@linkprobe/core 0.1.1 → 0.2.0
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 +101 -71
- package/dist/index.d.mts +41 -38
- package/dist/index.d.ts +41 -38
- package/dist/index.js +77 -102
- package/dist/index.js.map +1 -0
- package/dist/index.mjs +73 -71
- package/dist/index.mjs.map +1 -0
- package/package.json +12 -4
package/README.md
CHANGED
|
@@ -2,10 +2,29 @@
|
|
|
2
2
|
|
|
3
3
|
The framework-agnostic metadata extraction engine for LinkProbe.
|
|
4
4
|
|
|
5
|
-
`@linkprobe/core`
|
|
5
|
+
`@linkprobe/core` extracts, analyzes, and resolves webpage metadata from URLs including Open Graph, Twitter Cards, and HTML metadata.
|
|
6
|
+
|
|
7
|
+
It is designed for building link previews, content cards, and metadata-driven applications.
|
|
8
|
+
|
|
9
|
+
## Features
|
|
10
|
+
|
|
11
|
+
* Open Graph metadata extraction
|
|
12
|
+
* Twitter Card metadata extraction
|
|
13
|
+
* HTML metadata extraction
|
|
14
|
+
* Metadata resolution across multiple sources
|
|
15
|
+
* Metadata coverage analysis
|
|
16
|
+
* Metadata diagnostics
|
|
17
|
+
* Fully typed API
|
|
18
|
+
* Framework-agnostic core
|
|
6
19
|
|
|
7
20
|
## Installation
|
|
8
21
|
|
|
22
|
+
```bash
|
|
23
|
+
npm i @linkprobe/core
|
|
24
|
+
```
|
|
25
|
+
|
|
26
|
+
or
|
|
27
|
+
|
|
9
28
|
```bash
|
|
10
29
|
pnpm add @linkprobe/core
|
|
11
30
|
```
|
|
@@ -13,7 +32,7 @@ pnpm add @linkprobe/core
|
|
|
13
32
|
## Quick Start
|
|
14
33
|
|
|
15
34
|
```ts
|
|
16
|
-
import {probe} from "@linkprobe/core";
|
|
35
|
+
import { probe } from "@linkprobe/core";
|
|
17
36
|
|
|
18
37
|
const result = await probe("https://github.com");
|
|
19
38
|
|
|
@@ -22,85 +41,109 @@ if (result.status === "success") {
|
|
|
22
41
|
}
|
|
23
42
|
```
|
|
24
43
|
|
|
25
|
-
##
|
|
44
|
+
## API
|
|
45
|
+
|
|
46
|
+
### probe(url, options)
|
|
47
|
+
|
|
48
|
+
Extract metadata from a single URL.
|
|
26
49
|
|
|
27
50
|
```ts
|
|
28
|
-
{
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
url: "https://github.com",
|
|
32
|
-
openGraph: {
|
|
33
|
-
title: "GitHub",
|
|
34
|
-
description: "...",
|
|
35
|
-
image: "..."
|
|
36
|
-
},
|
|
37
|
-
twitter: {
|
|
38
|
-
title: "GitHub"
|
|
39
|
-
},
|
|
40
|
-
html: {
|
|
41
|
-
title: "GitHub"
|
|
42
|
-
}
|
|
43
|
-
},
|
|
44
|
-
page: {
|
|
45
|
-
requestedUrl: "https://github.com",
|
|
46
|
-
finalUrl: "https://github.com",
|
|
47
|
-
contentType: "text/html"
|
|
48
|
-
}
|
|
49
|
-
}
|
|
51
|
+
await probe("https://github.com", {
|
|
52
|
+
timeout: 5000,
|
|
53
|
+
});
|
|
50
54
|
```
|
|
51
55
|
|
|
52
|
-
|
|
56
|
+
### probeMany(urls, options)
|
|
53
57
|
|
|
54
|
-
|
|
58
|
+
Extract metadata from multiple URLs.
|
|
55
59
|
|
|
56
|
-
|
|
60
|
+
```ts
|
|
61
|
+
import { probeMany } from "@linkprobe/core";
|
|
62
|
+
|
|
63
|
+
const results = await probeMany([
|
|
64
|
+
"https://github.com",
|
|
65
|
+
"https://vercel.com",
|
|
66
|
+
]);
|
|
67
|
+
```
|
|
68
|
+
|
|
69
|
+
### resolveMetadata(metadata, options?)
|
|
70
|
+
|
|
71
|
+
Resolve metadata using priority rules across sources.
|
|
57
72
|
|
|
58
73
|
```ts
|
|
59
|
-
import {
|
|
74
|
+
import { resolveMetadata } from "@linkprobe/core";
|
|
60
75
|
|
|
61
|
-
const
|
|
76
|
+
const resolved = resolveMetadata(result.metadata, {
|
|
77
|
+
titlePriority: ["openGraph", "twitter", "html"],
|
|
78
|
+
});
|
|
79
|
+
```
|
|
62
80
|
|
|
63
|
-
|
|
64
|
-
const metadata = resolveMetadata(result.metadata);
|
|
81
|
+
## Coverage
|
|
65
82
|
|
|
66
|
-
|
|
83
|
+
Indicates how complete the extracted metadata is.
|
|
84
|
+
|
|
85
|
+
```ts
|
|
86
|
+
result.coverage;
|
|
87
|
+
```
|
|
88
|
+
|
|
89
|
+
```ts
|
|
90
|
+
{
|
|
91
|
+
available: ["title", "description", "image", "favicon"],
|
|
92
|
+
missing: [],
|
|
93
|
+
score: 100
|
|
67
94
|
}
|
|
68
95
|
```
|
|
69
96
|
|
|
70
|
-
|
|
97
|
+
## Diagnostics
|
|
98
|
+
|
|
99
|
+
Provides insight into detected metadata sources.
|
|
100
|
+
|
|
101
|
+
```ts
|
|
102
|
+
result.diagnostics;
|
|
103
|
+
```
|
|
71
104
|
|
|
72
105
|
```ts
|
|
73
106
|
{
|
|
74
|
-
|
|
75
|
-
|
|
76
|
-
|
|
77
|
-
|
|
78
|
-
|
|
107
|
+
openGraph: {
|
|
108
|
+
detected: true,
|
|
109
|
+
fields: ["title", "description", "image"]
|
|
110
|
+
},
|
|
111
|
+
twitter: {
|
|
112
|
+
detected: true,
|
|
113
|
+
fields: ["title", "description"]
|
|
114
|
+
},
|
|
115
|
+
html: {
|
|
116
|
+
detected: true,
|
|
117
|
+
fields: ["title", "description", "favicon"]
|
|
118
|
+
}
|
|
79
119
|
}
|
|
80
120
|
```
|
|
81
121
|
|
|
82
|
-
##
|
|
122
|
+
## Error Handling
|
|
83
123
|
|
|
84
124
|
```ts
|
|
85
|
-
const
|
|
86
|
-
|
|
87
|
-
|
|
125
|
+
const result = await probe(url);
|
|
126
|
+
|
|
127
|
+
if (result.status === "failed") {
|
|
128
|
+
console.error(result.error.code, result.error.message);
|
|
129
|
+
}
|
|
88
130
|
```
|
|
89
131
|
|
|
90
|
-
|
|
132
|
+
### Error Codes
|
|
91
133
|
|
|
92
|
-
|
|
134
|
+
* FETCH_FAILED
|
|
135
|
+
* TIMEOUT
|
|
136
|
+
* UNKNOWN_ERROR
|
|
137
|
+
|
|
138
|
+
## Custom Priorities
|
|
93
139
|
|
|
94
140
|
```ts
|
|
95
|
-
|
|
96
|
-
|
|
141
|
+
const resolved = resolveMetadata(result.metadata, {
|
|
142
|
+
titlePriority: ["twitter", "openGraph", "html"],
|
|
143
|
+
descriptionPriority: ["openGraph", "html", "twitter"],
|
|
97
144
|
});
|
|
98
145
|
```
|
|
99
146
|
|
|
100
|
-
| Option | Type | Description |
|
|
101
|
-
| ------- | ------ | ------------------------------- |
|
|
102
|
-
| timeout | number | Request timeout in milliseconds |
|
|
103
|
-
|
|
104
147
|
## Supported Sources
|
|
105
148
|
|
|
106
149
|
### Open Graph
|
|
@@ -128,28 +171,15 @@ await probe("https://github.com", {
|
|
|
128
171
|
<link rel="canonical" />
|
|
129
172
|
```
|
|
130
173
|
|
|
131
|
-
## Error Handling
|
|
132
|
-
|
|
133
|
-
```ts
|
|
134
|
-
const result = await probe(url);
|
|
135
|
-
|
|
136
|
-
if (result.status === "failed") {
|
|
137
|
-
console.error(result.error.code, result.error.message);
|
|
138
|
-
}
|
|
139
|
-
```
|
|
140
|
-
|
|
141
|
-
Possible error codes:
|
|
142
|
-
|
|
143
|
-
```txt
|
|
144
|
-
FETCH_FAILED
|
|
145
|
-
TIMEOUT
|
|
146
|
-
UNKNOWN_ERROR
|
|
147
|
-
```
|
|
148
|
-
|
|
149
174
|
## TypeScript
|
|
150
175
|
|
|
151
|
-
All
|
|
176
|
+
All APIs are fully typed.
