */
|
|
12
|
+
export declare const isJsonObject: (value: JsonValue | undefined) => value is JsonObject;
|
|
3
13
|
export interface StructuredDataExtraction {
|
|
4
14
|
items: StructuredDataItem[];
|
|
5
15
|
errors: StructuredDataError[];
|
|
6
16
|
}
|
|
7
|
-
export declare function extractStructuredData($: CheerioAPI): StructuredDataExtraction;
|
|
8
|
-
export declare function contextString(value: unknown): string | null;
|
|
9
|
-
export declare function typesOf(value: unknown): string[];
|
|
10
17
|
/** `https://schema.org/Article` -> `Article`, `schema:Article` -> `Article`. */
|
|
11
|
-
export declare
|
|
18
|
+
export declare const shortType: (type: string) => string;
|
|
19
|
+
export declare const contextString: (value: JsonValue | undefined) => string | null;
|
|
20
|
+
export declare const typesOf: (value: JsonValue | undefined) => string[];
|
|
21
|
+
export declare const extractStructuredData: (doc: Document) => StructuredDataExtraction;
|