@apiverve/metadataextractor 1.1.10 → 1.1.13
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/README.md +8 -7
- package/index.d.ts +90 -1
- package/index.js +100 -9
- package/package.json +20 -6
- package/examples/basic.js +0 -38
- package/tmp/build.dat +0 -1
package/README.md
CHANGED
|
@@ -5,8 +5,9 @@ Metadata Extractor is a simple tool for extracting metadata from web pages. It r
|
|
|
5
5
|

|
|
6
6
|

|
|
7
7
|

|
|
8
|
+
[](https://www.npmjs.com/package/@apiverve/metadataextractor)
|
|
8
9
|
|
|
9
|
-
This is a Javascript Wrapper for the [Metadata Extractor API](https://apiverve.com/marketplace/metadataextractor)
|
|
10
|
+
This is a Javascript Wrapper for the [Metadata Extractor API](https://apiverve.com/marketplace/metadataextractor?utm_source=npm&utm_medium=readme)
|
|
10
11
|
|
|
11
12
|
---
|
|
12
13
|
|
|
@@ -27,15 +28,15 @@ yarn add @apiverve/metadataextractor
|
|
|
27
28
|
## Configuration
|
|
28
29
|
|
|
29
30
|
Before using the Metadata Extractor API client, you have to setup your account and obtain your API Key.
|
|
30
|
-
You can get it by signing up at [https://apiverve.com](https://apiverve.com)
|
|
31
|
+
You can get it by signing up at [https://apiverve.com](https://apiverve.com?utm_source=npm&utm_medium=readme)
|
|
31
32
|
|
|
32
33
|
---
|
|
33
34
|
|
|
34
35
|
## Quick Start
|
|
35
36
|
|
|
36
|
-
[Get started with the Quick Start Guide](https://docs.apiverve.com/quickstart)
|
|
37
|
+
[Get started with the Quick Start Guide](https://docs.apiverve.com/quickstart?utm_source=npm&utm_medium=readme)
|
|
37
38
|
|
|
38
|
-
The Metadata Extractor API documentation is found here: [https://docs.apiverve.com/ref/metadataextractor](https://docs.apiverve.com/ref/metadataextractor).
|
|
39
|
+
The Metadata Extractor API documentation is found here: [https://docs.apiverve.com/ref/metadataextractor](https://docs.apiverve.com/ref/metadataextractor?utm_source=npm&utm_medium=readme).
|
|
39
40
|
You can find parameters, example responses, and status codes documented here.
|
|
40
41
|
|
|
41
42
|
### Setup
|
|
@@ -1042,7 +1043,7 @@ async function makeRequest() {
|
|
|
1042
1043
|
|
|
1043
1044
|
## Customer Support
|
|
1044
1045
|
|
|
1045
|
-
Need any assistance? [Get in touch with Customer Support](https://apiverve.com/contact).
|
|
1046
|
+
Need any assistance? [Get in touch with Customer Support](https://apiverve.com/contact?utm_source=npm&utm_medium=readme).
|
|
1046
1047
|
|
|
1047
1048
|
---
|
|
1048
1049
|
|
|
@@ -1054,14 +1055,14 @@ Stay up to date by following [@apiverveHQ](https://twitter.com/apiverveHQ) on Tw
|
|
|
1054
1055
|
|
|
1055
1056
|
## Legal
|
|
1056
1057
|
|
|
1057
|
-
All usage of the APIVerve website, API, and services is subject to the [APIVerve Terms of Service](https://apiverve.com/terms)
|
|
1058
|
+
All usage of the APIVerve website, API, and services is subject to the [APIVerve Terms of Service](https://apiverve.com/terms?utm_source=npm&utm_medium=readme), [Privacy Policy](https://apiverve.com/privacy?utm_source=npm&utm_medium=readme), and [Refund Policy](https://apiverve.com/refund?utm_source=npm&utm_medium=readme).