|
|
152
177
|
|
|
153
178
|
```ts
|
|
154
|
-
import type {
|
|
179
|
+
import type {
|
|
180
|
+
ProbeResult,
|
|
181
|
+
Metadata,
|
|
182
|
+
ResolvedMetadata,
|
|
183
|
+
ProbeOptions,
|
|
184
|
+
} from "@linkprobe/core";
|
|
155
185
|
```
|
package/dist/index.d.mts
CHANGED
|
@@ -1,92 +1,95 @@
|
|
|
1
|
+
interface SourceDiagnostics {
|
|
2
|
+
detected: boolean;
|
|
3
|
+
fields: string[];
|
|
4
|
+
}
|
|
5
|
+
interface ProbeDiagnostics {
|
|
6
|
+
html?: SourceDiagnostics;
|
|
7
|
+
openGraph?: SourceDiagnostics;
|
|
8
|
+
twitter?: SourceDiagnostics;
|
|
9
|
+
}
|
|
10
|
+
|
|
1
11
|
interface OpenGraphMetadata {
|
|
2
|
-
title?: string;
|
|
3
12
|
description?: string;
|
|
4
13
|
image?: string;
|
|
14
|
+
locale?: string;
|
|
5
15
|
siteName?: string;
|
|
16
|
+
title?: string;
|
|
6
17
|
type?: string;
|
|
7
|
-
locale?: string;
|
|
8
18
|
}
|
|
9
19
|
interface TwitterMetadata {
|
|
10
|
-
|
|
20
|
+
creator?: string;
|
|
11
21
|
description?: string;
|
|
12
22
|
image?: string;
|
|
13
23
|
site?: string;
|
|
14
|
-
|
|
24
|
+
title?: string;
|
|
15
25
|
}
|
|
16
26
|
interface HtmlMetadata {
|
|
17
|
-
|
|
27
|
+
canonicalUrl?: string;
|
|
18
28
|
description?: string;
|
|
19
29
|
favicon?: string;
|
|
20
|
-
|
|
30
|
+
title?: string;
|
|
21
31
|
}
|
|
22
32
|
interface Metadata {
|
|
23
|
-
|
|
33
|
+
html?: HtmlMetadata;
|
|
24
34
|
openGraph?: OpenGraphMetadata;
|
|
25
35
|
twitter?: TwitterMetadata;
|
|
26
|
-
|
|
36
|
+
url: string;
|
|
37
|
+
}
|
|
38
|
+
|
|
39
|
+
interface MetadataCoverage {
|
|
40
|
+
available: string[];
|
|
41
|
+
missing: string[];
|
|
42
|
+
score: number;
|
|
27
43
|
}
|
|
28
44
|
|
|
29
45
|
interface ProbeOptions {
|
|
30
46
|
timeout?: number;
|
|
31
47
|
}
|
|
32
48
|
interface PageInfo {
|
|
33
|
-
requestedUrl: string;
|
|
34
|
-
finalUrl: string;
|
|
35
49
|
contentType?: string;
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
detected: boolean;
|
|
39
|
-
fields: string[];
|
|
40
|
-
}
|
|
41
|
-
interface ProbeDiagnostics {
|
|
42
|
-
openGraph?: SourceDiagnostics;
|
|
43
|
-
twitter?: SourceDiagnostics;
|
|
44
|
-
html?: SourceDiagnostics;
|
|
50
|
+
finalUrl: string;
|
|
51
|
+
requestedUrl: string;
|
|
45
52
|
}
|
|
46
53
|
interface ProbeSuccess {
|
|
47
|
-
|
|
54
|
+
coverage: MetadataCoverage;
|
|
55
|
+
diagnostics: ProbeDiagnostics;
|
|
48
56
|
metadata: Metadata;
|
|
49
57
|
page: PageInfo;
|
|
50
|
-
|
|
58
|
+
status: "success";
|
|
51
59
|
}
|
|
52
60
|
interface ProbeError {
|
|
53
61
|
code: string;
|
|
54
62
|
message: string;
|
|
55
63
|
}
|
|
56
64
|
interface ProbeFailed {
|
|
57
|
-
status: "failed";
|
|
58
65
|
error: ProbeError;
|
|
66
|
+
status: "failed";
|
|
59
67
|
}
|
|
60
68
|
type ProbeResult = ProbeSuccess | ProbeFailed;
|
|
61
69
|
|
|
62
|
-
|
|
70
|
+
interface ProbeManyOptions extends ProbeOptions {
|
|
71
|
+
concurrency?: number;
|
|
72
|
+
}
|
|
73
|
+
|
|
74
|
+
type MetadataSource = "html" | "openGraph" | "twitter";
|
|
63
75
|
interface ResolveMetadataOptions {
|
|
64
|
-
titlePriority?: MetadataSource[];
|
|
65
76
|
descriptionPriority?: MetadataSource[];
|
|
66
77
|
imagePriority?: MetadataSource[];
|
|
78
|
+
titlePriority?: MetadataSource[];
|
|
67
79
|
}
|
|
68
80
|
interface ResolvedMetadata {
|
|
69
|
-
|
|
81
|
+
canonicalUrl?: string;
|
|
70
82
|
description?: string;
|
|
71
|
-
image?: string;
|
|
72
83
|
favicon?: string;
|
|
84
|
+
image?: string;
|
|
73
85
|
siteName?: string;
|
|
74
|
-
|
|
75
|
-
}
|
|
76
|
-
interface MetadataCoverage {
|
|
77
|
-
score: number;
|
|
78
|
-
available: string[];
|
|
79
|
-
missing: string[];
|
|
86
|
+
title?: string;
|
|
80
87
|
}
|
|
81
88
|
|
|
82
|
-
declare function buildDiagnostics(metadata: Metadata): ProbeDiagnostics;
|
|
83
|
-
|
|
84
|
-
declare function getMetadataCoverage(metadata: Metadata): MetadataCoverage;
|
|
85
|
-
|
|
86
89
|
declare function probe(url: string, options?: ProbeOptions): Promise<ProbeResult>;
|
|
87
90
|
|
|
88
|
-
declare function probeMany(urls: string[], options?:
|
|
91
|
+
declare function probeMany(urls: string[], options?: ProbeManyOptions): Promise<ProbeResult[]>;
|
|
89
92
|
|
|
90
93
|
declare function resolveMetadata(metadata: Metadata, options?: ResolveMetadataOptions): ResolvedMetadata;
|
|
91
94
|
|
|
92
|
-
export {
|
|
95
|
+
export { type HtmlMetadata, type Metadata, type MetadataCoverage, type MetadataSource, type OpenGraphMetadata, type PageInfo, type ProbeDiagnostics, type ProbeError, type ProbeFailed, type ProbeManyOptions, type ProbeOptions, type ProbeResult, type ProbeSuccess, type ResolveMetadataOptions, type ResolvedMetadata, type SourceDiagnostics, type TwitterMetadata, probe, probeMany, resolveMetadata };
|
package/dist/index.d.ts
CHANGED
|
@@ -1,92 +1,95 @@
|
|
|
1
|
+
interface SourceDiagnostics {
|
|
2
|
+
detected: boolean;
|
|
3
|
+
fields: string[];
|
|
4
|
+
}
|
|
5
|
+
interface ProbeDiagnostics {
|
|
6
|
+
html?: SourceDiagnostics;
|
|
7
|
+
openGraph?: SourceDiagnostics;
|
|
8
|
+
twitter?: SourceDiagnostics;
|
|
9
|
+
}
|
|
10
|
+
|
|
1
11
|
interface OpenGraphMetadata {
|
|
2
|
-
title?: string;
|
|
3
12
|
description?: string;
|
|
4
13
|
image?: string;
|
|
14
|
+
locale?: string;
|
|
5
15
|
siteName?: string;
|
|
16
|
+
title?: string;
|
|
6
17
|
type?: string;
|
|
7
|
-
locale?: string;
|
|
8
18
|
}
|
|
9
19
|
interface TwitterMetadata {
|
|
10
|
-
|
|
20
|
+
creator?: string;
|
|
11
21
|
description?: string;
|
|
12
22
|
image?: string;
|
|
13
23
|
site?: string;
|
|
14
|
-
|
|
24
|
+
title?: string;
|
|
15
25
|
}
|
|
16
26
|
interface HtmlMetadata {
|
|
17
|
-
|
|
27
|
+
canonicalUrl?: string;
|
|
18
28
|
description?: string;
|
|
19
29
|
favicon?: string;
|
|
20
|
-
|
|
30
|
+
title?: string;
|
|
21
31
|
}
|
|
22
32
|
interface Metadata {
|
|
23
|
-
|
|
33
|
+
html?: HtmlMetadata;
|
|
24
34
|
openGraph?: OpenGraphMetadata;
|
|
25
35
|
twitter?: TwitterMetadata;
|
|
26
|
-
|
|
36
|
+
url: string;
|
|
37
|
+
}
|
|
38
|
+
|
|
39
|
+
interface MetadataCoverage {
|
|
40
|
+
available: string[];
|
|
41
|
+
missing: string[];
|
|
42
|
+
score: number;
|
|
27
43
|
}
|
|
28
44
|
|
|
29
45
|
interface ProbeOptions {
|
|
30
46
|
timeout?: number;
|
|
31
47
|
}
|
|
32
48
|
interface PageInfo {
|
|
33
|
-
requestedUrl: string;
|
|
34
|
-
finalUrl: string;
|
|
35
49
|
contentType?: string;
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
detected: boolean;
|
|
39
|
-
fields: string[];
|
|
40
|
-
}
|
|
41
|
-
interface ProbeDiagnostics {
|
|
42
|
-
openGraph?: SourceDiagnostics;
|
|
43
|
-
twitter?: SourceDiagnostics;
|
|
44
|
-
html?: SourceDiagnostics;
|
|
50
|
+
finalUrl: string;
|
|
51
|
+
requestedUrl: string;
|
|
45
52
|
}
|
|
46
53
|
interface ProbeSuccess {
|
|
47
|
-
|
|
54
|
+
coverage: MetadataCoverage;
|
|
55
|
+
diagnostics: ProbeDiagnostics;
|
|
48
56
|
metadata: Metadata;
|
|
49
57
|
page: PageInfo;
|
|
50
|
-
|
|
58
|
+
status: "success";
|
|
51
59
|
}
|
|
52
60
|
interface ProbeError {
|
|
53
61
|
code: string;
|
|
54
62
|
message: string;
|
|
55
63
|
}
|
|
56
64
|
interface ProbeFailed {
|
|
57
|
-
status: "failed";
|
|
58
65
|
error: ProbeError;
|
|
66
|
+
status: "failed";
|
|
59
67
|
}
|
|
60
68
|
type ProbeResult = ProbeSuccess | ProbeFailed;
|
|
61
69
|
|
|
62
|
-
|
|
70
|
+
interface ProbeManyOptions extends ProbeOptions {
|
|
71
|
+
concurrency?: number;
|
|
72
|
+
}
|
|
73
|
+
|
|
74
|
+
type MetadataSource = "html" | "openGraph" | "twitter";
|
|
63
75
|
interface ResolveMetadataOptions {
|
|
64
|
-
titlePriority?: MetadataSource[];
|
|
65
76
|
descriptionPriority?: MetadataSource[];
|
|
66
77
|
imagePriority?: MetadataSource[];
|
|
78
|
+
titlePriority?: MetadataSource[];
|
|
67
79
|
}
|
|
68
80
|
interface ResolvedMetadata {
|
|
69
|
-
|
