s3db.js 18.0.11-next.1534f717 → 18.0.11-next.47047b5d
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/dist/clients/recker-http-handler.js +56 -8
- package/dist/clients/recker-http-handler.js.map +1 -1
- package/dist/concerns/id/alphabets.js +150 -0
- package/dist/concerns/id/alphabets.js.map +1 -0
- package/dist/concerns/id/entropy.js +243 -0
- package/dist/concerns/id/entropy.js.map +1 -0
- package/dist/concerns/id/generators/nanoid.js +74 -0
- package/dist/concerns/id/generators/nanoid.js.map +1 -0
- package/dist/concerns/id/generators/sid.js +73 -0
- package/dist/concerns/id/generators/sid.js.map +1 -0
- package/dist/concerns/id/generators/ulid.js +208 -0
- package/dist/concerns/id/generators/ulid.js.map +1 -0
- package/dist/concerns/id/generators/uuid-v7.js +150 -0
- package/dist/concerns/id/generators/uuid-v7.js.map +1 -0
- package/dist/concerns/id/index.js +74 -0
- package/dist/concerns/id/index.js.map +1 -0
- package/dist/concerns/plugin-storage.js +114 -0
- package/dist/concerns/plugin-storage.js.map +1 -1
- package/dist/concerns/s3-errors.js +72 -0
- package/dist/concerns/s3-errors.js.map +1 -0
- package/dist/concerns/s3-key.js +54 -0
- package/dist/concerns/s3-key.js.map +1 -0
- package/dist/concerns/safe-merge.js +47 -0
- package/dist/concerns/safe-merge.js.map +1 -0
- package/dist/core/resource-config-validator.js +12 -2
- package/dist/core/resource-config-validator.js.map +1 -1
- package/dist/core/resource-partitions.class.js +12 -1
- package/dist/core/resource-partitions.class.js.map +1 -1
- package/dist/core/resource-persistence.class.js +41 -12
- package/dist/core/resource-persistence.class.js.map +1 -1
- package/dist/core/resource-query.class.js +21 -47
- package/dist/core/resource-query.class.js.map +1 -1
- package/dist/plugins/concerns/s3-mutex.class.js +155 -0
- package/dist/plugins/concerns/s3-mutex.class.js.map +1 -0
- package/dist/plugins/recon/stages/recker-asn-stage.js +279 -0
- package/dist/plugins/recon/stages/recker-asn-stage.js.map +1 -0
- package/dist/plugins/recon/stages/recker-dns-stage.js +227 -0
- package/dist/plugins/recon/stages/recker-dns-stage.js.map +1 -0
- package/dist/plugins/recon/stages/recker-scrape-stage.js +369 -0
- package/dist/plugins/recon/stages/recker-scrape-stage.js.map +1 -0
- package/dist/plugins/spider/recker-link-discoverer.js +544 -0
- package/dist/plugins/spider/recker-link-discoverer.js.map +1 -0
- package/dist/plugins/spider/recker-llms-validator.js +334 -0
- package/dist/plugins/spider/recker-llms-validator.js.map +1 -0
- package/dist/plugins/spider/recker-robots-validator.js +336 -0
- package/dist/plugins/spider/recker-robots-validator.js.map +1 -0
- package/dist/plugins/spider/recker-security-adapter.js +325 -0
- package/dist/plugins/spider/recker-security-adapter.js.map +1 -0
- package/dist/plugins/spider/recker-seo-adapter.js +399 -0
- package/dist/plugins/spider/recker-seo-adapter.js.map +1 -0
- package/dist/plugins/spider/recker-sitemap-validator.js +406 -0
- package/dist/plugins/spider/recker-sitemap-validator.js.map +1 -0
- package/dist/resource.class.js +2 -0
- package/dist/resource.class.js.map +1 -1
- package/dist/s3db.cjs +353 -71
- package/dist/s3db.cjs.map +1 -1
- package/dist/s3db.es.js +354 -72
- package/dist/s3db.es.js.map +1 -1
- package/dist/types/clients/recker-http-handler.d.ts +1 -0
- package/dist/types/clients/recker-http-handler.d.ts.map +1 -1
- package/dist/types/clients/types.d.ts +14 -0
- package/dist/types/clients/types.d.ts.map +1 -1
- package/dist/types/concerns/id/alphabets.d.ts +125 -0
- package/dist/types/concerns/id/alphabets.d.ts.map +1 -0
- package/dist/types/concerns/id/entropy.d.ts +84 -0
- package/dist/types/concerns/id/entropy.d.ts.map +1 -0
- package/dist/types/concerns/id/generators/nanoid.d.ts +46 -0
- package/dist/types/concerns/id/generators/nanoid.d.ts.map +1 -0
- package/dist/types/concerns/id/generators/sid.d.ts +45 -0
- package/dist/types/concerns/id/generators/sid.d.ts.map +1 -0
- package/dist/types/concerns/id/generators/ulid.d.ts +71 -0
- package/dist/types/concerns/id/generators/ulid.d.ts.map +1 -0
- package/dist/types/concerns/id/generators/uuid-v7.d.ts +60 -0
- package/dist/types/concerns/id/generators/uuid-v7.d.ts.map +1 -0
- package/dist/types/concerns/id/index.d.ts +51 -0
- package/dist/types/concerns/id/index.d.ts.map +1 -0
- package/dist/types/concerns/plugin-storage.d.ts +25 -0
- package/dist/types/concerns/plugin-storage.d.ts.map +1 -1
- package/dist/types/concerns/s3-errors.d.ts +20 -0
- package/dist/types/concerns/s3-errors.d.ts.map +1 -0
- package/dist/types/concerns/s3-key.d.ts +30 -0
- package/dist/types/concerns/s3-key.d.ts.map +1 -0
- package/dist/types/concerns/safe-merge.d.ts +22 -0
- package/dist/types/concerns/safe-merge.d.ts.map +1 -0
- package/dist/types/core/resource-config-validator.d.ts.map +1 -1
- package/dist/types/core/resource-partitions.class.d.ts.map +1 -1
- package/dist/types/core/resource-persistence.class.d.ts.map +1 -1
- package/dist/types/core/resource-query.class.d.ts.map +1 -1
- package/dist/types/plugins/concerns/s3-mutex.class.d.ts +30 -0
- package/dist/types/plugins/concerns/s3-mutex.class.d.ts.map +1 -0
- package/dist/types/plugins/recon/stages/recker-asn-stage.d.ts +90 -0
- package/dist/types/plugins/recon/stages/recker-asn-stage.d.ts.map +1 -0
- package/dist/types/plugins/recon/stages/recker-dns-stage.d.ts +125 -0