|
|
1058
1059
|
|
|
1059
1060
|
---
|
|
1060
1061
|
|
|
1061
1062
|
## License
|
|
1062
1063
|
Licensed under the The MIT License (MIT)
|
|
1063
1064
|
|
|
1064
|
-
Copyright (©)
|
|
1065
|
+
Copyright (©) 2026 APIVerve, and EvlarSoft LLC
|
|
1065
1066
|
|
|
1066
1067
|
Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
|
|
1067
1068
|
|
package/index.d.ts
CHANGED
|
@@ -7,10 +7,99 @@ declare module '@apiverve/metadataextractor' {
|
|
|
7
7
|
export interface metadataextractorResponse {
|
|
8
8
|
status: string;
|
|
9
9
|
error: string | null;
|
|
10
|
-
data:
|
|
10
|
+
data: MetadataExtractorData;
|
|
11
11
|
code?: number;
|
|
12
12
|
}
|
|
13
13
|
|
|
14
|
+
|
|
15
|
+
interface MetadataExtractorData {
|
|
16
|
+
requestURL: string;
|
|
17
|
+
url: string;
|
|
18
|
+
canonical: string;
|
|
19
|
+
charset: string;
|
|
20
|
+
title: string;
|
|
21
|
+
image: string;
|
|
22
|
+
favicons: Favicon[];
|
|
23
|
+
author: string;
|
|
24
|
+
description: string;
|
|
25
|
+
keywords: string;
|
|
26
|
+
source: string;
|
|
27
|
+
price: string;
|
|
28
|
+
priceCurrency: string;
|
|
29
|
+
availability: string;
|
|
30
|
+
robots: string;
|
|
31
|
+
jsonld: any[];
|
|
32
|
+
ogURL: string;
|
|
33
|
+
ogLocale: string;
|
|
34
|
+
ogLocaleAlternate: string;
|
|
35
|
+
ogTitle: string;
|
|
36
|
+
ogType: string;
|
|
37
|
+
ogDescription: string;
|
|
38
|
+
ogDeterminer: string;
|
|
39
|
+
ogSiteName: string;
|
|
40
|
+
ogImage: string;
|
|
41
|
+
ogImageSecureURL: string;
|
|
42
|
+
ogImageType: string;
|
|
43
|
+
ogImageWidth: string;
|
|
44
|
+
ogImageHeight: string;
|
|
45
|
+
twitterTitle: string;
|
|
46
|
+
twitterDescription: string;
|
|
47
|
+
twitterImage: string;
|
|
48
|
+
twitterImageAlt: string;
|
|
49
|
+
twitterCard: string;
|
|
50
|
+
twitterSite: string;
|
|
51
|
+
twitterSiteID: string;
|
|
52
|
+
twitterURL: string;
|
|
53
|
+
twitterAccountID: string;
|
|
54
|
+
twitterCreator: string;
|
|
55
|
+
twitterCreatorID: string;
|
|
56
|
+
twitterPlayer: string;
|
|
57
|
+
twitterPlayerWidth: string;
|
|
58
|
+
twitterPlayerHeight: string;
|
|
59
|
+
twitterPlayerStream: string;
|
|
60
|
+
twitterAppNameIphone: string;
|
|
61
|
+
twitterAppIDIphone: string;
|
|
62
|
+
twitterAppURLIphone: string;
|
|
63
|
+
twitterAppNameIpad: string;
|
|
64
|
+
twitterAppIDIpad: string;
|
|
65
|
+
twitterAppURLIpad: string;
|
|
66
|
+
twitterAppNameGoogleplay: string;
|
|
67
|
+
twitterAppIDGoogleplay: string;
|
|
68
|
+
twitterAppURLGoogleplay: string;
|
|
69
|
+
headings: Heading[];
|
|
70
|
+
imgTags: ImgTag[];
|
|
71
|
+
responseBody: string;
|
|
72
|
+
fbAppID: string;
|
|
73
|
+
msapplicationTileColor: string;
|
|
74
|
+
msapplicationTileImage: string;
|
|
75
|
+
pDomainVerify: string;
|
|
76
|
+
}
|
|
77
|
+
|
|
78
|
+
interface Favicon {
|
|
79
|
+
rel: string;
|
|
80
|
+
href: string;
|
|
81
|
+
sizes?: string;
|
|
82
|
+
}
|
|
83
|
+
|
|
84
|
+
interface Heading {
|
|
85
|
+
level: Level;
|
|
86
|
+
text: string;
|
|
87
|
+
}
|
|
88
|
+
|
|
89
|
+
enum Level {
|
|
90
|
+
H1 = "h1",
|
|
91
|
+
H2 = "h2",
|
|
92
|
+
H3 = "h3",