|
81
|
+
canonicalUrl?: string;
|
|
70
82
|
description?: string;
|
|
71
|
-
image?: string;
|
|
72
83
|
favicon?: string;
|
|
84
|
+
image?: string;
|
|
73
85
|
siteName?: string;
|
|
74
|
-
|
|
75
|
-
}
|
|
76
|
-
interface MetadataCoverage {
|
|
77
|
-
score: number;
|
|
78
|
-
available: string[];
|
|
79
|
-
missing: string[];
|
|
86
|
+
title?: string;
|
|
80
87
|
}
|
|
81
88
|
|
|
82
|
-
declare function buildDiagnostics(metadata: Metadata): ProbeDiagnostics;
|
|
83
|
-
|
|
84
|
-
declare function getMetadataCoverage(metadata: Metadata): MetadataCoverage;
|
|
85
|
-
|
|
86
89
|
declare function probe(url: string, options?: ProbeOptions): Promise<ProbeResult>;
|
|
87
90
|
|
|
88
|
-
declare function probeMany(urls: string[], options?:
|
|
91
|
+
declare function probeMany(urls: string[], options?: ProbeManyOptions): Promise<ProbeResult[]>;
|
|
89
92
|
|
|
90
93
|
declare function resolveMetadata(metadata: Metadata, options?: ResolveMetadataOptions): ResolvedMetadata;
|
|
91
94
|
|
|
92
|
-
export {
|
|
95
|
+
export { type HtmlMetadata, type Metadata, type MetadataCoverage, type MetadataSource, type OpenGraphMetadata, type PageInfo, type ProbeDiagnostics, type ProbeError, type ProbeFailed, type ProbeManyOptions, type ProbeOptions, type ProbeResult, type ProbeSuccess, type ResolveMetadataOptions, type ResolvedMetadata, type SourceDiagnostics, type TwitterMetadata, probe, probeMany, resolveMetadata };
|
package/dist/index.js
CHANGED
|
@@ -1,32 +1,8 @@
|
|
|
1
|
-
|
|
2
|
-
|
|
3
|
-
var
|
|
4
|
-
|
|
5
|
-
|
|
6
|
-
var __export = (target, all) => {
|
|
7
|
-
for (var name in all)
|
|
8
|
-
__defProp(target, name, { get: all[name], enumerable: true });
|
|
9
|
-
};
|
|
10
|
-
var __copyProps = (to, from, except, desc) => {
|
|
11
|
-
if (from && typeof from === "object" || typeof from === "function") {
|
|
12
|
-
for (let key of __getOwnPropNames(from))
|
|
13
|
-
if (!__hasOwnProp.call(to, key) && key !== except)
|
|
14
|
-
__defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
|
|
15
|
-
}
|
|
16
|
-
return to;
|
|
17
|
-
};
|
|
18
|
-
var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
|
|
19
|
-
|
|
20
|
-
// src/index.ts
|
|
21
|
-
var index_exports = {};
|
|
22
|
-
__export(index_exports, {
|
|
23
|
-
buildDiagnostics: () => buildDiagnostics,
|
|
24
|
-
getMetadataCoverage: () => getMetadataCoverage,
|
|
25
|
-
probe: () => probe,
|
|
26
|
-
probeMany: () => probeMany,
|
|
27
|
-
resolveMetadata: () => resolveMetadata
|
|
28
|
-
});
|
|
29
|
-
module.exports = __toCommonJS(index_exports);
|
|
1
|
+
'use strict';
|
|
2
|
+
|
|
3
|
+
var cheerio = require('cheerio');
|
|
4
|
+
|
|
5
|
+
// src/probe.ts
|
|
30
6
|
|
|
31
7
|
// src/utils/extract-fields.ts
|
|
32
8
|
function extractFields(source) {
|
|
@@ -36,69 +12,6 @@ function extractFields(source) {
|
|
|
36
12
|
return Object.entries(source).filter(([, value]) => value !== void 0 && value !== null && value !== "").map(([key]) => key);
|
|
37
13
|
}
|
|
38
14
|
|
|
39
|
-
// src/build-diagnostics.ts
|
|
40
|
-
function buildDiagnostics(metadata) {
|
|
41
|
-
const openGraphFields = extractFields(metadata.openGraph);
|
|
42
|
-
const twitterFields = extractFields(metadata.twitter);
|
|
43
|
-
const htmlFields = extractFields(metadata.html);
|
|
44
|
-
return {
|
|
45
|
-
html: {
|
|
46
|
-
detected: htmlFields.length > 0,
|
|
47
|
-
fields: htmlFields
|
|
48
|
-
},
|
|
49
|
-
openGraph: {
|
|
50
|
-
detected: openGraphFields.length > 0,
|
|
51
|
-
fields: openGraphFields
|
|
52
|
-
},
|
|
53
|
-
twitter: {
|
|
54
|
-
detected: twitterFields.length > 0,
|
|
55
|
-
fields: twitterFields
|
|
56
|
-
}
|
|
57
|
-
};
|
|
58
|
-
}
|
|
59
|
-
|
|
60
|
-
// src/resolve-metadata.ts
|
|
61
|
-
var DEFAULT_PRIORITY = ["openGraph", "twitter", "html"];
|
|
62
|
-
function resolveField(metadata, field, priority) {
|
|
63
|
-
for (const source of priority) {
|
|
64
|
-
const value = metadata[source]?.[field];
|
|
65
|
-
if (value !== void 0 && value !== null && value !== "") {
|
|
66
|
-
return value;
|
|
67
|
-
}
|
|
68
|
-
}
|
|
69
|
-
return void 0;
|
|
70
|
-
}
|
|
71
|
-
function resolveMetadata(metadata, options) {
|
|
72
|
-
return {
|
|
73
|
-
canonicalUrl: metadata.html?.canonicalUrl,
|
|
74
|
-
description: resolveField(
|
|
75
|
-
metadata,
|
|
76
|
-
"description",
|
|
77
|
-
options?.descriptionPriority ?? DEFAULT_PRIORITY
|
|
78
|
-
),
|
|
79
|
-
favicon: metadata.html?.favicon,
|
|
80
|
-
image: resolveField(metadata, "image", options?.imagePriority ?? DEFAULT_PRIORITY),
|
|
81
|
-
siteName: metadata.openGraph?.siteName,
|
|
82
|
-
title: resolveField(metadata, "title", options?.titlePriority ?? DEFAULT_PRIORITY)
|
|
83
|
-
};
|
|
84
|
-
}
|
|
85
|
-
|
|
86
|
-
// src/get-metadata-coverage.ts
|
|
87
|
-
var REQUIRED_FIELDS = ["title", "description", "image", "favicon"];
|
|
88
|
-
function getMetadataCoverage(metadata) {
|
|
89
|
-
const resolved = resolveMetadata(metadata);
|
|
90
|
-
const available = REQUIRED_FIELDS.filter((field) => resolved[field]);
|
|
91
|
-
const missing = REQUIRED_FIELDS.filter((field) => !resolved[field]);
|
|
92
|
-
return {
|
|
93
|
-
available: [...available],
|
|
94
|
-
missing: [...missing],
|
|
95
|
-
score: Math.round(available.length / REQUIRED_FIELDS.length * 100)
|
|
96
|
-
};
|
|
97
|
-
}
|
|
98
|
-
|
|
99
|
-
// src/probe.ts
|
|
100
|
-
var import_cheerio = require("cheerio");
|
|
101
|
-
|
|
102
15
|
// src/utils/resolve-url.ts
|
|
103
16
|
function resolveUrl(url, baseUrl) {
|
|
104
17
|
try {
|
|
@@ -153,7 +66,7 @@ var TwitterCardParser = class {
|
|
|
153
66
|
}
|
|
154
67
|
};
|
|
155
68
|
|
|
156
|
-
// src/parsers/
|
|
69
|
+
// src/parsers/parsers.ts
|
|
157
70
|
var parsers = {
|
|
158
71
|
html: new HtmlMetaParser(),
|
|
159
72
|
openGraph: new OpenGraphParser(),
|
|
@@ -183,16 +96,80 @@ async function fetchHtml(url, options) {
|
|
|
183
96
|
};
|
|
184
97
|
}
|
|
185
98
|
|
|
99
|
+
// src/lib/build-diagnostics.ts
|
|
100
|
+
function buildDiagnostics(metadata) {
|
|
101
|
+
const openGraphFields = extractFields(metadata.openGraph);
|
|
102
|
+
const twitterFields = extractFields(metadata.twitter);
|
|
103
|
+
const htmlFields = extractFields(metadata.html);
|
|
104
|
+
return {
|
|
105
|
+
html: {
|
|
106
|
+
detected: htmlFields.length > 0,
|
|
107
|
+
fields: htmlFields
|
|
108
|
+
},
|
|
109
|
+
openGraph: {
|
|
110
|
+
detected: openGraphFields.length > 0,
|
|
111
|
+
fields: openGraphFields
|
|
112
|
+
},
|
|
113
|
+
twitter: {
|
|
114
|
+
detected: twitterFields.length > 0,
|
|
115
|
+
fields: twitterFields
|
|
116
|
+
}
|
|
117
|
+
};
|
|
118
|
+
}
|
|
119
|
+
|
|
120
|
+
// src/resolve-metadata.ts
|
|
121
|
+
var DEFAULT_PRIORITY = ["openGraph", "twitter", "html"];
|
|
122
|
+
function resolveMetadata(metadata, options) {
|
|
123
|
+
return {
|
|
124
|
+
canonicalUrl: metadata.html?.canonicalUrl,
|
|
125
|
+
description: resolveField(
|
|
126
|
+
metadata,
|
|
127
|
+
"description",
|
|
128
|
+
options?.descriptionPriority ?? DEFAULT_PRIORITY
|
|
129
|
+
),
|
|
130
|
+
favicon: metadata.html?.favicon,
|
|
131
|
+
image: resolveField(metadata, "image", options?.imagePriority ?? DEFAULT_PRIORITY),
|
|
132
|
+
siteName: metadata.openGraph?.siteName,
|
|
133
|
+
title: resolveField(metadata, "title", options?.titlePriority ?? DEFAULT_PRIORITY)
|
|
134
|
+
};
|
|
135
|
+
}
|
|
136
|
+
|
|
137
|
+
// src/lib/get-metadata-coverage.ts
|
|
138
|
+
var REQUIRED_FIELDS = ["title", "description", "image", "favicon"];
|
|
139
|
+
function getMetadataCoverage(metadata) {
|
|
140
|
+
const resolved = resolveMetadata(metadata);
|
|
141
|
+
const available = REQUIRED_FIELDS.filter((field) => resolved[field]);
|
|
142
|
+
const missing = REQUIRED_FIELDS.filter((field) => !resolved[field]);