- package/dist/types/plugins/recon/stages/recker-dns-stage.d.ts.map +1 -0
- package/dist/types/plugins/recon/stages/recker-scrape-stage.d.ts +96 -0
- package/dist/types/plugins/recon/stages/recker-scrape-stage.d.ts.map +1 -0
- package/dist/types/plugins/spider/recker-link-discoverer.d.ts +54 -0
- package/dist/types/plugins/spider/recker-link-discoverer.d.ts.map +1 -0
- package/dist/types/plugins/spider/recker-llms-validator.d.ts +105 -0
- package/dist/types/plugins/spider/recker-llms-validator.d.ts.map +1 -0
- package/dist/types/plugins/spider/recker-robots-validator.d.ts +92 -0
- package/dist/types/plugins/spider/recker-robots-validator.d.ts.map +1 -0
- package/dist/types/plugins/spider/recker-security-adapter.d.ts +83 -0
- package/dist/types/plugins/spider/recker-security-adapter.d.ts.map +1 -0
- package/dist/types/plugins/spider/recker-seo-adapter.d.ts +187 -0
- package/dist/types/plugins/spider/recker-seo-adapter.d.ts.map +1 -0
- package/dist/types/plugins/spider/recker-sitemap-validator.d.ts +121 -0
- package/dist/types/plugins/spider/recker-sitemap-validator.d.ts.map +1 -0
- package/dist/types/resource.class.d.ts.map +1 -1
- package/mcp/prompts/index.ts +275 -0
- package/mcp/resources/index.ts +322 -0
- package/mcp/tools/plugins.ts +1137 -0
- package/mcp/tools/streams.ts +340 -0
- package/package.json +20 -21
- package/src/clients/recker-http-handler.ts +74 -8
- package/src/clients/types.ts +14 -0
- package/src/concerns/id/alphabets.ts +175 -0
- package/src/concerns/id/entropy.ts +286 -0
- package/src/concerns/id/generators/sid.ts +90 -0
- package/src/concerns/id/generators/ulid.ts +249 -0
- package/src/concerns/id/generators/uuid-v7.ts +179 -0
- package/src/concerns/id/index.ts +167 -0
- package/src/concerns/plugin-storage.ts +144 -0
- package/src/concerns/s3-errors.ts +97 -0
- package/src/concerns/s3-key.ts +62 -0
- package/src/concerns/safe-merge.ts +60 -0
- package/src/core/resource-config-validator.ts +9 -2
- package/src/core/resource-partitions.class.ts +14 -1
- package/src/core/resource-persistence.class.ts +47 -13
- package/src/core/resource-query.class.ts +21 -46
- package/src/plugins/concerns/s3-mutex.class.ts +228 -0
- package/src/plugins/recon/stages/recker-asn-stage.ts +385 -0
- package/src/plugins/recon/stages/recker-dns-stage.ts +360 -0
- package/src/plugins/recon/stages/recker-scrape-stage.ts +509 -0
- package/src/plugins/spider/recker-link-discoverer.ts +645 -0
- package/src/plugins/spider/recker-llms-validator.ts +500 -0
- package/src/plugins/spider/recker-robots-validator.ts +473 -0
- package/src/plugins/spider/recker-security-adapter.ts +489 -0
- package/src/plugins/spider/recker-seo-adapter.ts +605 -0
- package/src/plugins/spider/recker-sitemap-validator.ts +621 -0
- package/src/resource.class.ts +2 -0
|
@@ -0,0 +1,54 @@
|
|
|
1
|
+
import type { URLPatternMatcher } from './url-pattern-matcher.js';
|
|
2
|
+
import { ReckerRobotsValidator } from './recker-robots-validator.js';
|
|
3
|
+
import { ReckerSitemapValidator } from './recker-sitemap-validator.js';
|
|
4
|
+
import type { LinkDiscovererConfig, DiscoveredLink, RobotsCheckResult, DiscoveryStats, SitemapDiscoveryOptions, ResetOptions } from './link-discoverer.js';
|
|
5
|
+
export declare class ReckerLinkDiscoverer {
|
|
6
|
+
private config;
|
|
7
|
+
private patternMatcher;
|
|
8
|
+
private robotsValidator;
|
|
9
|
+
private sitemapValidator;
|
|
10
|
+
private discovered;
|
|
11
|
+
private queued;
|
|
12
|
+
private blockedByRobots;
|
|
13
|
+
private fromSitemap;
|
|
14
|
+
private reckerAvailable;
|
|
15
|
+
private parse;
|
|
16
|
+
private reckerExtractLinks;
|
|
17
|
+
private fallbackDiscoverer;
|
|
18
|
+
constructor(config?: LinkDiscovererConfig);
|
|
19
|
+
private _checkReckerAvailability;
|
|
20
|
+
private _getFallbackDiscoverer;
|
|
21
|
+
setPatternMatcher(matcher: URLPatternMatcher): void;
|
|
22
|
+
setRobotsFetcher(fetcher: (url: string) => Promise<string>): void;
|
|
23
|
+
extractLinksSync(html: string, baseUrl: string, currentDepth?: number): DiscoveredLink[];
|
|
24
|
+
private _extractLinksWithRecker;
|
|
25
|
+
private _extractLinksWithRegex;
|
|
26
|
+
extractLinksAsync(html: string, baseUrl: string, currentDepth?: number): Promise<DiscoveredLink[]>;
|
|
27
|
+
isAllowedByRobots(url: string): Promise<RobotsCheckResult>;
|
|
28
|
+
preloadRobots(url: string): Promise<void>;
|
|
29
|
+
getSitemaps(url: string): Promise<string[]>;
|
|
30
|
+
discoverFromSitemaps(url: string, options?: SitemapDiscoveryOptions): Promise<DiscoveredLink[]>;
|
|
31
|
+
parseSitemap(sitemapUrl: string, options?: Record<string, unknown>): Promise<Array<{
|
|
32
|
+
url?: string;
|
|
33
|
+
[key: string]: unknown;
|
|
34
|
+
}>>;
|
|
35
|
+
probeSitemapLocations(url: string): Promise<Array<{
|
|
36
|
+
url: string;
|
|
37
|
+
exists: boolean;
|
|
38
|
+
format?: string;
|
|
39
|
+
}>>;
|
|
40
|
+
private _normalizeUrl;
|
|
41
|
+
private _shouldFollow;
|
|
42
|
+
private _shouldFollowPattern;
|
|
43
|
+
private _getMainDomain;
|
|
44
|
+
markQueued(url: string): void;
|
|
45
|
+
isQueued(url: string): boolean;
|
|
46
|
+
getStats(): DiscoveryStats;
|
|
47
|
+
reset(options?: ResetOptions): void;
|
|
48
|
+
isLimitReached(): boolean;
|
|
49
|
+
getRobotsValidation(url: string): Promise<ReturnType<ReckerRobotsValidator['validate']> | null>;
|
|
50
|
+