|
|
93
|
+
H4 = "h4",
|
|
94
|
+
H5 = "h5",
|
|
95
|
+
H6 = "h6",
|
|
96
|
+
}
|
|
97
|
+
|
|
98
|
+
interface ImgTag {
|
|
99
|
+
src: string;
|
|
100
|
+
alt?: string;
|
|
101
|
+
}
|
|
102
|
+
|
|
14
103
|
export default class metadataextractorWrapper {
|
|
15
104
|
constructor(options: metadataextractorOptions);
|
|
16
105
|
|
package/index.js
CHANGED
|
@@ -34,6 +34,102 @@ class metadataextractorWrapper {
|
|
|
34
34
|
|
|
35
35
|
// secure is deprecated, all requests must be made over HTTPS
|
|
36
36
|
this.baseURL = 'https://api.apiverve.com/v1/metadataextractor';
|
|
37
|
+
|
|
38
|
+
// Validation rules for parameters (generated from schema)
|
|
39
|
+
this.validationRules = {"url":{"type":"string","required":true,"format":"url"}};
|
|
40
|
+
}
|
|
41
|
+
|
|
42
|
+
/**
|
|
43
|
+
* Validate query parameters against schema rules
|
|
44
|
+
* @param {Object} query - The query parameters to validate
|
|
45
|
+
* @throws {Error} - If validation fails
|
|
46
|
+
*/
|
|
47
|
+
validateParams(query) {
|
|
48
|
+
const errors = [];
|
|
49
|
+
|
|
50
|
+
for (const [paramName, rules] of Object.entries(this.validationRules)) {
|
|
51
|
+
const value = query[paramName];
|
|
52
|
+
|
|
53
|
+
// Check required
|
|
54
|
+
if (rules.required && (value === undefined || value === null || value === '')) {
|
|
55
|
+
errors.push(`Required parameter [${paramName}] is missing.`);
|
|
56
|
+
continue;
|
|
57
|
+
}
|
|
58
|
+
|
|
59
|
+
// Skip validation if value is not provided and not required
|
|
60
|
+
if (value === undefined || value === null) {
|
|
61
|
+
continue;
|
|
62
|
+
}
|
|
63
|
+
|
|
64
|
+
// Type validation
|
|
65
|
+
if (rules.type === 'integer' || rules.type === 'number') {
|
|
66
|
+
const numValue = Number(value);
|
|
67
|
+
if (isNaN(numValue)) {
|
|
68
|
+
errors.push(`Parameter [${paramName}] must be a valid ${rules.type}.`);
|
|
69
|
+
continue;
|
|
70
|
+
}
|
|
71
|
+
|
|
72
|
+
if (rules.type === 'integer' && !Number.isInteger(numValue)) {
|
|
73
|
+
errors.push(`Parameter [${paramName}] must be an integer.`);
|
|
74
|
+
continue;
|
|
75
|
+
}
|
|
76
|
+
|
|
77
|
+
// Min/max validation for numbers
|
|
78
|
+
if (rules.min !== undefined && numValue < rules.min) {
|
|
79
|
+
errors.push(`Parameter [${paramName}] must be at least ${rules.min}.`);
|
|
80
|
+
}
|
|
81
|
+
if (rules.max !== undefined && numValue > rules.max) {
|
|
82
|
+
errors.push(`Parameter [${paramName}] must be at most ${rules.max}.`);
|
|
83
|
+
}
|
|
84
|
+
} else if (rules.type === 'string') {
|
|
85
|
+
if (typeof value !== 'string') {
|
|
86
|
+
errors.push(`Parameter [${paramName}] must be a string.`);
|
|
87
|
+
continue;
|
|
88
|
+
}
|
|
89
|
+
|
|
90
|
+
// Length validation for strings
|
|
91
|
+
if (rules.minLength !== undefined && value.length < rules.minLength) {
|
|
92
|
+
errors.push(`Parameter [${paramName}] must be at least ${rules.minLength} characters.`);
|
|
93
|
+
}
|
|
94
|
+
if (rules.maxLength !== undefined && value.length > rules.maxLength) {
|
|
95
|
+
errors.push(`Parameter [${paramName}] must be at most ${rules.maxLength} characters.`);