|
|
143
|
+
return {
|
|
144
|
+
available: [...available],
|
|
145
|
+
missing: [...missing],
|
|
146
|
+
score: Math.round(available.length / REQUIRED_FIELDS.length * 100)
|
|
147
|
+
};
|
|
148
|
+
}
|
|
149
|
+
|
|
150
|
+
// src/lib/resolve-field.ts
|
|
151
|
+
function resolveField(metadata, field, priority) {
|
|
152
|
+
for (const source of priority) {
|
|
153
|
+
const value = metadata[source]?.[field];
|
|
154
|
+
if (value !== void 0 && value !== null && value !== "") {
|
|
155
|
+
return value;
|
|
156
|
+
}
|
|
157
|
+
}
|
|
158
|
+
return void 0;
|
|
159
|
+
}
|
|
160
|
+
|
|
186
161
|
// src/probe.ts
|
|
187
162
|
async function probe(url, options) {
|
|
188
163
|
try {
|
|
189
164
|
const page = await fetchHtml(url, { timeout: options?.timeout });
|
|
190
|
-
const $ =
|
|
165
|
+
const $ = cheerio.load(page.html);
|
|
191
166
|
const pageUrl = page.url;
|
|
192
167
|
const context = { $, pageUrl };
|
|
193
168
|
const metadata = extractMetadata(context);
|
|
194
169
|
const diagnostics = buildDiagnostics(metadata);
|
|
170
|
+
const coverage = getMetadataCoverage(metadata);
|
|
195
171
|
return {
|
|
172
|
+
coverage,
|
|
196
173
|
diagnostics,
|
|
197
174
|
metadata,
|
|
198
175
|
page: {
|
|
@@ -233,11 +210,9 @@ async function probe(url, options) {
|
|
|
233
210
|
async function probeMany(urls, options) {
|
|
234
211
|
return Promise.all(urls.map((url) => probe(url, options)));
|
|
235
212
|
}
|
|
236
|
-
|
|
237
|
-
|
|
238
|
-
|
|
239
|
-
|
|
240
|
-
|
|
241
|
-
|
|
242
|
-
resolveMetadata
|
|
243
|
-
});
|
|
213
|
+
|
|
214
|
+
exports.probe = probe;
|
|
215
|
+
exports.probeMany = probeMany;
|
|
216
|
+
exports.resolveMetadata = resolveMetadata;
|
|
217
|
+
//# sourceMappingURL=index.js.map
|
|
218
|
+
//# sourceMappingURL=index.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"sources":["../src/utils/extract-fields.ts","../src/utils/resolve-url.ts","../src/parsers/html-meta-parser.ts","../src/parsers/open-graph-parser.ts","../src/parsers/twitter-card-parser.ts","../src/parsers/parsers.ts","../src/extractors/extract-metadata.ts","../src/fetchers/fetch-html.ts","../src/lib/build-diagnostics.ts","../src/resolve-metadata.ts","../src/lib/get-metadata-coverage.ts","../src/lib/resolve-field.ts","../src/probe.ts","../src/probe-many.ts"],"names":["load"],"mappings":";;;;;;;AAAO,SAAS,cAAc,MAAA,EAA4C;AACxE,EAAA,IAAI,CAAC,MAAA,EAAQ;AACX,IAAA,OAAO,EAAC;AAAA,EACV;AAEA,EAAA,OAAO,MAAA,CAAO,QAAQ,MAAM,CAAA,CACzB,OAAO,CAAC,GAAG,KAAK,CAAA,KAAM,KAAA,KAAU,UAAa,KAAA,KAAU,IAAA,IAAQ,UAAU,EAAE,CAAA,CAC3E,IAAI,CAAC,CAAC,GAAG,CAAA,KAAM,GAAG,CAAA;AACvB;;;ACRO,SAAS,UAAA,CAAW,KAAa,OAAA,EAAyB;AAC/D,EAAA,IAAI;AACF,IAAA,OAAO,IAAI,GAAA,CAAI,GAAA,EAAK,OAAO,EAAE,QAAA,EAAS;AAAA,EACxC,CAAA,CAAA,MAAQ;AACN,IAAA,OAAO,GAAA;AAAA,EACT;AACF;;;ACFO,IAAM,iBAAN,MAA6D;AAAA,EAClE,MAAM,OAAA,EAA+C;AACnD,IAAA,MAAM,EAAC,CAAA,EAAG,OAAA,EAAO,GAAI,OAAA;AAErB,IAAA,OAAO;AAAA,MACL,YAAA,EAAc,CAAA,CAAE,uBAAuB,CAAA,CAAE,KAAK,MAAM,CAAA;AAAA,MACpD,WAAA,EAAa,CAAA,CAAE,0BAA0B,CAAA,CAAE,KAAK,SAAS,CAAA;AAAA,MACzD,OAAA,EAAS,UAAA;AAAA,QACP,EAAE,kBAAkB,CAAA,CAAE,IAAA,CAAK,MAAM,KAC/B,CAAA,CAAE,2BAA2B,CAAA,CAAE,IAAA,CAAK,MAAM,CAAA,IAC1C,CAAA,CAAE,8BAA8B,CAAA,CAAE,IAAA,CAAK,MAAM,CAAA,IAC7C,cAAA;AAAA,QACF;AAAA,OACF;AAAA,MACA,KAAA,EAAO,CAAA,CAAE,OAAO,CAAA,CAAE,IAAA;AAAK,KACzB;AAAA,EACF;AACF,CAAA;;;ACjBO,IAAM,kBAAN,MAAmE;AAAA,EACxE,MAAM,OAAA,EAAoD;AACxD,IAAA,MAAM,EAAC,CAAA,EAAG,OAAA,EAAO,GAAI,OAAA;AAErB,IAAA,OAAO;AAAA,MACL,WAAA,EAAa,CAAA,CAAE,iCAAiC,CAAA,CAAE,KAAK,SAAS,CAAA;AAAA,MAChE,KAAA,EAAO,WAAW,CAAA,CAAE,2BAA2B,EAAE,IAAA,CAAK,SAAS,CAAA,IAAK,EAAA,EAAI,OAAO,CAAA;AAAA,MAC/E,MAAA,EAAQ,CAAA,CAAE,4BAA4B,CAAA,CAAE,KAAK,SAAS,CAAA;AAAA,MACtD,QAAA,EAAU,CAAA,CAAE,+BAA+B,CAAA,CAAE,KAAK,SAAS,CAAA;AAAA,MAC3D,KAAA,EAAO,CAAA,CAAE,2BAA2B,CAAA,CAAE,KAAK,SAAS,CAAA;AAAA,MACpD,IAAA,EAAM,CAAA,CAAE,0BAA0B,CAAA,CAAE,KAAK,SAAS;AAAA,KACpD;AAAA,EACF;AACF,CAAA;;;ACbO,IAAM,oBAAN,MAAmE;AAAA,EACxE,MAAM,OAAA,EAAkD;AACtD,IAAA,MAAM,EAAC,CAAA,EAAG,OAAA,EAAO,GAAI,OAAA;AAErB,IAAA,OAAO;AAAA,MACL,OAAA,EAAS,CAAA,CAAE,8BAA8B,CAAA,CAAE,KAAK,SAAS,CAAA;AAAA,MACzD,WAAA,EAAa,CAAA,CAAE,kCAAkC,CAAA,CAAE,KAAK,SAAS,CAAA;AAAA,MACjE,KAAA,EAAO,WAAW,CAAA,CAAE,4BAA4B,EAAE,IAAA,CAAK,SAAS,CAAA,IAAK,EAAA,EAAI,OAAO,CAAA;AAAA,MAChF,IAAA,EAAM,CAAA,CAAE,2BAA2B,CAAA,CAAE,KAAK,SAAS,CAAA;AAAA,MACnD,KAAA,EAAO,CAAA,CAAE,4BAA4B,CAAA,CAAE,KAAK,SAAS;AAAA,KACvD;AAAA,EACF;AACF,CAAA;;;ACZO,IAAM,OAAA,GAAU;AAAA,EACrB,IAAA,EAAM,IAAI,cAAA,EAAe;AAAA,EACzB,SAAA,EAAW,IAAI,eAAA,EAAgB;AAAA,EAC/B,OAAA,EAAS,IAAI,iBAAA;AACf,CAAA;;;ACJO,SAAS,gBAAgB,OAAA,EAAkC;AAChE,EAAA,OAAO;AAAA,IACL,IAAA,EAAM,OAAA,CAAQ,IAAA,CAAK,KAAA,CAAM,OAAO,CAAA;AAAA,IAChC,SAAA,EAAW,OAAA,CAAQ,SAAA,CAAU,KAAA,CAAM,OAAO,CAAA;AAAA,IAC1C,OAAA,EAAS,OAAA,CAAQ,OAAA,CAAQ,KAAA,CAAM,OAAO,CAAA;AAAA,IACtC,KAAK,OAAA,CAAQ;AAAA,GACf;AACF;;;ACTA,eAAsB,SAAA,CAAU,KAAa,OAAA,EAAqD;AAChG,EAAA,MAAM,UAAA,GAAa,IAAI,eAAA,EAAgB;AAEvC,EAAA,MAAM,OAAA,GAAU,WAAW,MAAM,UAAA,CAAW,OAAM,EAAG,OAAA,CAAQ,WAAW,GAAI,CAAA;AAE5E,EAAA,MAAM,QAAA,GAAW,MAAM,KAAA,CAAM,GAAA,EAAK,EAAC,MAAA,EAAQ,UAAA,CAAW,QAAO,CAAA;AAE7D,EAAA,YAAA,CAAa,OAAO,CAAA;AAEpB,EAAA,OAAO;AAAA,IACL,WAAA,EAAa,QAAA,CAAS,OAAA,CAAQ,GAAA,CAAI,cAAc,CAAA,IAAK,MAAA;AAAA,IACrD,IAAA,EAAM,MAAM,QAAA,CAAS,IAAA,EAAK;AAAA,IAC1B,KAAK,QAAA,CAAS;AAAA,GAChB;AACF;;;ACZO,SAAS,iBAAiB,QAAA,EAAsC;AACrE,EAAA,MAAM,eAAA,GAAkB,aAAA,CAAc,QAAA,CAAS,SAAoC,CAAA;AACnF,EAAA,MAAM,aAAA,GAAgB,aAAA,CAAc,QAAA,CAAS,OAAkC,CAAA;AAC/E,EAAA,MAAM,UAAA,GAAa,aAAA,CAAc,QAAA,CAAS,IAA+B,CAAA;AAEzE,EAAA,OAAO;AAAA,IACL,IAAA,EAAM;AAAA,MACJ,QAAA,EAAU,WAAW,MAAA,GAAS,CAAA;AAAA,MAC9B,MAAA,EAAQ;AAAA,KACV;AAAA,IACA,SAAA,EAAW;AAAA,MACT,QAAA,EAAU,gBAAgB,MAAA,GAAS,CAAA;AAAA,MACnC,MAAA,EAAQ;AAAA,KACV;AAAA,IACA,OAAA,EAAS;AAAA,MACP,QAAA,EAAU,cAAc,MAAA,GAAS,CAAA;AAAA,MACjC,MAAA,EAAQ;AAAA;AACV,GACF;AACF;;;ACnBA,IAAM,gBAAA,GAAqC,CAAC,WAAA,EAAa,SAAA,EAAW,MAAM,CAAA;AAEnE,SAAS,eAAA,CACd,UACA,OAAA,EACkB;AAClB,EAAA,OAAO;AAAA,IACL,YAAA,EAAc,SAAS,IAAA,EAAM,YAAA;AAAA,IAC7B,WAAA,EAAa,YAAA;AAAA,MACX,QAAA;AAAA,MACA,aAAA;AAAA,MACA,SAAS,mBAAA,IAAuB;AAAA,KAClC;AAAA,IACA,OAAA,EAAS,SAAS,IAAA,EAAM,OAAA;AAAA,IACxB,OAAO,YAAA,CAAa,QAAA,EAAU,OAAA,EAAS,OAAA,EAAS,iBAAiB,gBAAgB,CAAA;AAAA,IACjF,QAAA,EAAU,SAAS,SAAA,EAAW,QAAA;AAAA,IAC9B,OAAO,YAAA,CAAa,QAAA,EAAU,OAAA,EAAS,OAAA,EAAS,iBAAiB,gBAAgB;AAAA,GACnF;AACF;;;AClBA,IAAM,eAAA,GAAkB,CAAC,OAAA,EAAS,aAAA,EAAe,SAAS,SAAS,CAAA;AAE5D,SAAS,oBAAoB,QAAA,EAAsC;AACxE,EAAA,MAAM,QAAA,GAAW,gBAAgB,QAAQ,CAAA;AACzC,EAAA,MAAM,YAAY,eAAA,CAAgB,MAAA,CAAO,CAAC,KAAA,KAAU,QAAA,CAAS,KAAK,CAAC,CAAA;AACnE,EAAA,MAAM,OAAA,GAAU,gBAAgB,MAAA,CAAO,CAAC,UAAU,CAAC,QAAA,CAAS,KAAK,CAAC,CAAA;AAElE,EAAA,OAAO;AAAA,IACL,SAAA,EAAW,CAAC,GAAG,SAAS,CAAA;AAAA,IACxB,OAAA,EAAS,CAAC,GAAG,OAAO,CAAA;AAAA,IACpB,OAAO,IAAA,CAAK,KAAA,CAAO,UAAU,MAAA,GAAS,eAAA,CAAgB,SAAU,GAAG;AAAA,GACrE;AACF;;;ACdO,SAAS,YAAA,CACd,QAAA,EACA,KAAA,EACA,QAAA,EACqB;AACrB,EAAA,KAAA,MAAW,UAAU,QAAA,EAAU;AAC7B,IAAA,MAAM,KAAA,GAAQ,QAAA,CAAS,MAAM,CAAA,GAAI,KAA+C,CAAA;AAEhF,IAAA,IAAI,KAAA,KAAU,MAAA,IAAa,KAAA,KAAU,IAAA,IAAQ,UAAU,EAAA,EAAI;AACzD,MAAA,OAAO,KAAA;AAAA,IACT;AAAA,EACF;AAEA,EAAA,OAAO,MAAA;AACT;;;ACRA,eAAsB,KAAA,CAAM,KAAa,OAAA,EAA8C;AACrF,EAAA,IAAI;AACF,IAAA,MAAM,IAAA,GAAO,MAAM,SAAA,CAAU,GAAA,EAAK,EAAC,OAAA,EAAS,OAAA,EAAS,SAAQ,CAAA;AAE7D,IAAA,MAAM,CAAA,GAAIA,YAAA,CAAK,IAAA,CAAK,IAAI,CAAA;AACxB,IAAA,MAAM,UAAU,IAAA,CAAK,GAAA;AAErB,IAAA,MAAM,OAAA,GAAyB,EAAC,CAAA,EAAG,OAAA,EAAO;AAE1C,IAAA,MAAM,QAAA,GAAW,gBAAgB,OAAO,CAAA;AACxC,IAAA,MAAM,WAAA,GAAc,iBAAiB,QAAQ,CAAA;AAC7C,IAAA,MAAM,QAAA,GAAW,oBAAoB,QAAQ,CAAA;AAE7C,IAAA,OAAO;AAAA,MACL,QAAA;AAAA,MACA,WAAA;AAAA,MACA,QAAA;AAAA,MACA,IAAA,EAAM;AAAA,QACJ,aAAa,IAAA,CAAK,WAAA;AAAA,QAClB,UAAU,IAAA,CAAK,GAAA;AAAA,QACf,YAAA,EAAc;AAAA,OAChB;AAAA,MACA,MAAA,EAAQ;AAAA,KACV;AAAA,EACF,SAAS,KAAA,EAAO;AACd,IAAA,IAAI,KAAA,YAAiB,KAAA,IAAS,KAAA,CAAM,IAAA,KAAS,YAAA;AAC3C,MAAA,OAAO;AAAA,QACL,KAAA,EAAO;AAAA,UACL,IAAA,EAAM,SAAA;AAAA,UACN,OAAA,EAAS;AAAA,SACX;AAAA,QACA,MAAA,EAAQ;AAAA,OACV;AAEF,IAAA,IAAI,KAAA,YAAiB,SAAA;AACnB,MAAA,OAAO;AAAA,QACL,KAAA,EAAO;AAAA,UACL,IAAA,EAAM,cAAA;AAAA,UACN,SAAS,KAAA,CAAM;AAAA,SACjB;AAAA,QACA,MAAA,EAAQ;AAAA,OACV;AAEF,IAAA,OAAO;AAAA,MACL,KAAA,EAAO;AAAA,QACL,IAAA,EAAM,eAAA;AAAA,QACN,OAAA,EAAS;AAAA,OACX;AAAA,MACA,MAAA,EAAQ;AAAA,KACV;AAAA,EACF;AACF;;;ACvDA,eAAsB,SAAA,CACpB,MACA,OAAA,EACwB;AACxB,EAAA,OAAO,OAAA,CAAQ,GAAA,CAAI,IAAA,CAAK,GAAA,CAAI,CAAC,QAAQ,KAAA,CAAM,GAAA,EAAK,OAAO,CAAC,CAAC,CAAA;AAC3D","file":"index.js","sourcesContent":["export function extractFields(source?: Record<string, unknown>): string[] {\n if (!source) {\n return [];\n }\n\n return Object.entries(source)\n .filter(([, value]) => value !