getSitemapValidation(url: string): Promise<ReturnType<ReckerSitemapValidator['validate']> | null>;
|
|
51
|
+
isReckerEnabled(): boolean;
|
|
52
|
+
}
|
|
53
|
+
export default ReckerLinkDiscoverer;
|
|
54
|
+
//# sourceMappingURL=recker-link-discoverer.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"recker-link-discoverer.d.ts","sourceRoot":"","sources":["../../../../src/plugins/spider/recker-link-discoverer.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,iBAAiB,EAAe,MAAM,0BAA0B,CAAC;AAC/E,OAAO,EAAE,qBAAqB,EAAE,MAAM,8BAA8B,CAAC;AACrE,OAAO,EAAE,sBAAsB,EAAE,MAAM,+BAA+B,CAAC;AACvE,OAAO,KAAK,EACV,oBAAoB,EACpB,cAAc,EACd,iBAAiB,EACjB,cAAc,EACd,uBAAuB,EACvB,YAAY,EACb,MAAM,sBAAsB,CAAC;AA4B9B,qBAAa,oBAAoB;IAC/B,OAAO,CAAC,MAAM,CAGZ;IACF,OAAO,CAAC,cAAc,CAA2B;IACjD,OAAO,CAAC,eAAe,CAA+B;IACtD,OAAO,CAAC,gBAAgB,CAAgC;IACxD,OAAO,CAAC,UAAU,CAAc;IAChC,OAAO,CAAC,MAAM,CAAc;IAC5B,OAAO,CAAC,eAAe,CAAc;IACrC,OAAO,CAAC,WAAW,CAAc;IAEjC,OAAO,CAAC,eAAe,CAAwB;IAC/C,OAAO,CAAC,KAAK,CAA4B;IACzC,OAAO,CAAC,kBAAkB,CAAmC;IAC7D,OAAO,CAAC,kBAAkB,CAA8D;gBAE5E,MAAM,GAAE,oBAAyB;YA6D/B,wBAAwB;YA8BxB,sBAAsB;IAQpC,iBAAiB,CAAC,OAAO,EAAE,iBAAiB,GAAG,IAAI;IAOnD,gBAAgB,CAAC,OAAO,EAAE,CAAC,GAAG,EAAE,MAAM,KAAK,OAAO,CAAC,MAAM,CAAC,GAAG,IAAI;IASjE,gBAAgB,CAAC,IAAI,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,YAAY,GAAE,MAAU,GAAG,cAAc,EAAE;IAY3F,OAAO,CAAC,uBAAuB;IAgE/B,OAAO,CAAC,sBAAsB;IAwDxB,iBAAiB,CAAC,IAAI,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,YAAY,GAAE,MAAU,GAAG,OAAO,CAAC,cAAc,EAAE,CAAC;IA+BrG,iBAAiB,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC,iBAAiB,CAAC;IAO1D,aAAa,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC;IAYzC,WAAW,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,EAAE,CAAC;IAY3C,oBAAoB,CAAC,GAAG,EAAE,MAAM,EAAE,OAAO,GAAE,uBAA4B,GAAG,OAAO,CAAC,cAAc,EAAE,CAAC;IA+GnG,YAAY,CAChB,UAAU,EAAE,MAAM,EAClB,OAAO,GAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAM,GACpC,OAAO,CAAC,KAAK,CAAC;QAAE,GAAG,CAAC,EAAE,MAAM,CAAC;QAAC,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAA;KAAE,CAAC,CAAC;IAWrD,qBAAqB,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC,KAAK,CAAC;QAAE,GAAG,EAAE,MAAM,CAAC;QAAC,MAAM,EAAE,OAAO,CAAC;QAAC,MAAM,CAAC,EAAE,MAAM,CAAA;KAAE,CAAC,CAAC;IAY3G,OAAO,CAAC,aAAa;IAmBrB,OAAO,CAAC,aAAa;IAsCrB,OAAO,CAAC,oBAAoB;IAW5B,OAAO,CAAC,cAAc;IAMtB,UAAU,CAAC,GAAG,EAAE,MAAM,GAAG,IAAI;IAI7B,QAAQ,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO;IAQ9B,QAAQ,IAAI,cAAc;IAc1B,KAAK,CAAC,OAAO,GAAE,YAAiB,GAAG,IAAI;IAgBvC,cAAc,IAAI,OAAO;IAInB,mBAAmB,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC,UAAU,CAAC,qBAAqB,CAAC,UAAU,CAAC,CAAC,GAAG,IAAI,CAAC;IAK/F,oBAAoB,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC,UAAU,CAAC,sBAAsB,CAAC,UAAU,CAAC,CAAC,GAAG,IAAI,CAAC;IAYvG,eAAe,IAAI,OAAO;CAG3B;AAED,eAAe,oBAAoB,CAAC"}
|
|
@@ -0,0 +1,105 @@
|
|
|
1
|
+
import type { CrawlContext } from './crawl-context.js';
|
|
2
|
+
export interface LlmsTxtLink {
|
|
3
|
+
text: string;
|
|
4
|
+
url: string;
|
|
5
|
+
description?: string;
|
|
6
|
+
section?: string;
|
|
7
|
+
}
|
|
8
|
+
export interface LlmsTxtSection {
|
|
9
|
+
title: string;
|
|
10
|
+
content: string;
|
|
11
|
+
links: LlmsTxtLink[];
|
|
12
|
+
}
|
|
13
|
+
export interface LlmsTxtParseResult {
|
|
14
|
+
valid: boolean;
|
|
15
|
+
errors: string[];
|
|
16
|
+
warnings: string[];
|
|
17
|
+
siteName?: string;
|
|
18
|
+
siteDescription?: string;
|
|
19
|
+
sections: LlmsTxtSection[];
|
|
20
|
+
links: LlmsTxtLink[];
|
|
21
|
+
hasFullVersion: boolean;
|
|
22
|
+
rawContent: string;
|
|
23
|
+
size: number;
|
|
24
|
+
}
|
|
25
|
+
export interface LlmsTxtValidationIssue {
|
|
26
|
+
type: 'error' | 'warning' | 'info';
|
|
27
|
+
code: string;
|
|
28
|
+
message: string;
|
|
29
|
+
line?: number;
|
|
30
|
+
recommendation?: string;
|
|
31
|
+
}
|
|
32
|
+
export interface LlmsTxtValidationResult {
|
|
33
|
+
valid: boolean;
|
|
34
|
+
issues: LlmsTxtValidationIssue[];
|
|
35
|
+
parseResult: LlmsTxtParseResult;
|
|
36
|
+
}
|
|
37
|
+
export interface LlmsTxtCheckResult {
|
|
38
|
+
exists: boolean;
|
|
39
|
+
valid: boolean;
|
|
40
|
+
status?: number;
|
|
41
|
+
fullVersionExists?: boolean;
|
|
42
|
+
siteName?: string;
|
|
43
|
+
siteDescription?: string;
|
|
44
|
+
sections: LlmsTxtSection[];
|
|
45
|
+
links: LlmsTxtLink[];
|
|
46
|
+
issues: LlmsTxtValidationIssue[];
|
|
47
|
+
errors: string[];
|
|
48
|
+
warnings: string[];
|
|
49
|
+
size?: number;
|
|
50
|
+
}
|
|
51
|
+
export interface LlmsTxtTemplateOptions {
|
|
52
|
+
siteName: string;
|
|
53
|
+
siteDescription: string;
|
|
54
|
+
sections?: Array<{
|
|
55
|
+
title: string;
|
|
56
|
+
links: Array<{
|
|
57
|
+
text: string;
|
|
58
|
+
url: string;
|
|
59
|
+
description?: string;
|
|
60
|
+
}>;
|
|
61
|
+
}>;
|
|
62
|
+
}
|
|
63
|
+
export interface LlmsTxtValidatorConfig {
|
|
64
|
+
userAgent?: string;
|
|
65
|
+
fetchTimeout?: number;
|
|
66
|
+
cacheTimeout?: number;
|
|
67
|
+
context?: CrawlContext | null;
|
|
68
|
+
}
|
|
69
|
+
export declare class ReckerLlmsTxtValidator {
|
|
70
|
+
private config;
|
|
71
|
+
private _context;
|
|
72
|
+
private cache;
|
|
73
|
+
private _httpClient;
|
|
74
|
+
private reckerAvailable;
|
|
75
|
+
private parseLlmsTxt;
|
|
76
|
+
private validateLlmsTxt;
|
|
77
|
+
private fetchAndValidateLlmsTxt;
|
|
78
|
+
private generateLlmsTxtTemplate;
|
|
79
|
+
constructor(config?: LlmsTxtValidatorConfig);