|
|
96
|
+
}
|
|
97
|
+
|
|
98
|
+
// Format validation
|
|
99
|
+
if (rules.format) {
|
|
100
|
+
const formatPatterns = {
|
|
101
|
+
'email': /^[^\s@]+@[^\s@]+\.[^\s@]+$/,
|
|
102
|
+
'url': /^https?:\/\/.+/i,
|
|
103
|
+
'ip': /^(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)$|^([0-9a-fA-F]{1,4}:){7}[0-9a-fA-F]{1,4}$/,
|
|
104
|
+
'date': /^\d{4}-\d{2}-\d{2}$/,
|
|
105
|
+
'hexColor': /^#?([0-9a-fA-F]{3}|[0-9a-fA-F]{6})$/
|
|
106
|
+
};
|
|
107
|
+
|
|
108
|
+
if (formatPatterns[rules.format] && !formatPatterns[rules.format].test(value)) {
|
|
109
|
+
errors.push(`Parameter [${paramName}] must be a valid ${rules.format}.`);
|
|
110
|
+
}
|
|
111
|
+
}
|
|
112
|
+
} else if (rules.type === 'boolean') {
|
|
113
|
+
if (typeof value !== 'boolean' && value !== 'true' && value !== 'false') {
|
|
114
|
+
errors.push(`Parameter [${paramName}] must be a boolean.`);
|
|
115
|
+
}
|
|
116
|
+
} else if (rules.type === 'array') {
|
|
117
|
+
if (!Array.isArray(value)) {
|
|
118
|
+
errors.push(`Parameter [${paramName}] must be an array.`);
|
|
119
|
+
}
|
|
120
|
+
}
|
|
121
|
+
|
|
122
|
+
// Enum validation
|
|
123
|
+
if (rules.enum && Array.isArray(rules.enum)) {
|
|
124
|
+
if (!rules.enum.includes(value)) {
|
|
125
|
+
errors.push(`Parameter [${paramName}] must be one of: ${rules.enum.join(', ')}.`);
|
|
126
|
+
}
|
|
127
|
+
}
|
|
128
|
+
}
|
|
129
|
+
|
|
130
|
+
if (errors.length > 0) {
|
|
131
|
+
throw new Error(`Validation failed: ${errors.join(' ')} See documentation: https://docs.apiverve.com/ref/metadataextractor`);
|
|
132
|
+
}
|
|
37
133
|
}
|
|
38
134
|
|
|
39
135
|
async execute(query, callback) {
|
|
@@ -58,14 +154,8 @@ class metadataextractorWrapper {
|
|
|
58
154
|
}
|
|
59
155
|
}
|
|
60
156
|
|
|
61
|
-
|
|
62
|
-
|
|
63
|
-
for (var i = 0; i < requiredParams.length; i++) {
|
|
64
|
-
if (!query[requiredParams[i]]) {
|
|
65
|
-
throw new Error(`Required parameter [${requiredParams[i]}] is missing. See documentation: https://docs.apiverve.com/ref/metadataextractor`);
|
|
66
|
-
}
|
|
67
|
-
}
|
|
68
|
-
}
|
|
157
|
+
// Validate parameters against schema rules
|
|
158
|
+
this.validateParams(query);
|
|
69
159
|
|
|
70
160
|
const method = 'POST';
|
|
71
161
|
const url = method === 'POST' ? this.baseURL : this.constructURL(query);
|
|
@@ -108,7 +198,7 @@ class metadataextractorWrapper {
|
|
|
108
198
|
constructURL(query) {
|
|
109
199
|
let url = this.baseURL;
|
|
110
200
|
|
|
111
|
-
if(query && typeof query === 'object')
|
|
201
|
+
if(query && typeof query === 'object')
|
|
112
202
|
{
|
|
113
203
|
if (Object.keys(query).length > 0) {
|
|
114
204
|
const queryString = Object.keys(query)
|
|
@@ -119,6 +209,7 @@ class metadataextractorWrapper {
|
|
|
119
209
|
}
|
|
120
210
|
return url;
|
|
121
211
|
}
|
|
212
|
+
|
|
122
213
|
}
|
|
123
214
|
|
|
124
215
|
module.exports = metadataextractorWrapper;
|
package/package.json
CHANGED
|
@@ -1,26 +1,40 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@apiverve/metadataextractor",
|
|
3
|
-
"version": "1.1.