== undefined && value !== null && value !== \"\")\n .map(([key]) => key);\n}\n","export function resolveUrl(url: string, baseUrl: string): string {\n try {\n return new URL(url, baseUrl).toString();\n } catch {\n return url;\n }\n}\n","import type {HtmlMetadata, MetadataParser, ParserContext} from \"../types\";\n\nimport {resolveUrl} from \"../utils\";\n\nexport class HtmlMetaParser implements MetadataParser<HtmlMetadata> {\n parse(context: ParserContext): Partial<HtmlMetadata> {\n const {$, pageUrl} = context;\n\n return {\n canonicalUrl: $('link[rel=\"canonical\"]').attr(\"href\"),\n description: $('meta[name=\"description\"]').attr(\"content\"),\n favicon: resolveUrl(\n $('link[rel=\"icon\"]').attr(\"href\") ??\n $('link[rel=\"shortcut icon\"]').attr(\"href\") ??\n $('link[rel=\"apple-touch-icon\"]').attr(\"href\") ??\n \"/favicon.ico\",\n pageUrl,\n ),\n title: $(\"title\").text(),\n };\n }\n}\n","import type {MetadataParser, OpenGraphMetadata, ParserContext} from \"../types\";\n\nimport {resolveUrl} from \"../utils\";\n\nexport class OpenGraphParser implements MetadataParser<OpenGraphMetadata> {\n parse(context: ParserContext): Partial<OpenGraphMetadata> {\n const {$, pageUrl} = context;\n\n return {\n description: $('meta[property=\"og:description\"]').attr(\"content\"),\n image: resolveUrl($('meta[property=\"og:image\"]').attr(\"content\") ?? \"\", pageUrl),\n locale: $('meta[property=\"og:locale\"]').attr(\"content\"),\n siteName: $('meta[property=\"og:site_name\"]').attr(\"content\"),\n title: $('meta[property=\"og:title\"]').attr(\"content\"),\n type: $('meta[property=\"og:type\"]').attr(\"content\"),\n };\n }\n}\n","import type {MetadataParser, ParserContext, TwitterMetadata} from \"../types\";\n\nimport {resolveUrl} from \"../utils\";\n\nexport class TwitterCardParser implements MetadataParser<TwitterMetadata> {\n parse(context: ParserContext): Partial<TwitterMetadata> {\n const {$, pageUrl} = context;\n\n return {\n creator: $('meta[name=\"twitter:creator\"]').attr(\"content\"),\n description: $('meta[name=\"twitter:description\"]').attr(\"content\"),\n image: resolveUrl($('meta[name=\"twitter:image\"]').attr(\"content\") ?? \"\", pageUrl),\n site: $('meta[name=\"twitter:site\"]').attr(\"content\"),\n title: $('meta[name=\"twitter:title\"]').attr(\"content\"),\n };\n }\n}\n","import {HtmlMetaParser} from \"./html-meta-parser\";\nimport {OpenGraphParser} from \"./open-graph-parser\";\nimport {TwitterCardParser} from \"./twitter-card-parser\";\n\nexport const parsers = {\n html: new HtmlMetaParser(),\n openGraph: new OpenGraphParser(),\n twitter: new TwitterCardParser(),\n};\n","import type {Metadata, ParserContext} from \"../types\";\n\nimport {parsers} from \"../parsers\";\n\nexport function extractMetadata(context: ParserContext): Metadata {\n return {\n html: parsers.html.parse(context),\n openGraph: parsers.openGraph.parse(context),\n twitter: parsers.twitter.parse(context),\n url: context.pageUrl,\n };\n}\n","import type {FetchHtmlOptions, FetchHtmlResult} from \"../types\";\n\nexport async function fetchHtml(url: string, options: FetchHtmlOptions): Promise<FetchHtmlResult> {\n const controller = new AbortController();\n\n const timeout = setTimeout(() => controller.abort(), options.timeout ?? 5000);\n\n const response = await fetch(url, {signal: controller.signal});\n\n clearTimeout(timeout);\n\n return {\n contentType: response.headers.get(\"content-type\") ?? undefined,\n html: await response.text(),\n url: response.url,\n };\n}\n","import type {Metadata, ProbeDiagnostics} from \"../types\";\n\nimport {extractFields} from \"../utils\";\n\nexport function buildDiagnostics(metadata: Metadata): ProbeDiagnostics {\n const openGraphFields = extractFields(metadata.openGraph as Record<string, unknown>);\n const twitterFields = extractFields(metadata.twitter as Record<string, unknown>);\n const htmlFields = extractFields(metadata.html as Record<string, unknown>);\n\n return {\n html: {\n detected: htmlFields.length > 0,\n fields: htmlFields,\n },\n openGraph: {\n detected: openGraphFields.length > 0,\n fields: openGraphFields,\n },\n twitter: {\n detected: twitterFields.length > 0,\n fields: twitterFields,\n },\n };\n}\n","import type {Metadata, MetadataSource, ResolveMetadataOptions, ResolvedMetadata} from \"./types\";\n\nimport {resolveField} from \"./lib\";\n\nconst DEFAULT_PRIORITY: MetadataSource[] = [\"openGraph\", \"twitter\", \"html\"];\n\nexport function resolveMetadata(\n metadata: Metadata,\n options?: ResolveMetadataOptions,\n): ResolvedMetadata {\n return {\n canonicalUrl: metadata.html?.canonicalUrl,\n description: resolveField(\n metadata,\n \"description\",\n options?.descriptionPriority ?? DEFAULT_PRIORITY,\n ),\n favicon: metadata.html?.favicon,\n image: resolveField(metadata, \"image\", options?.imagePriority ?? DEFAULT_PRIORITY),\n siteName: metadata.openGraph?.siteName,\n title: resolveField(metadata, \"title\", options?.titlePriority ?? DEFAULT_PRIORITY),\n };\n}\n","import type {Metadata, MetadataCoverage} from \"../types\";\n\nimport {resolveMetadata} from \"../resolve-metadata\";\n\nconst REQUIRED_FIELDS = [\"title\", \"description\", \"image\", \"favicon\"] as const;\n\nexport function getMetadataCoverage(metadata: Metadata): MetadataCoverage {\n const resolved = resolveMetadata(metadata);\n const available = REQUIRED_FIELDS.filter((field) => resolved[field]);\n const missing = REQUIRED_FIELDS.filter((field) => !resolved[field]);\n\n return {\n available: [...available],\n missing: [...missing],\n score: Math.round((available.length / REQUIRED_FIELDS.length) * 100),\n };\n}\n","import type {Metadata, MetadataSource, ResolvedMetadata} from \"../types\";\n\nexport function resolveField<T extends keyof ResolvedMetadata>(\n metadata: Metadata,\n field: T,\n priority: MetadataSource[],\n): ResolvedMetadata[T] {\n for (const source of priority) {\n const value = metadata[source]?.[field as keyof (typeof metadata)[typeof source]];\n\n if (value !== undefined && value !== null && value !== \"\") {\n return value as ResolvedMetadata[T];\n }\n }\n\n return undefined;\n}\n","import type {ParserContext, ProbeOptions, ProbeResult} from \"./types\";\n\nimport {load} from \"cheerio\";\n\nimport {extractMetadata} from \"./extractors\";\nimport {fetchHtml} from \"./fetchers\";\nimport {buildDiagnostics, getMetadataCoverage} from \"./lib\";\n\nexport async function probe(url: string, options?: ProbeOptions): Promise<ProbeResult> {\n try {\n const page = await fetchHtml(url, {timeout: options?.timeout});\n\n const $ = load(page.html);\n const pageUrl = page.url;\n\n const context: ParserContext = {$, pageUrl};\n\n const metadata = extractMetadata(context);\n const diagnostics = buildDiagnostics(metadata);\n const coverage = getMetadataCoverage(metadata);\n\n return {\n coverage,\n diagnostics,\n metadata,\n page: {\n contentType: page.contentType,\n finalUrl: page.url,\n requestedUrl: url,\n },\n status: \"success\",\n };\n } catch (error) {\n if (error instanceof Error && error.name === \"AbortError\")\n return {\n error: {\n code: \"TIMEOUT\",\n message: \"Request timed out\",\n },\n status: \"failed\",\n };\n\n if (error instanceof TypeError)\n return {\n error: {\n code: \"FETCH_FAILED\",\n message: error.message,\n },\n status: \"failed\",\n };\n\n return {\n error: {\n code: \"UNKNOWN_ERROR\",\n message: \"Unknown error\",\n },\n status: \"failed\",\n };\n }\n}\n","import type {ProbeManyOptions, ProbeResult} from \"./types\";\n\nimport {probe} from \"./probe\";\n\nexport async function probeMany(\n urls: string[],\n options?: ProbeManyOptions,\n): Promise<ProbeResult[]> {\n return Promise.all(urls.map((url) => probe(url, options)));\n}\n"]}