|
|
80
|
+
private _checkReckerAvailability;
|
|
81
|
+
private _getHttpClient;
|
|
82
|
+
check(domain: string): Promise<LlmsTxtCheckResult>;
|
|
83
|
+
private _fallbackCheck;
|
|
84
|
+
private _simpleParse;
|
|
85
|
+
validate(domain: string): Promise<LlmsTxtValidationResult | null>;
|
|
86
|
+
validateContent(content: string, baseUrl?: string): LlmsTxtValidationResult | null;
|
|
87
|
+
parseContent(content: string): LlmsTxtParseResult | null;
|
|
88
|
+
generateTemplate(options: LlmsTxtTemplateOptions): string | null;
|
|
89
|
+
private _fallbackGenerateTemplate;
|
|
90
|
+
checkFullVersion(domain: string): Promise<{
|
|
91
|
+
exists: boolean;
|
|
92
|
+
status?: number;
|
|
93
|
+
size?: number;
|
|
94
|
+
}>;
|
|
95
|
+
getLinks(domain: string): Promise<LlmsTxtLink[]>;
|
|
96
|
+
getSections(domain: string): Promise<LlmsTxtSection[]>;
|
|
97
|
+
clearCache(domain?: string): void;
|
|
98
|
+
getCacheStats(): {
|
|
99
|
+
size: number;
|
|
100
|
+
domains: string[];
|
|
101
|
+
};
|
|
102
|
+
isReckerEnabled(): boolean;
|
|
103
|
+
}
|
|
104
|
+
export default ReckerLlmsTxtValidator;
|
|
105
|
+
//# sourceMappingURL=recker-llms-validator.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"recker-llms-validator.d.ts","sourceRoot":"","sources":["../../../../src/plugins/spider/recker-llms-validator.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,oBAAoB,CAAC;AAEvD,MAAM,WAAW,WAAW;IAC1B,IAAI,EAAE,MAAM,CAAC;IACb,GAAG,EAAE,MAAM,CAAC;IACZ,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,OAAO,CAAC,EAAE,MAAM,CAAC;CAClB;AAED,MAAM,WAAW,cAAc;IAC7B,KAAK,EAAE,MAAM,CAAC;IACd,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,WAAW,EAAE,CAAC;CACtB;AAED,MAAM,WAAW,kBAAkB;IACjC,KAAK,EAAE,OAAO,CAAC;IACf,MAAM,EAAE,MAAM,EAAE,CAAC;IACjB,QAAQ,EAAE,MAAM,EAAE,CAAC;IACnB,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,QAAQ,EAAE,cAAc,EAAE,CAAC;IAC3B,KAAK,EAAE,WAAW,EAAE,CAAC;IACrB,cAAc,EAAE,OAAO,CAAC;IACxB,UAAU,EAAE,MAAM,CAAC;IACnB,IAAI,EAAE,MAAM,CAAC;CACd;AAED,MAAM,WAAW,sBAAsB;IACrC,IAAI,EAAE,OAAO,GAAG,SAAS,GAAG,MAAM,CAAC;IACnC,IAAI,EAAE,MAAM,CAAC;IACb,OAAO,EAAE,MAAM,CAAC;IAChB,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,cAAc,CAAC,EAAE,MAAM,CAAC;CACzB;AAED,MAAM,WAAW,uBAAuB;IACtC,KAAK,EAAE,OAAO,CAAC;IACf,MAAM,EAAE,sBAAsB,EAAE,CAAC;IACjC,WAAW,EAAE,kBAAkB,CAAC;CACjC;AAED,MAAM,WAAW,kBAAkB;IACjC,MAAM,EAAE,OAAO,CAAC;IAChB,KAAK,EAAE,OAAO,CAAC;IACf,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,iBAAiB,CAAC,EAAE,OAAO,CAAC;IAC5B,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,QAAQ,EAAE,cAAc,EAAE,CAAC;IAC3B,KAAK,EAAE,WAAW,EAAE,CAAC;IACrB,MAAM,EAAE,sBAAsB,EAAE,CAAC;IACjC,MAAM,EAAE,MAAM,EAAE,CAAC;IACjB,QAAQ,EAAE,MAAM,EAAE,CAAC;IACnB,IAAI,CAAC,EAAE,MAAM,CAAC;CACf;AAED,MAAM,WAAW,sBAAsB;IACrC,QAAQ,EAAE,MAAM,CAAC;IACjB,eAAe,EAAE,MAAM,CAAC;IACxB,QAAQ,CAAC,EAAE,KAAK,CAAC;QACf,KAAK,EAAE,MAAM,CAAC;QACd,KAAK,EAAE,KAAK,CAAC;YACX,IAAI,EAAE,MAAM,CAAC;YACb,GAAG,EAAE,MAAM,CAAC;YACZ,WAAW,CAAC,EAAE,MAAM,CAAC;SACtB,CAAC,CAAC;KACJ,CAAC,CAAC;CACJ;AAED,MAAM,WAAW,sBAAsB;IACrC,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,OAAO,CAAC,EAAE,YAAY,GAAG,IAAI,CAAC;CAC/B;AAyBD,qBAAa,sBAAsB;IACjC,OAAO,CAAC,MAAM,CAEZ;IACF,OAAO,CAAC,QAAQ,CAAsB;IACtC,OAAO,CAAC,KAAK,CAA0B;IACvC,OAAO,CAAC,WAAW,CAAoB;IAEvC,OAAO,CAAC,eAAe,CAAwB;IAC/C,OAAO,CAAC,YAAY,CAAmC;IACvD,OAAO,CAAC,eAAe,CAAsC;IAC7D,OAAO,CAAC,uBAAuB,CAA8C;IAC7E,OAAO,CAAC,uBAAuB,CAA8C;gBAEjE,MAAM,GAAE,sBAA2B;YAajC,wBAAwB;YAmBxB,cAAc;IAyBtB,KAAK,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,kBAAkB,CAAC;YAqE1C,cAAc;IAwD5B,OAAO,CAAC,YAAY;IAmEd,QAAQ,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,uBAAuB,GAAG,IAAI,CAAC;IA2BvE,eAAe,CAAC,OAAO,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,MAAM,GAAG,uBAAuB,GAAG,IAAI;IAQlF,YAAY,CAAC,OAAO,EAAE,MAAM,GAAG,kBAAkB,GAAG,IAAI;IAQxD,gBAAgB,CAAC,OAAO,EAAE,sBAAsB,GAAG,MAAM,GAAG,IAAI;IAQhE,OAAO,CAAC,yBAAyB;IA0B3B,gBAAgB,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC;QAC9C,MAAM,EAAE,OAAO,CAAC;QAChB,MAAM,CAAC,EAAE,MAAM,CAAC;QAChB,IAAI,CAAC,EAAE,MAAM,CAAC;KACf,CAAC;IAuBI,QAAQ,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,WAAW,EAAE,CAAC;IAKhD,WAAW,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,cAAc,EAAE,CAAC;IAK5D,UAAU,CAAC,MAAM,CAAC,EAAE,MAAM,GAAG,IAAI;IASjC,aAAa,IAAI;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,EAAE,CAAA;KAAE;IAOpD,eAAe,IAAI,OAAO;CAG3B;AAED,eAAe,sBAAsB,CAAC"}
|
|
@@ -0,0 +1,92 @@
|
|
|
1
|
+
import type { RobotsCheckResult, RobotsParserConfig, CacheStats } from './robots-parser.js';
|
|
2
|
+
type ReckerRobotsParseResult = {
|
|
3
|
+
valid: boolean;
|
|
4
|
+
errors: Array<{
|
|
5
|
+
line: number;
|
|
6
|
+
message: string;
|
|
7
|
+
}>;
|
|
8
|
+
warnings: Array<{
|
|
9
|
+
line: number;
|
|
10
|
+
message: string;
|
|
11
|
+
}>;
|
|
12
|
+
directives: Array<{
|
|
13
|
+
type: 'user-agent' | 'allow' | 'disallow' | 'sitemap' | 'crawl-delay' | 'host' | 'clean-param';
|
|
14
|
+
value: string;
|
|
15
|
+
line: number;
|
|
16
|
+
}>;
|
|
17
|
+
userAgentBlocks: Array<{
|
|
18
|
+
userAgents: string[];
|
|
19
|
+
rules: Array<{
|
|
20
|
+
type: 'allow' | 'disallow';
|
|
21
|
+
path: string;
|
|
22
|
+
line: number;
|
|
23
|
+
}>;
|
|
24
|
+
crawlDelay?: number;
|
|
25
|
+
}>;
|
|
26
|
+
sitemaps: string[];
|
|
27
|
+
host?: string;
|
|
28
|
+
blocksAllRobots: boolean;
|
|
29
|
+
blocksImportantPaths: boolean;
|
|
30