|
|
3
|
+
"version": "1.1.13",
|
|
4
4
|
"description": "Metadata Extractor is a simple tool for extracting metadata from web pages. It returns the meta title, meta description, and more.",
|
|
5
5
|
"main": "index.js",
|
|
6
6
|
"types": "index.d.ts",
|
|
7
|
+
"sideEffects": false,
|
|
8
|
+
"engines": {
|
|
9
|
+
"node": ">=14.0.0"
|
|
10
|
+
},
|
|
11
|
+
"files": [
|
|
12
|
+
"index.js",
|
|
13
|
+
"index.d.ts",
|
|
14
|
+
"LICENSE"
|
|
15
|
+
],
|
|
7
16
|
"scripts": {
|
|
8
17
|
"test": "mocha",
|
|
9
18
|
"example": "node examples/basic.js"
|
|
10
19
|
},
|
|
11
20
|
"repository": {
|
|
12
21
|
"type": "git",
|
|
13
|
-
"url": "git+https://github.com/apiverve/metadataextractor-
|
|
22
|
+
"url": "git+https://github.com/apiverve/metadataextractor-api.git",
|
|
23
|
+
"directory": "npm"
|
|
14
24
|
},
|
|
15
25
|
"keywords": [
|
|
16
|
-
"
|
|
26
|
+
""
|
|
17
27
|
],
|
|
18
|
-
"author":
|
|
28
|
+
"author": {
|
|
29
|
+
"name": "APIVerve",
|
|
30
|
+
"email": "hello@apiverve.com",
|
|
31
|
+
"url": "https://apiverve.com"
|
|
32
|
+
},
|
|
19
33
|
"license": "MIT",
|
|
20
34
|
"bugs": {
|
|
21
|
-
"url": "https://github.com/apiverve/metadataextractor-
|
|
35
|
+
"url": "https://github.com/apiverve/metadataextractor-api/issues"
|
|
22
36
|
},
|
|
23
|
-
"homepage": "https://apiverve.com/marketplace/metadataextractor?utm_source=npm",
|
|
37
|
+
"homepage": "https://apiverve.com/marketplace/metadataextractor?utm_source=npm&utm_medium=homepage",
|
|
24
38
|
"devDependencies": {
|
|
25
39
|
"mocha": "^11.0.1",
|
|
26
40
|
"chai": "^5.1.2",
|
package/examples/basic.js
DELETED
|
@@ -1,38 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* Basic Example - Metadata Extractor API
|
|
3
|
-
*
|
|
4
|
-
* This example demonstrates how to use the Metadata Extractor API.
|
|
5
|
-
* Make sure to set your API key in the .env file or replace '[YOUR_API_KEY]' below.
|
|
6
|
-
*/
|
|
7
|
-
|
|
8
|
-
require('dotenv').config();
|
|
9
|
-
const metadataextractorAPI = require('../index.js');
|
|
10
|
-
|
|
11
|
-
// Initialize the API client
|
|
12
|
-
const api = new metadataextractorAPI({
|
|
13
|
-
api_key: process.env.API_KEY || '[YOUR_API_KEY]'
|
|
14
|
-
});
|
|
15
|
-
|
|
16
|
-
// Example query
|
|
17
|
-
var query = {
|
|
18
|
-
"url": "https://apiverve.com"
|
|
19
|
-
};
|
|
20
|
-
|
|
21
|
-
// Make the API request using callback
|
|
22
|
-
console.log('Making request to Metadata Extractor API...\n');
|
|
23
|
-
|
|
24
|
-
api.execute(query, function (error, data) {
|
|
25
|
-
if (error) {
|
|
26
|
-
console.error('Error occurred:');
|
|
27
|
-
if (error.error) {
|
|
28
|
-
console.error('Message:', error.error);
|
|
29
|
-
console.error('Status:', error.status);
|
|
30
|
-
} else {
|
|
31
|
-
console.error(JSON.stringify(error, null, 2));
|
|
32
|
-
}
|
|
33
|
-
return;
|
|
34
|
-
}
|
|
35
|
-
|
|
36
|
-
console.log('Response:');
|
|
37
|
-
console.log(JSON.stringify(data, null, 2));
|
|
38
|
-
});
|
package/tmp/build.dat
DELETED
|
@@ -1 +0,0 @@
|
|
|
1
|
-
#
|