|
package/dist/index.mjs
CHANGED
|
@@ -1,3 +1,7 @@
|
|
|
1
|
+
import { load } from 'cheerio';
|
|
2
|
+
|
|
3
|
+
// src/probe.ts
|
|
4
|
+
|
|
1
5
|
// src/utils/extract-fields.ts
|
|
2
6
|
function extractFields(source) {
|
|
3
7
|
if (!source) {
|
|
@@ -6,69 +10,6 @@ function extractFields(source) {
|
|
|
6
10
|
return Object.entries(source).filter(([, value]) => value !== void 0 && value !== null && value !== "").map(([key]) => key);
|
|
7
11
|
}
|
|
8
12
|
|
|
9
|
-
// src/build-diagnostics.ts
|
|
10
|
-
function buildDiagnostics(metadata) {
|
|
11
|
-
const openGraphFields = extractFields(metadata.openGraph);
|
|
12
|
-
const twitterFields = extractFields(metadata.twitter);
|
|
13
|
-
const htmlFields = extractFields(metadata.html);
|
|
14
|
-
return {
|
|
15
|
-
html: {
|
|
16
|
-
detected: htmlFields.length > 0,
|
|
17
|
-
fields: htmlFields
|
|
18
|
-
},
|
|
19
|
-
openGraph: {
|
|
20
|
-
detected: openGraphFields.length > 0,
|
|
21
|
-
fields: openGraphFields
|
|
22
|
-
},
|
|
23
|
-
twitter: {
|
|
24
|
-
detected: twitterFields.length > 0,
|
|
25
|
-
fields: twitterFields
|
|
26
|
-
}
|
|
27
|
-
};
|
|
28
|
-
}
|
|
29
|
-
|
|
30
|
-
// src/resolve-metadata.ts
|
|
31
|
-
var DEFAULT_PRIORITY = ["openGraph", "twitter", "html"];
|
|
32
|
-
function resolveField(metadata, field, priority) {
|
|
33
|
-
for (const source of priority) {
|
|
34
|
-
const value = metadata[source]?.[field];
|
|
35
|
-
if (value !== void 0 && value !== null && value !== "") {
|
|
36
|
-
return value;
|
|
37
|
-
}
|
|
38
|
-
}
|
|
39
|
-
return void 0;
|
|
40
|
-
}
|
|
41
|
-
function resolveMetadata(metadata, options) {
|
|
42
|
-
return {
|
|
43
|
-
canonicalUrl: metadata.html?.canonicalUrl,
|
|
44
|
-
description: resolveField(
|
|
45
|
-
metadata,
|
|
46
|
-
"description",
|
|
47
|
-
options?.descriptionPriority ?? DEFAULT_PRIORITY
|
|
48
|
-
),
|
|
49
|
-
favicon: metadata.html?.favicon,
|
|
50
|
-
image: resolveField(metadata, "image", options?.imagePriority ?? DEFAULT_PRIORITY),
|
|
51
|
-
siteName: metadata.openGraph?.siteName,
|
|
52
|
-
title: resolveField(metadata, "title", options?.titlePriority ?? DEFAULT_PRIORITY)
|
|
53
|
-
};
|
|
54
|
-
}
|
|
55
|
-
|
|
56
|
-
// src/get-metadata-coverage.ts
|
|
57
|
-
var REQUIRED_FIELDS = ["title", "description", "image", "favicon"];
|
|
58
|
-
function getMetadataCoverage(metadata) {
|
|
59
|
-
const resolved = resolveMetadata(metadata);
|
|
60
|
-
const available = REQUIRED_FIELDS.filter((field) => resolved[field]);
|
|
61
|
-
const missing = REQUIRED_FIELDS.filter((field) => !resolved[field]);
|
|
62
|
-
return {
|
|
63
|
-
available: [...available],
|
|
64
|
-
missing: [...missing],
|
|
65
|
-
score: Math.round(available.length / REQUIRED_FIELDS.length * 100)
|
|
66
|
-
};
|
|
67
|
-
}
|
|
68
|
-
|
|
69
|
-
// src/probe.ts
|
|
70
|
-
import { load } from "cheerio";
|
|
71
|
-
|
|
72
13
|
// src/utils/resolve-url.ts
|
|
73
14
|
function resolveUrl(url, baseUrl) {
|
|
74
15
|
try {
|
|
@@ -123,7 +64,7 @@ var TwitterCardParser = class {
|
|
|
123
64
|
}
|
|
124
65
|
};
|
|
125
66
|
|
|
126
|
-
// src/parsers/
|
|
67
|
+
// src/parsers/parsers.ts
|
|
127
68
|
var parsers = {
|
|
128
69
|
html: new HtmlMetaParser(),
|
|
129
70
|
openGraph: new OpenGraphParser(),
|
|
@@ -153,6 +94,68 @@ async function fetchHtml(url, options) {
|
|
|
153
94
|
};
|
|
154
95
|
}
|
|
155
96
|
|
|
97
|
+
// src/lib/build-diagnostics.ts
|
|
98
|
+
function buildDiagnostics(metadata) {
|
|
99
|
+
const openGraphFields = extractFields(metadata.openGraph);
|
|
100
|
+
const twitterFields = extractFields(metadata.twitter);
|
|
101
|
+
const htmlFields = extractFields(metadata.html);
|
|
102
|
+
return {
|
|
103
|
+
html: {
|
|
104
|
+
detected: htmlFields.length > 0,
|
|
105
|
+
fields: htmlFields
|
|
106
|
+
},
|
|
107
|
+
openGraph: {
|
|
108
|
+
detected: openGraphFields.length > 0,
|
|
109
|
+
fields: openGraphFields
|
|
110
|
+
},
|
|
111
|
+
twitter: {
|
|
112
|
+
detected: twitterFields.length > 0,
|
|
113
|
+
fields: twitterFields
|
|
114
|
+
}
|
|
115
|
+
};
|
|
116
|
+
}
|
|
117
|
+
|
|
118
|
+
// src/resolve-metadata.ts
|
|
119
|
+
var DEFAULT_PRIORITY = ["openGraph", "twitter", "html"];
|
|
120
|
+
function resolveMetadata(metadata, options) {
|
|
121
|
+
return {
|
|
122
|
+
canonicalUrl: metadata.html?.canonicalUrl,
|
|
123
|
+
description: resolveField(
|
|
124
|
+
metadata,
|
|
125
|
+
"description",
|
|
126
|
+
options?.descriptionPriority ?? DEFAULT_PRIORITY
|
|
127
|
+
),
|
|
128
|
+
favicon: metadata.html?.favicon,
|
|
129
|
+
image: resolveField(metadata, "image", options?.imagePriority ?? DEFAULT_PRIORITY),
|
|
130
|
+
siteName: metadata.openGraph?.siteName,
|
|
131
|
+
title: resolveField(metadata, "title", options?.titlePriority ?? DEFAULT_PRIORITY)
|
|
132
|
+
};
|
|
133
|
+
}
|
|
134
|
+
|
|
135
|
+
// src/lib/get-metadata-coverage.ts
|
|
136
|
+
var REQUIRED_FIELDS = ["title", "description", "image", "favicon"];
|
|
137
|
+
function getMetadataCoverage(metadata) {
|
|
138
|
+
const resolved = resolveMetadata(metadata);
|
|
139
|
+
const available = REQUIRED_FIELDS.filter((field) => resolved[field]);
|
|
140
|
+
const missing = REQUIRED_FIELDS.filter((field) => !resolved[field]);
|
|
141
|
+
return {
|
|
142
|
+
available: [...available],
|
|
143
|
+
missing: [...missing],
|
|
144
|
+
score: Math.round(available.length / REQUIRED_FIELDS.length * 100)
|
|
145
|
+
};
|
|
146
|
+
}
|
|
147
|
+
|
|
148
|
+
// src/lib/resolve-field.ts
|
|
149
|
+
function resolveField(metadata, field, priority) {
|
|
150
|
+
for (const source of priority) {
|
|
151
|
+
const value = metadata[source]?.[field];
|
|
152
|
+
if (value !== void 0 && value !== null && value !== "") {
|
|
153
|
+
return value;
|
|
154
|
+
}
|
|
155
|
+
}
|
|
156
|
+
return void 0;
|
|
157
|
+
}
|
|
158
|
+
|
|
156
159
|
// src/probe.ts
|
|
157
160
|
async function probe(url, options) {
|
|
158
161
|
try {
|
|
@@ -162,7 +165,9 @@ async function probe(url, options) {
|
|
|
162
165
|
const context = { $, pageUrl };
|
|
163
166
|
const metadata = extractMetadata(context);
|
|
164
167
|
const diagnostics = buildDiagnostics(metadata);
|
|
168
|
+
const coverage = getMetadataCoverage(metadata);
|
|
165
169
|
return {
|
|
170
|
+
coverage,
|
|
166
171
|
diagnostics,
|
|
167
172
|
metadata,
|
|
168
173
|
page: {
|
|
@@ -203,10 +208,7 @@ async function probe(url, options) {
|
|
|
203
208
|
async function probeMany(urls, options) {
|
|
204
209
|
return Promise.all(urls.map((url) => probe(url, options)));
|
|
205
210
|
}
|
|
206
|
-
|
|
207
|
-
|
|
208
|
-
|
|
209
|
-
|
|
210
|
-
probeMany,
|
|
211
|
-
resolveMetadata
|
|
212
|
-
};
|
|
211
|
+
|
|
212
|
+
export { probe, probeMany, resolveMetadata };
|
|
213
|
+
//# sourceMappingURL=index.mjs.map
|
|
214
|
+