|
+
size: number;
|
|
31
|
+
};
|
|
32
|
+
type ReckerRobotsValidationIssue = {
|
|
33
|
+
type: 'error' | 'warning' | 'info';
|
|
34
|
+
code: string;
|
|
35
|
+
message: string;
|
|
36
|
+
line?: number;
|
|
37
|
+
recommendation?: string;
|
|
38
|
+
};
|
|
39
|
+
type ReckerRobotsValidationResult = {
|
|
40
|
+
valid: boolean;
|
|
41
|
+
issues: ReckerRobotsValidationIssue[];
|
|
42
|
+
parseResult: ReckerRobotsParseResult;
|
|
43
|
+
};
|
|
44
|
+
export interface RobotsValidationDetails {
|
|
45
|
+
valid: boolean;
|
|
46
|
+
issues: ReckerRobotsValidationIssue[];
|
|
47
|
+
blocksAllRobots: boolean;
|
|
48
|
+
blocksImportantPaths: boolean;
|
|
49
|
+
host?: string;
|
|
50
|
+
size: number;
|
|
51
|
+
}
|
|
52
|
+
export declare class ReckerRobotsValidator {
|
|
53
|
+
private config;
|
|
54
|
+
private _context;
|
|
55
|
+
private cache;
|
|
56
|
+
private fetcher;
|
|
57
|
+
private _httpClient;
|
|
58
|
+
private reckerAvailable;
|
|
59
|
+
private parseRobotsTxt;
|
|
60
|
+
private validateRobotsTxt;
|
|
61
|
+
private isPathAllowed;
|
|
62
|
+
private fetchAndValidateRobotsTxt;
|
|
63
|
+
private fallbackParser;
|
|
64
|
+
constructor(config?: RobotsParserConfig);
|
|
65
|
+
private _checkReckerAvailability;
|
|
66
|
+
private _getFallbackParser;
|
|
67
|
+
setFetcher(fetcher: (url: string) => Promise<string>): void;
|
|
68
|
+
isAllowed(url: string): Promise<RobotsCheckResult>;
|
|
69
|
+
private _getCachedOrFetch;
|
|
70
|
+
private _getHttpClient;
|
|
71
|
+
private _fetchRobotsTxt;
|
|
72
|
+
private _getCrawlDelayFromParseResult;
|
|
73
|
+
private _findMatchedRule;
|
|
74
|
+
private _pathMatches;
|
|
75
|
+
getSitemaps(domain: string): Promise<string[]>;
|
|
76
|
+
getCrawlDelay(domain: string): Promise<number | null>;
|
|
77
|
+
preload(domain: string): Promise<void>;
|
|
78
|
+
clearCache(domain?: string): void;
|
|
79
|
+
getCacheStats(): CacheStats;
|
|
80
|
+
validate(url: string): Promise<RobotsValidationDetails | null>;
|
|
81
|
+
validateContent(content: string, baseUrl?: string): Promise<ReckerRobotsValidationResult | null>;
|
|
82
|
+
parseContent(content: string): ReckerRobotsParseResult | null;
|
|
83
|
+
getBlockingStatus(domain: string): {
|
|
84
|
+
blocksAllRobots: boolean;
|
|
85
|
+
blocksImportantPaths: boolean;
|
|
86
|
+
} | null;
|
|
87
|
+
getHost(domain: string): string | null;
|
|
88
|
+
getValidationIssues(domain: string): Promise<ReckerRobotsValidationIssue[]>;
|
|
89
|
+
isReckerEnabled(): boolean;
|
|
90
|
+
}
|
|
91
|
+
export default ReckerRobotsValidator;
|
|
92
|
+
//# sourceMappingURL=recker-robots-validator.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"recker-robots-validator.d.ts","sourceRoot":"","sources":["../../../../src/plugins/spider/recker-robots-validator.ts"],"names":[],"mappings":"AAEA,OAAO,KAAK,EAAE,iBAAiB,EAAE,kBAAkB,EAAE,UAAU,EAAe,MAAM,oBAAoB,CAAC;AAEzG,KAAK,uBAAuB,GAAG;IAC7B,KAAK,EAAE,OAAO,CAAC;IACf,MAAM,EAAE,KAAK,CAAC;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,CAAA;KAAE,CAAC,CAAC;IACjD,QAAQ,EAAE,KAAK,CAAC;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,CAAA;KAAE,CAAC,CAAC;IACnD,UAAU,EAAE,KAAK,CAAC;QAChB,IAAI,EAAE,YAAY,GAAG,OAAO,GAAG,UAAU,GAAG,SAAS,GAAG,aAAa,GAAG,MAAM,GAAG,aAAa,CAAC;QAC/F,KAAK,EAAE,MAAM,CAAC;QACd,IAAI,EAAE,MAAM,CAAC;KACd,CAAC,CAAC;IACH,eAAe,EAAE,KAAK,CAAC;QACrB,UAAU,EAAE,MAAM,EAAE,CAAC;QACrB,KAAK,EAAE,KAAK,CAAC;YAAE,IAAI,EAAE,OAAO,GAAG,UAAU,CAAC;YAAC,IAAI,EAAE,MAAM,CAAC;YAAC,IAAI,EAAE,MAAM,CAAA;SAAE,CAAC,CAAC;QACzE,UAAU,CAAC,EAAE,MAAM,CAAC;KACrB,CAAC,CAAC;IACH,QAAQ,EAAE,MAAM,EAAE,CAAC;IACnB,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,eAAe,EAAE,OAAO,CAAC;IACzB,oBAAoB,EAAE,OAAO,CAAC;IAC9B,IAAI,EAAE,MAAM,CAAC;CACd,CAAC;AAEF,KAAK,2BAA2B,GAAG;IACjC,IAAI,EAAE,OAAO,GAAG,SAAS,GAAG,MAAM,CAAC;IACnC,IAAI,EAAE,MAAM,CAAC;IACb,OAAO,EAAE,MAAM,CAAC;IAChB,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,cAAc,CAAC,EAAE,MAAM,CAAC;CACzB,CAAC;AAEF,KAAK,4BAA4B,GAAG;IAClC,KAAK,EAAE,OAAO,CAAC;IACf,MAAM,EAAE,2BAA2B,EAAE,CAAC;IACtC,WAAW,EAAE,uBAAuB,CAAC;CACtC,CAAC;AAuBF,MAAM,WAAW,uBAAuB;IACtC,KAAK,EAAE,OAAO,CAAC;IACf,MAAM,EAAE,2BAA2B,EAAE,CAAC;IACtC,eAAe,EAAE,OAAO,CAAC;IACzB,oBAAoB,EAAE,OAAO,CAAC;IAC9B,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,IAAI,EAAE,MAAM,CAAC;CACd;AAED,qBAAa,qBAAqB;IAChC,OAAO,CAAC,MAAM,CAGZ;IACF,OAAO,CAAC,QAAQ,CAAsB;IACtC,OAAO,CAAC,KAAK,CAA0B;IACvC,OAAO,CAAC,OAAO,CAA4C;IAC3D,OAAO,CAAC,WAAW,CAAoB;IAEvC,OAAO,CAAC,eAAe,CAAwB;IAC/C,OAAO,CAAC,cAAc,CAAqC;IAC3D,OAAO,CAAC,iBAAiB,CAAwC;IACjE,OAAO,CAAC,aAAa,CAAoC;IACzD,OAAO,CAAC,yBAAyB,CAAuC;IACxE,OAAO,CAAC,cAAc,CAA0D;gBAEpE,MAAM,GAAE,kBAAuB;YAgB7B,wBAAwB;YAmBxB,kBAAkB;IAQhC,UAAU,CAAC,OAAO,EAAE,CAAC,GAAG,EAAE,MAAM,KAAK,OAAO,CAAC,MAAM,CAAC,GAAG,IAAI;IAOrD,SAAS,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC,iBAAiB,CAAC;YAuC1C,iBAAiB;YAsCjB,cAAc;YAyBd,eAAe;IAkB7B,OAAO,CAAC,6BAA6B;IA8BrC,OAAO,CAAC,gBAAgB;IAoDxB,OAAO,CAAC,YAAY;IAcd,WAAW,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,EAAE,CAAC;IAY9C,aAAa,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,GAAG,IAAI,CAAC;IAcrD,OAAO,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC;IAI5C,UAAU,CAAC,MAAM,CAAC,EAAE,MAAM,GAAG,IAAI;IAQjC,aAAa,IAAI,UAAU;IAOrB,QAAQ,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC,uBAAuB,GAAG,IAAI,CAAC;IA6B9D,eAAe,CAAC,OAAO,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,MAAM,GAAG,OAAO,CAAC,4BAA4B,GAAG,IAAI,CAAC;IAUtG,YAAY,CAAC,OAAO,EAAE,MAAM,GAAG,uBAAuB,GAAG,IAAI;IAQ7D,iBAAiB,CAAC,MAAM,EAAE,MAAM,GAAG;QACjC,eAAe,EAAE,OAAO,CAAC;QACzB,oBAAoB,EAAE,OAAO,CAAC;KAC/B,GAAG,IAAI;IAUR,OAAO,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,GAAG,IAAI;IAKhC,mBAAmB,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,2BAA2B,EAAE,CAAC;IAKjF,eAAe,IAAI,OAAO;CAG3B;AAED,eAAe,qBAAqB,CAAC"}