//# sourceMappingURL=index.mjs.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"sources":["../src/utils/extract-fields.ts","../src/utils/resolve-url.ts","../src/parsers/html-meta-parser.ts","../src/parsers/open-graph-parser.ts","../src/parsers/twitter-card-parser.ts","../src/parsers/parsers.ts","../src/extractors/extract-metadata.ts","../src/fetchers/fetch-html.ts","../src/lib/build-diagnostics.ts","../src/resolve-metadata.ts","../src/lib/get-metadata-coverage.ts","../src/lib/resolve-field.ts","../src/probe.ts","../src/probe-many.ts"],"names":[],"mappings":";;;;;AAAO,SAAS,cAAc,MAAA,EAA4C;AACxE,EAAA,IAAI,CAAC,MAAA,EAAQ;AACX,IAAA,OAAO,EAAC;AAAA,EACV;AAEA,EAAA,OAAO,MAAA,CAAO,QAAQ,MAAM,CAAA,CACzB,OAAO,CAAC,GAAG,KAAK,CAAA,KAAM,KAAA,KAAU,UAAa,KAAA,KAAU,IAAA,IAAQ,UAAU,EAAE,CAAA,CAC3E,IAAI,CAAC,CAAC,GAAG,CAAA,KAAM,GAAG,CAAA;AACvB;;;ACRO,SAAS,UAAA,CAAW,KAAa,OAAA,EAAyB;AAC/D,EAAA,IAAI;AACF,IAAA,OAAO,IAAI,GAAA,CAAI,GAAA,EAAK,OAAO,EAAE,QAAA,EAAS;AAAA,EACxC,CAAA,CAAA,MAAQ;AACN,IAAA,OAAO,GAAA;AAAA,EACT;AACF;;;ACFO,IAAM,iBAAN,MAA6D;AAAA,EAClE,MAAM,OAAA,EAA+C;AACnD,IAAA,MAAM,EAAC,CAAA,EAAG,OAAA,EAAO,GAAI,OAAA;AAErB,IAAA,OAAO;AAAA,MACL,YAAA,EAAc,CAAA,CAAE,uBAAuB,CAAA,CAAE,KAAK,MAAM,CAAA;AAAA,MACpD,WAAA,EAAa,CAAA,CAAE,0BAA0B,CAAA,CAAE,KAAK,SAAS,CAAA;AAAA,MACzD,OAAA,EAAS,UAAA;AAAA,QACP,EAAE,kBAAkB,CAAA,CAAE,IAAA,CAAK,MAAM,KAC/B,CAAA,CAAE,2BAA2B,CAAA,CAAE,IAAA,CAAK,MAAM,CAAA,IAC1C,CAAA,CAAE,8BAA8B,CAAA,CAAE,IAAA,CAAK,MAAM,CAAA,IAC7C,cAAA;AAAA,QACF;AAAA,OACF;AAAA,MACA,KAAA,EAAO,CAAA,CAAE,OAAO,CAAA,CAAE,IAAA;AAAK,KACzB;AAAA,EACF;AACF,CAAA;;;ACjBO,IAAM,kBAAN,MAAmE;AAAA,EACxE,MAAM,OAAA,EAAoD;AACxD,IAAA,MAAM,EAAC,CAAA,EAAG,OAAA,EAAO,GAAI,OAAA;AAErB,IAAA,OAAO;AAAA,MACL,WAAA,EAAa,CAAA,CAAE,iCAAiC,CAAA,CAAE,KAAK,SAAS,CAAA;AAAA,MAChE,KAAA,EAAO,WAAW,CAAA,CAAE,2BAA2B,EAAE,IAAA,CAAK,SAAS,CAAA,IAAK,EAAA,EAAI,OAAO,CAAA;AAAA,MAC/E,MAAA,EAAQ,CAAA,CAAE,4BAA4B,CAAA,CAAE,KAAK,SAAS,CAAA;AAAA,MACtD,QAAA,EAAU,CAAA,CAAE,+BAA+B,CAAA,CAAE,KAAK,SAAS,CAAA;AAAA,MAC3D,KAAA,EAAO,CAAA,CAAE,2BAA2B,CAAA,CAAE,KAAK,SAAS,CAAA;AAAA,MACpD,IAAA,EAAM,CAAA,CAAE,0BAA0B,CAAA,CAAE,KAAK,SAAS;AAAA,KACpD;AAAA,EACF;AACF,CAAA;;;ACbO,IAAM,oBAAN,MAAmE;AAAA,EACxE,MAAM,OAAA,EAAkD;AACtD,IAAA,MAAM,EAAC,CAAA,EAAG,OAAA,EAAO,GAAI,OAAA;AAErB,IAAA,OAAO;AAAA,MACL,OAAA,EAAS,CAAA,CAAE,8BAA8B,CAAA,CAAE,KAAK,SAAS,CAAA;AAAA,MACzD,WAAA,EAAa,CAAA,CAAE,kCAAkC,CAAA,CAAE,KAAK,SAAS,CAAA;AAAA,MACjE,KAAA,EAAO,WAAW,CAAA,CAAE,4BAA4B,EAAE,IAAA,CAAK,SAAS,CAAA,IAAK,EAAA,EAAI,OAAO,CAAA;AAAA,MAChF,IAAA,EAAM,CAAA,CAAE,2BAA2B,CAAA,CAAE,KAAK,SAAS,CAAA;AAAA,MACnD,KAAA,EAAO,CAAA,CAAE,4BAA4B,CAAA,CAAE,KAAK,SAAS;AAAA,KACvD;AAAA,EACF;AACF,CAAA;;;ACZO,IAAM,OAAA,GAAU;AAAA,EACrB,IAAA,EAAM,IAAI,cAAA,EAAe;AAAA,EACzB,SAAA,EAAW,IAAI,eAAA,EAAgB;AAAA,EAC/B,OAAA,EAAS,IAAI,iBAAA;AACf,CAAA;;;ACJO,SAAS,gBAAgB,OAAA,EAAkC;AAChE,EAAA,OAAO;AAAA,IACL,IAAA,EAAM,OAAA,CAAQ,IAAA,CAAK,KAAA,CAAM,OAAO,CAAA;AAAA,IAChC,SAAA,EAAW,OAAA,CAAQ,SAAA,CAAU,KAAA,CAAM,OAAO,CAAA;AAAA,IAC1C,OAAA,EAAS,OAAA,CAAQ,OAAA,CAAQ,KAAA,CAAM,OAAO,CAAA;AAAA,IACtC,KAAK,OAAA,CAAQ;AAAA,GACf;AACF;;;ACTA,eAAsB,SAAA,CAAU,KAAa,OAAA,EAAqD;AAChG,EAAA,MAAM,UAAA,GAAa,IAAI,eAAA,EAAgB;AAEvC,EAAA,MAAM,OAAA,GAAU,WAAW,MAAM,UAAA,CAAW,OAAM,EAAG,OAAA,CAAQ,WAAW,GAAI,CAAA;AAE5E,EAAA,MAAM,QAAA,GAAW,MAAM,KAAA,CAAM,GAAA,EAAK,EAAC,MAAA,EAAQ,UAAA,CAAW,QAAO,CAAA;AAE7D,EAAA,YAAA,CAAa,OAAO,CAAA;AAEpB,EAAA,OAAO;AAAA,IACL,WAAA,EAAa,QAAA,CAAS,OAAA,CAAQ,GAAA,CAAI,cAAc,CAAA,IAAK,MAAA;AAAA,IACrD,IAAA,EAAM,MAAM,QAAA,CAAS,IAAA,EAAK;AAAA,IAC1B,KAAK,QAAA,CAAS;AAAA,GAChB;AACF;;;ACZO,SAAS,iBAAiB,QAAA,EAAsC;AACrE,EAAA,MAAM,eAAA,GAAkB,aAAA,CAAc,QAAA,CAAS,SAAoC,CAAA;AACnF,EAAA,MAAM,aAAA,GAAgB,aAAA,CAAc,QAAA,CAAS,OAAkC,CAAA;AAC/E,EAAA,MAAM,UAAA,GAAa,aAAA,CAAc,QAAA,CAAS,IAA+B,CAAA;AAEzE,EAAA,OAAO;AAAA,IACL,IAAA,EAAM;AAAA,MACJ,QAAA,EAAU,WAAW,MAAA,GAAS,CAAA;AAAA,MAC9B,MAAA,EAAQ;AAAA,KACV;AAAA,IACA,SAAA,EAAW;AAAA,MACT,QAAA,EAAU,gBAAgB,MAAA,GAAS,CAAA;AAAA,MACnC,MAAA,EAAQ;AAAA,KACV;AAAA,IACA,OAAA,EAAS;AAAA,MACP,QAAA,EAAU,cAAc,MAAA,GAAS,CAAA;AAAA,MACjC,MAAA,EAAQ;AAAA;AACV,GACF;AACF;;;ACnBA,IAAM,gBAAA,GAAqC,CAAC,WAAA,EAAa,SAAA,EAAW,MAAM,CAAA;AAEnE,SAAS,eAAA,CACd,UACA,OAAA,EACkB;AAClB,EAAA,OAAO;AAAA,IACL,YAAA,EAAc,SAAS,IAAA,EAAM,YAAA;AAAA,IAC7B,WAAA,EAAa,YAAA;AAAA,MACX,QAAA;AAAA,MACA,aAAA;AAAA,MACA,SAAS,mBAAA,IAAuB;AAAA,KAClC;AAAA,IACA,OAAA,EAAS,SAAS,IAAA,EAAM,OAAA;AAAA,IACxB,OAAO,YAAA,CAAa,QAAA,EAAU,OAAA,EAAS,OAAA,EAAS,iBAAiB,gBAAgB,CAAA;AAAA,IACjF,QAAA,EAAU,SAAS,SAAA,EAAW,QAAA;AAAA,IAC9B,OAAO,YAAA,CAAa,QAAA,EAAU,OAAA,EAAS,OAAA,EAAS,iBAAiB,gBAAgB;AAAA,GACnF;AACF;;;AClBA,IAAM,eAAA,GAAkB,CAAC,OAAA,EAAS,aAAA,EAAe,SAAS,SAAS,CAAA;AAE5D,SAAS,oBAAoB,QAAA,EAAsC;AACxE,EAAA,MAAM,QAAA,GAAW,gBAAgB,QAAQ,CAAA;AACzC,EAAA,MAAM,YAAY,eAAA,CAAgB,MAAA,CAAO,CAAC,KAAA,KAAU,QAAA,CAAS,KAAK,CAAC,CAAA;AACnE,EAAA,MAAM,OAAA,GAAU,gBAAgB,MAAA,CAAO,CAAC,UAAU,CAAC,QAAA,CAAS,KAAK,CAAC,CAAA;AAElE,EAAA,OAAO;AAAA,IACL,SAAA,EAAW,CAAC,GAAG,SAAS,CAAA;AAAA,IACxB,OAAA,EAAS,CAAC,GAAG,OAAO,CAAA;AAAA,IACpB,OAAO,IAAA,CAAK,KAAA,CAAO,UAAU,MAAA,GAAS,eAAA,CAAgB,SAAU,GAAG;AAAA,GACrE;AACF;;;ACdO,SAAS,YAAA,CACd,QAAA,EACA,KAAA,EACA,QAAA,EACqB;AACrB,EAAA,KAAA,MAAW,UAAU,QAAA,EAAU;AAC7B,IAAA,MAAM,KAAA,GAAQ,QAAA,CAAS,MAAM,CAAA,GAAI,KAA+C,CAAA;AAEhF,IAAA,IAAI,KAAA,KAAU,MAAA,IAAa,KAAA,KAAU,IAAA,IAAQ,UAAU,EAAA,EAAI;AACzD,MAAA,OAAO,KAAA;AAAA,IACT;AAAA,EACF;AAEA,EAAA,OAAO,MAAA;AACT;;;ACRA,eAAsB,KAAA,CAAM,KAAa,OAAA,EAA8C;AACrF,EAAA,IAAI;AACF,IAAA,MAAM,IAAA,GAAO,MAAM,SAAA,CAAU,GAAA,EAAK,EAAC,OAAA,EAAS,OAAA,EAAS,SAAQ,CAAA;AAE7D,IAAA,MAAM,CAAA,GAAI,IAAA,CAAK,IAAA,CAAK,IAAI,CAAA;AACxB,IAAA,MAAM,UAAU,IAAA,CAAK,GAAA;AAErB,IAAA,MAAM,OAAA,GAAyB,EAAC,CAAA,EAAG,OAAA,EAAO;AAE1C,IAAA,MAAM,QAAA,GAAW,gBAAgB,OAAO,CAAA;AACxC,IAAA,MAAM,WAAA,GAAc,iBAAiB,QAAQ,CAAA;AAC7C,IAAA,MAAM,QAAA,GAAW,oBAAoB,QAAQ,CAAA;AAE7C,IAAA,OAAO;AAAA,MACL,QAAA;AAAA,MACA,WAAA;AAAA,MACA,QAAA;AAAA,MACA,IAAA,EAAM;AAAA,QACJ,aAAa,IAAA,CAAK,WAAA;AAAA,QAClB,UAAU,IAAA,CAAK,GAAA;AAAA,QACf,YAAA,EAAc;AAAA,OAChB;AAAA,MACA,MAAA,EAAQ;AAAA,KACV;AAAA,EACF,SAAS,KAAA,EAAO;AACd,IAAA,IAAI,KAAA,YAAiB,KAAA,IAAS,KAAA,CAAM,IAAA,KAAS,YAAA;AAC3C,MAAA,OAAO;AAAA,QACL,KAAA,EAAO;AAAA,UACL,IAAA,EAAM,SAAA;AAAA,UACN,OAAA,EAAS;AAAA,SACX;AAAA,QACA,MAAA,EAAQ;AAAA,OACV;AAEF,IAAA,IAAI,KAAA,YAAiB,SAAA;AACnB,MAAA,OAAO;AAAA,QACL,KAAA,EAAO;AAAA,UACL,IAAA,EAAM,cAAA;AAAA,UACN,SAAS,KAAA,CAAM;AAAA,SACjB;AAAA,QACA,MAAA,EAAQ;AAAA,OACV;AAEF,IAAA,OAAO;AAAA,MACL,KAAA,EAAO;AAAA,QACL,IAAA,EAAM,eAAA;AAAA,QACN,OAAA,EAAS;AAAA,OACX;AAAA,MACA,MAAA,EAAQ;AAAA,KACV;AAAA,EACF;AACF;;;ACvDA,eAAsB,SAAA,CACpB,MACA,OAAA,EACwB;AACxB,EAAA,OAAO,OAAA,CAAQ,GAAA,CAAI,IAAA,CAAK,GAAA,CAAI,CAAC,QAAQ,KAAA,CAAM,GAAA,EAAK,OAAO,CAAC,CAAC,CAAA;AAC3D","file":"index.mjs","sourcesContent":["export function extractFields(source?: Record<string, unknown>): string[] {\n if (!source) {\n return [];\n }\n\n return Object.entries(source)\n .filter(([, value]) => value !== undefined && value !== null && value !== \"\")\n .map(([key]) => key);\n}\n","export function resolveUrl(url: string, baseUrl: string): string {\n try {\n return new URL(url, baseUrl).toString();\n } catch {\n return url;\n }\n}\n","import type {HtmlMetadata, MetadataParser, ParserContext} from \"../types\";\n\nimport {resolveUrl} from \"../utils\";\n\nexport class HtmlMetaParser implements MetadataParser<HtmlMetadata> {\n parse(context: ParserContext): Partial<HtmlMetadata> {\n const {$, pageUrl} = context;\n\n return {\n canonicalUrl: $('link[rel=\"canonical\"]').attr(\"href\"),\n description: $('meta[name=\"description\"]').attr(\"content\"),\n favicon: resolveUrl(\n $('link[rel=\"icon\"]').attr(\"href\") ??\n $('link[rel=\"shortcut icon\"]').attr(\"href\") ??\n $('link[rel=\"apple-touch-icon\"]').attr(\"href\") ??\n \"/favicon.ico\",\n pageUrl,\n ),\n title: $(\"title\").text(),\n };\n }\n}\n","import type {MetadataParser, OpenGraphMetadata, ParserContext} from \"../types\";\n\nimport {resolveUrl} from \"../utils\";\n\nexport class OpenGraphParser implements MetadataParser<OpenGraphMetadata> {\n parse(context: ParserContext): Partial<OpenGraphMetadata> {\n const {$, pageUrl} = context;\n\n return {\n description: $('meta[property=\"og:description\"]').attr(\"content\"),\n image: resolveUrl($('meta[property=\"og:image\"]').attr(\"content\") ?? \"\", pageUrl),\n locale: $('meta[property=\"og:locale\"]').attr(\"content\"),\n siteName: $('meta[property=\"og:site_name\"]').attr(\"content\"),\n title: $('meta[property=\"og:title\"]').attr(\"content\"),\n type: $('meta[property=\"og:type\"]').attr(\"content\"),\n };\n }\n}\n","import type {MetadataParser, ParserContext, TwitterMetadata} from \"../types\";\n\nimport {resolveUrl} from \"../utils\";\n\nexport class TwitterCardParser implements MetadataParser<TwitterMetadata> {\n parse(context: ParserContext): Partial<TwitterMetadata> {\n const {$, pageUrl} = context;\n\n return {\n creator: $('meta[name=\"twitter:creator\"]').attr(\"content\"),\n description: $('meta[name=\"twitter:description\"]').attr(\"content\"),\n image: resolveUrl($('meta[name=\"twitter:image\"]').attr(\"content\") ?? \"\", pageUrl),\n site: $('meta[name=\"twitter:site\"]').attr(\"content\"),\n title: $('meta[name=\"twitter:title\"]').attr(\"content\"),\n };\n }\n}\n","import {HtmlMetaParser} from \"./html-meta-parser\";\nimport {OpenGraphParser} from \"./open-graph-parser\";\nimport {TwitterCardParser} from \"./twitter-card-parser\";\n\nexport const parsers = {\n html: new HtmlMetaParser(),\n openGraph: new OpenGraphParser(),\n twitter: new TwitterCardParser(),\n};\n","import type {Metadata, ParserContext} from \"../types\";\n\nimport {parsers} from \"../parsers\";\n\nexport function extractMetadata(context: ParserContext): Metadata {\n return {\n html: parsers.html.parse(context),\n openGraph: parsers.openGraph.parse(context),\n twitter: parsers.twitter.parse(context),\n url: context.pageUrl,\n };\n}\n","import type {FetchHtmlOptions, FetchHtmlResult} from \"../types\";\n\nexport async function fetchHtml(url: string, options: FetchHtmlOptions): Promise<FetchHtmlResult> {\n const controller = new AbortController();\n\n const timeout = setTimeout(() => controller.abort(), options.timeout ?? 5000);\n\n const response = await fetch(url, {signal: controller.signal});\n\n clearTimeout(timeout);\n\n return {\n contentType: response.headers.get(\"content-type\") ?? undefined,\n html: await response.text(),\n url: response.url,\n };\n}\n","import type {Metadata, ProbeDiagnostics} from \"../types\";\n\nimport {extractFields} from \"../utils\";\n\nexport function buildDiagnostics(metadata: Metadata): ProbeDiagnostics {\n const openGraphFields = extractFields(metadata.openGraph as Record<string, unknown>);\n const twitterFields = extractFields(metadata.twitter as Record<string, unknown>);\n const htmlFields = extractFields(metadata.html as Record<string, unknown>);\n\n return {\n html: {\n detected: htmlFields.length > 0,\n fields: htmlFields,\n },\n openGraph: {\n detected: openGraphFields.length > 0,\n fields: openGraphFields,\n },\n twitter: {\n detected: twitterFields.length > 0,\n fields: twitterFields,\n },\n };\n}\n","import type {Metadata, MetadataSource, ResolveMetadataOptions, ResolvedMetadata} from \"./types\";\n\nimport {resolveField} from \"./lib\";\n\nconst DEFAULT_PRIORITY: MetadataSource[] = [\"openGraph\", \"twitter\", \"html\"];\n\nexport function resolveMetadata(\n metadata: Metadata,\n options?: ResolveMetadataOptions,\n): ResolvedMetadata {\n return {\n canonicalUrl: metadata.html?.canonicalUrl,\n description: resolveField(\n metadata,\n \"description\",\n options?.descriptionPriority ?? DEFAULT_PRIORITY,\n ),\n favicon: metadata.html?.favicon,\n image: resolveField(metadata, \"image\", options?.imagePriority ?? DEFAULT_PRIORITY),\n siteName: metadata.openGraph?.siteName,\n title: resolveField(metadata, \"title\", options?.titlePriority ?? DEFAULT_PRIORITY),\n };\n}\n","import type {Metadata, MetadataCoverage} from \"../types\";\n\nimport {resolveMetadata} from \"../resolve-metadata\";\n\nconst REQUIRED_FIELDS = [\"title\", \"description\", \"image\", \"favicon\"] as const;\n\nexport function getMetadataCoverage(metadata: Metadata): MetadataCoverage {\n const resolved = resolveMetadata(metadata);\n const available = REQUIRED_FIELDS.filter((field) => resolved[field]);\n const missing = REQUIRED_FIELDS.filter((field) => !resolved[field]);\n\n return {\n available: [...available],\n missing: [...missing],\n score: Math.round((available.length / REQUIRED_FIELDS.length) * 100),\n };\n}\n","import type {Metadata, MetadataSource, ResolvedMetadata} from \"../types\";\n\nexport function resolveField<T extends keyof ResolvedMetadata>(\n metadata: Metadata,\n field: T,\n priority: MetadataSource[],\n): ResolvedMetadata[T] {\n for (const source of priority) {\n const value = metadata[source]?.[field as keyof (typeof metadata)[typeof source]];\n\n if (value !== undefined && value !== null && value !== \"\") {\n return value as ResolvedMetadata[T];\n }\n }\n\n return undefined;\n}\n","import type {ParserContext, ProbeOptions, ProbeResult} from \"./types\";\n\nimport {load} from \"cheerio\";\n\nimport {extractMetadata} from \"./extractors\";\nimport {fetchHtml} from \"./fetchers\";\nimport {buildDiagnostics, getMetadataCoverage} from \"./lib\";\n\nexport async function probe(url: string, options?: ProbeOptions): Promise<ProbeResult> {\n try {\n const page = await fetchHtml(url, {timeout: options?.timeout});\n\n const $ = load(page.html);\n const pageUrl = page.url;\n\n const context: ParserContext = {$, pageUrl};\n\n const metadata = extractMetadata(context);\n const diagnostics = buildDiagnostics(metadata);\n const coverage = getMetadataCoverage(metadata);\n\n return {\n coverage,\n diagnostics,\n metadata,\n page: {\n contentType: page.contentType,\n finalUrl: page.url,\n requestedUrl: url,\n },\n status: \"success\",\n };\n } catch (error) {\n if (error instanceof Error && error.name === \"AbortError\")\n return {\n error: {\n code: \"TIMEOUT\",\n message: \"Request timed out\",\n },\n status: \"failed\",\n };\n\n if (error instanceof TypeError)\n return {\n error: {\n code: \"FETCH_FAILED\",\n message: error.message,\n },\n status: \"failed\",\n };\n\n return {\n error: {\n code: \"UNKNOWN_ERROR\",\n message: \"Unknown error\",\n },\n status: \"failed\",\n };\n }\n}\n","import type {ProbeManyOptions, ProbeResult} from \"./types\";\n\nimport {probe} from \"./probe\";\n\nexport async function probeMany(\n urls: string[],\n options?: ProbeManyOptions,\n): Promise<ProbeResult[]> {\n return Promise.all(urls.map((url) => probe(url, options)));\n}\n"]}
|
package/package.json
CHANGED
|
@@ -1,10 +1,17 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@linkprobe/core",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.2.0",
|
|
4
4
|
"description": "Core metadata extraction engine for LinkProbe",
|
|
5
5
|
"main": "./dist/index.js",
|
|
6
6
|
"module": "./dist/index.mjs",
|
|
7
7
|
"types": "./dist/index.d.ts",
|
|
8
|
+
"exports": {
|
|
9
|
+
".": {
|
|
10
|
+
"types": "./dist/index.d.ts",
|
|
11
|
+
"import": "./dist/index.mjs",
|
|
12
|
+
"require": "./dist/index.js"
|
|
13
|
+
}
|
|
14
|
+
},
|
|
8
15
|
"files": [
|
|
9
16
|
"dist"
|
|
10
17
|
],
|
|
@@ -28,18 +35,19 @@
|
|
|
28
35
|
"cheerio": "^1.2.0"
|
|
29
36
|
},
|
|
30
37
|
"devDependencies": {
|
|
38
|
+
"@linkprobe/standard": "^0.1.1",
|
|
31
39
|
"tsup": "^8.5.1",
|
|
32
40
|
"typescript": "6.0.3",
|
|
33
|
-
"vitest": "^4.1.7"
|
|
34
|
-
"@linkprobe/standard": "0.1.1"
|
|
41
|
+
"vitest": "^4.1.7"
|
|
35
42
|
},
|
|
36
43
|
"publishConfig": {
|
|
37
44
|
"access": "public"
|
|
38
45
|
},
|
|
39
46
|
"scripts": {
|
|
47
|
+
"dev": "tsup --watch",
|
|
40
48
|
"lint": "eslint --max-warnings 0",
|
|
41
49
|
"check-types": "tsc --noEmit",
|
|
42
|
-
"build": "tsup
|
|
50
|
+
"build": "tsup",
|
|
43
51
|
"test": "vitest"
|
|
44
52
|
}
|
|
45
53
|
}
|