|
|
@@ -0,0 +1,83 @@
|
|
|
1
|
+
import type { SecurityAnalyzerConfig, SecurityAnalysisResult } from './security-analyzer.js';
|
|
2
|
+
type ReckerSecurityReport = {
|
|
3
|
+
grade: string;
|
|
4
|
+
score: number;
|
|
5
|
+
details: Array<{
|
|
6
|
+
header: string;
|
|
7
|
+
value?: string;
|
|
8
|
+
status: 'pass' | 'warn' | 'fail';
|
|
9
|
+
score: number;
|
|
10
|
+
message: string;
|
|
11
|
+
recommendation?: string;
|
|
12
|
+
}>;
|
|
13
|
+
csp?: {
|
|
14
|
+
raw: string;
|
|
15
|
+
directives: Array<{
|
|
16
|
+
name: string;
|
|
17
|
+
values: string[];
|
|
18
|
+
issues: string[];
|
|
19
|
+
severity: 'safe' | 'warn' | 'dangerous';
|
|
20
|
+
}>;
|
|
21
|
+
issues: string[];
|
|
22
|
+
score: number;
|
|
23
|
+
hasUnsafeInline: boolean;
|
|
24
|
+
hasUnsafeEval: boolean;
|
|
25
|
+
hasWildcard: boolean;
|
|
26
|
+
missingDirectives: string[];
|
|
27
|
+
};
|
|
28
|
+
summary: {
|
|
29
|
+
passed: number;
|
|
30
|
+
warnings: number;
|
|
31
|
+
failed: number;
|
|
32
|
+
};
|
|
33
|
+
};
|
|
34
|
+
interface Page {
|
|
35
|
+
on(event: 'response', handler: (response: PageResponse) => void): void;
|
|
36
|
+
on(event: 'console', handler: (msg: ConsoleMessage) => void): void;
|
|
37
|
+
removeListener(event: string, handler: (...args: unknown[]) => void): void;
|
|
38
|
+
content(): Promise<string>;
|
|
39
|
+
evaluateOnNewDocument(fn: string): Promise<void>;
|
|
40
|
+
waitForTimeout(ms: number): Promise<void>;
|
|
41
|
+
evaluate<T>(fn: () => T | Promise<T>): Promise<T>;
|
|
42
|
+
}
|
|
43
|
+
interface PageResponse {
|
|
44
|
+
url(): string;
|
|
45
|
+
headers(): Record<string, string>;
|
|
46
|
+
}
|
|
47
|
+
interface ConsoleMessage {
|
|
48
|
+
type(): string;
|
|
49
|
+
text(): string;
|
|
50
|
+
location(): unknown;
|
|
51
|
+
args(): unknown[];
|
|
52
|
+
}
|
|
53
|
+
export declare class ReckerSecurityAdapter {
|
|
54
|
+
private config;
|
|
55
|
+
private reckerAvailable;
|
|
56
|
+
private analyzeSecurityHeaders;
|
|
57
|
+
private fallbackAnalyzer;
|
|
58
|
+
private reckerGrade;
|
|
59
|
+
private reckerScore;
|
|
60
|
+
constructor(config?: SecurityAnalyzerConfig);
|
|
61
|
+
private _checkReckerAvailability;
|
|
62
|
+
private _getFallbackAnalyzer;
|
|
63
|
+
analyze(page: Page, baseUrl: string, html?: string, responseHeaders?: Record<string, string>): Promise<SecurityAnalysisResult>;
|
|
64
|
+
analyzeSelective(page: Page, baseUrl: string, html?: string, activities?: string[], responseHeaders?: Record<string, string>): Promise<SecurityAnalysisResult>;
|
|
65
|
+
private _analyzeWithReckerAndPuppeteer;
|
|
66
|
+
private _analyzeSelectiveWithRecker;
|
|
67
|
+
private _analyzeHeadersWithRecker;
|
|
68
|
+
private _mapReckerToSecurityResult;
|
|
69
|
+
private _mergeResults;
|
|
70
|
+
private _mapReckerHeaders;
|
|
71
|
+
private _mapReckerCSP;
|
|
72
|
+
private _mapCORS;
|
|
73
|
+
private _mapTLS;
|
|
74
|
+
getReckerGrade(): string | null;
|
|
75
|
+
getReckerScore(): number | null;
|
|
76
|
+
analyzeHeadersOnly(headers: Record<string, string>): Promise<{
|
|
77
|
+
grade: string;
|
|
78
|
+
score: number;
|
|
79
|
+
report: ReckerSecurityReport;
|
|
80
|
+
} | null>;
|
|
81
|
+
}
|
|
82
|
+
export default ReckerSecurityAdapter;
|
|
83
|
+
//# sourceMappingURL=recker-security-adapter.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"recker-security-adapter.d.ts","sourceRoot":"","sources":["../../../../src/plugins/spider/recker-security-adapter.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EACV,sBAAsB,EACtB,sBAAsB,EASvB,MAAM,wBAAwB,CAAC;AAEhC,KAAK,oBAAoB,GAAG;IAC1B,KAAK,EAAE,MAAM,CAAC;IACd,KAAK,EAAE,MAAM,CAAC;IACd,OAAO,EAAE,KAAK,CAAC;QACb,MAAM,EAAE,MAAM,CAAC;QACf,KAAK,CAAC,EAAE,MAAM,CAAC;QACf,MAAM,EAAE,MAAM,GAAG,MAAM,GAAG,MAAM,CAAC;QACjC,KAAK,EAAE,MAAM,CAAC;QACd,OAAO,EAAE,MAAM,CAAC;QAChB,cAAc,CAAC,EAAE,MAAM,CAAC;KACzB,CAAC,CAAC;IACH,GAAG,CAAC,EAAE;QACJ,GAAG,EAAE,MAAM,CAAC;QACZ,UAAU,EAAE,KAAK,CAAC;YAChB,IAAI,EAAE,MAAM,CAAC;YACb,MAAM,EAAE,MAAM,EAAE,CAAC;YACjB,MAAM,EAAE,MAAM,EAAE,CAAC;YACjB,QAAQ,EAAE,MAAM,GAAG,MAAM,GAAG,WAAW,CAAC;SACzC,CAAC,CAAC;QACH,MAAM,EAAE,MAAM,EAAE,CAAC;QACjB,KAAK,EAAE,MAAM,CAAC;QACd,eAAe,EAAE,OAAO,CAAC;QACzB,aAAa,EAAE,OAAO,CAAC;QACvB,WAAW,EAAE,OAAO,CAAC;QACrB,iBAAiB,EAAE,MAAM,EAAE,CAAC;KAC7B,CAAC;IACF,OAAO,EAAE;QACP,MAAM,EAAE,MAAM,CAAC;QACf,QAAQ,EAAE,MAAM,CAAC;QACjB,MAAM,EAAE,MAAM,CAAC;KAChB,CAAC;CACH,CAAC;AAIF,UAAU,IAAI;IACZ,EAAE,CAAC,KAAK,EAAE,UAAU,EAAE,OAAO,EAAE,CAAC,QAAQ,EAAE,YAAY,KAAK,IAAI,GAAG,IAAI,CAAC;IACvE,EAAE,CAAC,KAAK,EAAE,SAAS,EAAE,OAAO,EAAE,CAAC,GAAG,EAAE,cAAc,KAAK,IAAI,GAAG,IAAI,CAAC;IACnE,cAAc,CAAC,KAAK,EAAE,MAAM,EAAE,OAAO,EAAE,CAAC,GAAG,IAAI,EAAE,OAAO,EAAE,KAAK,IAAI,GAAG,IAAI,CAAC;IAC3E,OAAO,IAAI,OAAO,CAAC,MAAM,CAAC,CAAC;IAC3B,qBAAqB,CAAC,EAAE,EAAE,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC;IACjD,cAAc,CAAC,EAAE,EAAE,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC;IAC1C,QAAQ,CAAC,CAAC,EAAE,EAAE,EAAE,MAAM,CAAC,GAAG,OAAO,CAAC,CAAC,CAAC,GAAG,OAAO,CAAC,CAAC,CAAC,CAAC;CACnD;AAED,UAAU,YAAY;IACpB,GAAG,IAAI,MAAM,CAAC;IACd,OAAO,IAAI,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;CACnC;AAED,UAAU,cAAc;IACtB,IAAI,IAAI,MAAM,CAAC;IACf,IAAI,IAAI,MAAM,CAAC;IACf,QAAQ,IAAI,OAAO,CAAC;IACpB,IAAI,IAAI,OAAO,EAAE,CAAC;CACnB;AAaD,qBAAa,qBAAqB;IAChC,OAAO,CAAC,MAAM,CAAmC;IACjD,OAAO,CAAC,eAAe,CAAwB;IAC/C,OAAO,CAAC,sBAAsB,CAA6C;IAC3E,OAAO,CAAC,gBAAgB,CAAkE;IAC1F,OAAO,CAAC,WAAW,CAAuB;IAC1C,OAAO,CAAC,WAAW,CAAuB;gBAE9B,MAAM,GAAE,sBAA2B;YAejC,wBAAwB;YAmBxB,oBAAoB;IAQ5B,OAAO,CACX,IAAI,EAAE,IAAI,EACV,OAAO,EAAE,MAAM,EACf,IAAI,CAAC,EAAE,MAAM,EACb,eAAe,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,GACvC,OAAO,CAAC,sBAAsB,CAAC;IAW5B,gBAAgB,CACpB,IAAI,EAAE,IAAI,EACV,OAAO,EAAE,MAAM,EACf,IAAI,CAAC,EAAE,MAAM,EACb,UAAU,GAAE,MAAM,EAAO,EACzB,eAAe,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,GACvC,OAAO,CAAC,sBAAsB,CAAC;YAepB,8BAA8B;YAe9B,2BAA2B;IAiDzC,OAAO,CAAC,yBAAyB;IAiCjC,OAAO,CAAC,0BAA0B;IAgBlC,OAAO,CAAC,aAAa;IAiBrB,OAAO,CAAC,iBAAiB;IA0CzB,OAAO,CAAC,aAAa;IAgDrB,OAAO,CAAC,QAAQ;IA2ChB,OAAO,CAAC,OAAO;IA2Bf,cAAc,IAAI,MAAM,GAAG,IAAI;IAI/B,cAAc,IAAI,MAAM,GAAG,IAAI;IAIzB,kBAAkB,CAAC,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,GAAG,OAAO,CAAC;QACjE,KAAK,EAAE,MAAM,CAAC;QACd,KAAK,EAAE,MAAM,CAAC;QACd,MAAM,EAAE,oBAAoB,CAAC;KAC9B,GAAG,IAAI,CAAC;CAgBV;AAED,eAAe,qBAAqB,CAAC"}
|
|
@@ -0,0 +1,187 @@
|
|
|
1
|
+
import type { AnalysisResult, SEOAnalyzerConfig } from './seo-analyzer.js';
|
|
2
|
+
type ReckerSeoReport = {
|
|
3
|
+
url: string;
|
|
4
|
+
timestamp: Date;
|
|
5
|
+
grade: string;
|
|
6
|
+
score: number;
|
|
7
|
+
summary: {
|
|
8
|
+
totalChecks: number;
|
|
9
|
+
passed: number;
|
|
10
|
+
warnings: number;
|
|
11
|
+
errors: number;
|
|
12
|
+
infos: number;
|
|
13
|
+
passRate: number;
|
|
14
|
+
issuesByCategory: Record<string, {
|
|
15
|
+
passed: number;
|
|
16
|
+
warnings: number;
|
|
17
|
+
errors: number;
|
|
18
|
+
}>;
|
|
19
|
+
topIssues: Array<{
|
|
20
|
+
name: string;
|
|
21
|
+
message: string;
|
|
22
|
+
category: string;
|
|
23
|
+
severity: 'error' | 'warning';
|
|
24
|
+
}>;
|
|
25
|
+
quickWins: string[];
|
|
26
|
+
vitals: {
|
|
27
|
+
htmlSize?: number;
|
|
28
|
+
domElements?: number;
|
|
29
|
+
ttfb?: number;
|
|
30
|
+
totalTime?: number;
|
|
31
|
+
wordCount: number;
|
|
32
|
+
totalWordCount?: number;
|
|
33
|
+
readingTime: number;
|
|
34
|
+
imageCount: number;
|
|
35
|
+
linkCount: number;
|
|
36
|
+
};
|
|
37
|
+
completeness: {
|
|
38
|
+
meta: number;
|
|
39
|
+
social: number;
|
|
40
|
+
technical: number;
|
|
41
|
+
content: number;
|
|
42
|
+
images: number;
|
|
43
|
+
links: number;
|
|
44
|
+
};
|
|
45
|
+
};
|
|
46
|
+
checks: Array<{
|
|
47
|
+
name: string;
|
|
48
|
+
category: string;
|
|
49
|
+
status: 'pass' | 'warn' | 'fail' | 'info';
|
|
50
|
+
message: string;
|
|
51
|
+
value?: string | number;
|
|
52
|
+
recommendation?: string;
|
|
53
|
+
}>;
|
|
54
|
+
title?: {
|
|
55
|
+
text: string;
|
|
56
|
+
length: number;
|
|
57
|
+
};
|
|
58
|
+
metaDescription?: {
|
|
59
|
+
text: string;
|
|
60
|
+
length: number;
|
|
61
|
+
};
|
|
62
|
+
openGraph?: {
|
|
63
|
+
title?: string;
|
|
64
|
+
description?: string;
|
|
65
|
+
image?: string;
|
|
66
|
+
url?: string;
|
|
67
|
+
type?: string;
|
|
68
|
+
siteName?: string;
|
|
69
|
+
};
|
|
70
|
+
twitterCard?: {
|
|
71
|
+
card?: string;
|
|
72
|
+
title?: string;
|
|
73
|
+
description?: string;
|
|
74
|
+
image?: string;
|
|
75
|
+
site?: string;
|
|
76
|
+
};
|
|
77
|
+
structuredData: {
|
|
78
|
+
count: number;
|
|
79
|
+
types: string[];
|
|
80
|
+
items: Record<string, unknown>[];
|
|
81
|
+
};
|
|
82
|
+
content: {
|
|
83
|
+
wordCount: number;
|
|
84
|
+
totalWordCount?: number;
|
|
85
|
+
characterCount: number;
|
|
86
|
+
sentenceCount: number;
|
|
87
|
+
paragraphCount: number;
|
|
88
|
+
readingTimeMinutes: number;
|
|
89
|
+
avgWordsPerSentence: number;
|
|
90
|
+
avgParagraphLength: number;
|
|
91
|
+
listCount: number;
|
|
92
|
+
strongTagCount: number;
|
|
93
|
+
emTagCount: number;
|
|
94
|
+
fleschReadingEase?: number;
|
|
95
|
+
hasQuestionHeadings?: boolean;
|
|
96
|
+
};
|
|
97
|
+
headings: {
|
|
98
|
+
structure: Array<{
|
|
99
|
+
level: number;
|
|
100
|
+
text: string;
|
|
101
|
+
count: number;
|
|
102
|
+
}>;
|
|
103
|
+
h1Count: number;
|
|
104
|
+
hasProperHierarchy: boolean;
|
|
105
|
+
issues: string[];
|
|
106
|
+
};
|
|
107
|
+
keywords: {
|
|
108
|
+
primary: string | null;
|
|
109
|
+
secondary: string[];
|
|
110
|
+
density: Record<string, number>;
|
|
111
|
+
};
|
|
112
|
+
links: {
|
|
113
|
+
total: number;
|
|
114
|
+
internal: number;
|
|
115
|
+
external: number;
|
|
116
|
+
nofollow: number;
|
|
117
|
+
broken: number;
|
|
118
|
+
withoutText: number;
|
|
119
|
+
sponsoredLinks: number;
|
|
120
|
+
ugcLinks: number;
|
|
121
|
+
internalHttpLinks?: number;
|
|
122
|
+
internalHttpLinkUrls?: string[];
|
|
123
|
+
};
|
|
124
|
+
images: {
|
|
125
|
+
total: number;
|
|
126
|
+
withAlt: number;
|
|
127
|
+
withoutAlt: number;
|
|
128
|
+
lazy: number;
|
|
129
|
+
missingDimensions: number;
|
|
130
|
+
modernFormats: number;
|
|
131
|
+
altTextLengths: number[];
|
|
132
|
+
imageAltTexts: string[];
|
|
133
|
+
imageFilenames: string[];
|
|
134
|
+
imagesWithAsyncDecoding: number;
|
|
135
|
+
};
|
|
136
|
+
social: {
|
|
137
|
+
openGraph: {
|
|
138
|
+
present: boolean;
|
|
139
|
+
hasTitle: boolean;
|
|
140
|
+
hasDescription: boolean;
|
|
141
|
+
hasImage: boolean;
|
|
142
|
+
hasUrl: boolean;
|
|
143
|
+
issues: string[];
|
|
144
|
+
};
|
|
145
|
+
twitterCard: {
|
|
146
|
+
present: boolean;
|
|
147
|
+
hasCard: boolean;
|
|
148
|
+
hasTitle: boolean;
|
|
149
|
+
hasDescription: boolean;
|
|
150
|
+
hasImage: boolean;
|
|
151
|
+
issues: string[];
|
|
152
|
+
};
|
|
153
|
+
};
|
|
154
|
+
technical: {
|
|
155
|
+
hasCanonical: boolean;
|
|
156
|
+
canonicalUrl?: string;
|
|
157
|
+
hasRobotsMeta: boolean;
|
|
158
|
+
robotsContent?: string[];
|
|
159
|
+
hasViewport: boolean;
|
|
160
|
+
hasCharset: boolean;
|
|
161
|
+
hasLang: boolean;
|
|
162
|
+
langValue?: string;
|
|
163
|
+
};
|
|
164
|
+
};
|
|
165
|
+
export declare class ReckerSEOAdapter {
|
|
166
|
+
private config;
|
|
167
|
+
private reckerAvailable;
|
|
168
|
+
private analyzeSeo;
|
|
169
|
+
private fallbackAnalyzer;
|
|
170
|
+
constructor(config?: SEOAnalyzerConfig);
|
|
171
|
+
private _checkReckerAvailability;
|
|
172
|
+
private _getFallbackAnalyzer;
|
|
173
|
+
analyze(html: string, baseUrl: string): Promise<AnalysisResult>;
|
|
174
|
+
analyzeSelective(html: string, baseUrl: string, activities?: string[]): Promise<AnalysisResult>;
|
|
175
|
+
private _analyzeWithRecker;
|
|
176
|
+
private _mapActivitiesToCategories;
|
|
177
|
+
private _mapReckerToAnalysisResult;
|
|
178
|
+
private _mapOnPageSEO;
|
|
179
|
+
private _mapAccessibility;
|
|
180
|
+
private _mapInternalLinks;
|
|
181
|
+
private _mapKeywordOptimization;
|
|
182
|
+
private _mapSEOScore;
|
|
183
|
+
getReckerGrade(): string | null;
|
|
184
|
+
getDetailedReport(html: string, baseUrl: string): Promise<ReckerSeoReport | null>;
|
|
185
|
+
}
|
|
186
|
+
export default ReckerSEOAdapter;
|
|
187
|
+
//# sourceMappingURL=recker-seo-adapter.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"recker-seo-adapter.d.ts","sourceRoot":"","sources":["../../../../src/plugins/spider/recker-seo-adapter.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EACV,cAAc,EACd,iBAAiB,EAOlB,MAAM,mBAAmB,CAAC;AAE3B,KAAK,eAAe,GAAG;IACrB,GAAG,EAAE,MAAM,CAAC;IACZ,SAAS,EAAE,IAAI,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,KAAK,EAAE,MAAM,CAAC;IACd,OAAO,EAAE;QACP,WAAW,EAAE,MAAM,CAAC;QACpB,MAAM,EAAE,MAAM,CAAC;QACf,QAAQ,EAAE,MAAM,CAAC;QACjB,MAAM,EAAE,MAAM,CAAC;QACf,KAAK,EAAE,MAAM,CAAC;QACd,QAAQ,EAAE,MAAM,CAAC;QACjB,gBAAgB,EAAE,MAAM,CAAC,MAAM,EAAE;YAAE,MAAM,EAAE,MAAM,CAAC;YAAC,QAAQ,EAAE,MAAM,CAAC;YAAC,MAAM,EAAE,MAAM,CAAA;SAAE,CAAC,CAAC;QACvF,SAAS,EAAE,KAAK,CAAC;YAAE,IAAI,EAAE,MAAM,CAAC;YAAC,OAAO,EAAE,MAAM,CAAC;YAAC,QAAQ,EAAE,MAAM,CAAC;YAAC,QAAQ,EAAE,OAAO,GAAG,SAAS,CAAA;SAAE,CAAC,CAAC;QACrG,SAAS,EAAE,MAAM,EAAE,CAAC;QACpB,MAAM,EAAE;YACN,QAAQ,CAAC,EAAE,MAAM,CAAC;YAClB,WAAW,CAAC,EAAE,MAAM,CAAC;YACrB,IAAI,CAAC,EAAE,MAAM,CAAC;YACd,SAAS,CAAC,EAAE,MAAM,CAAC;YACnB,SAAS,EAAE,MAAM,CAAC;YAClB,cAAc,CAAC,EAAE,MAAM,CAAC;YACxB,WAAW,EAAE,MAAM,CAAC;YACpB,UAAU,EAAE,MAAM,CAAC;YACnB,SAAS,EAAE,MAAM,CAAC;SACnB,CAAC;QACF,YAAY,EAAE;YACZ,IAAI,EAAE,MAAM,CAAC;YACb,MAAM,EAAE,MAAM,CAAC;YACf,SAAS,EAAE,MAAM,CAAC;YAClB,OAAO,EAAE,MAAM,CAAC;YAChB,MAAM,EAAE,MAAM,CAAC;YACf,KAAK,EAAE,MAAM,CAAC;SACf,CAAC;KACH,CAAC;IACF,MAAM,EAAE,KAAK,CAAC;QACZ,IAAI,EAAE,MAAM,CAAC;QACb,QAAQ,EAAE,MAAM,CAAC;QACjB,MAAM,EAAE,MAAM,GAAG,MAAM,GAAG,MAAM,GAAG,MAAM,CAAC;QAC1C,OAAO,EAAE,MAAM,CAAC;QAChB,KAAK,CAAC,EAAE,MAAM,GAAG,MAAM,CAAC;QACxB,cAAc,CAAC,EAAE,MAAM,CAAC;KACzB,CAAC,CAAC;IACH,KAAK,CAAC,EAAE;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,MAAM,EAAE,MAAM,CAAA;KAAE,CAAC;IACzC,eAAe,CAAC,EAAE;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,MAAM,EAAE,MAAM,CAAA;KAAE,CAAC;IACnD,SAAS,CAAC,EAAE;QACV,KAAK,CAAC,EAAE,MAAM,CAAC;QACf,WAAW,CAAC,EAAE,MAAM,CAAC;QACrB,KAAK,CAAC,EAAE,MAAM,CAAC;QACf,GAAG,CAAC,EAAE,MAAM,CAAC;QACb,IAAI,CAAC,EAAE,MAAM,CAAC;QACd,QAAQ,CAAC,EAAE,MAAM,CAAC;KACnB,CAAC;IACF,WAAW,CAAC,EAAE;QACZ,IAAI,CAAC,EAAE,MAAM,CAAC;QACd,KAAK,CAAC,EAAE,MAAM,CAAC;QACf,WAAW,CAAC,EAAE,MAAM,CAAC;QACrB,KAAK,CAAC,EAAE,MAAM,CAAC;QACf,IAAI,CAAC,EAAE,MAAM,CAAC;KACf,CAAC;IACF,cAAc,EAAE;QACd,KAAK,EAAE,MAAM,CAAC;QACd,KAAK,EAAE,MAAM,EAAE,CAAC;QAChB,KAAK,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,EAAE,CAAC;KAClC,CAAC;IACF,OAAO,EAAE;QACP,SAAS,EAAE,MAAM,CAAC;QAClB,cAAc,CAAC,EAAE,MAAM,CAAC;QACxB,cAAc,EAAE,MAAM,CAAC;QACvB,aAAa,EAAE,MAAM,CAAC;QACtB,cAAc,EAAE,MAAM,CAAC;QACvB,kBAAkB,EAAE,MAAM,CAAC;QAC3B,mBAAmB,EAAE,MAAM,CAAC;QAC5B,kBAAkB,EAAE,MAAM,CAAC;QAC3B,SAAS,EAAE,MAAM,CAAC;QAClB,cAAc,EAAE,MAAM,CAAC;QACvB,UAAU,EAAE,MAAM,CAAC;QACnB,iBAAiB,CAAC,EAAE,MAAM,CAAC;QAC3B,mBAAmB,CAAC,EAAE,OAAO,CAAC;KAC/B,CAAC;IACF,QAAQ,EAAE;QACR,SAAS,EAAE,KAAK,CAAC;YAAE,KAAK,EAAE,MAAM,CAAC;YAAC,IAAI,EAAE,MAAM,CAAC;YAAC,KAAK,EAAE,MAAM,CAAA;SAAE,CAAC,CAAC;QACjE,OAAO,EAAE,MAAM,CAAC;QAChB,kBAAkB,EAAE,OAAO,CAAC;QAC5B,MAAM,EAAE,MAAM,EAAE,CAAC;KAClB,CAAC;IACF,QAAQ,EAAE;QACR,OAAO,EAAE,MAAM,GAAG,IAAI,CAAC;QACvB,SAAS,EAAE,MAAM,EAAE,CAAC;QACpB,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;KACjC,CAAC;IACF,KAAK,EAAE;QACL,KAAK,EAAE,MAAM,CAAC;QACd,QAAQ,EAAE,MAAM,CAAC;QACjB,QAAQ,EAAE,MAAM,CAAC;QACjB,QAAQ,EAAE,MAAM,CAAC;QACjB,MAAM,EAAE,MAAM,CAAC;QACf,WAAW,EAAE,MAAM,CAAC;QACpB,cAAc,EAAE,MAAM,CAAC;QACvB,QAAQ,EAAE,MAAM,CAAC;QACjB,iBAAiB,CAAC,EAAE,MAAM,CAAC;QAC3B,oBAAoB,CAAC,EAAE,MAAM,EAAE,CAAC;KACjC,CAAC;IACF,MAAM,EAAE;QACN,KAAK,EAAE,MAAM,CAAC;QACd,OAAO,EAAE,MAAM,CAAC;QAChB,UAAU,EAAE,MAAM,CAAC;QACnB,IAAI,EAAE,MAAM,CAAC;QACb,iBAAiB,EAAE,MAAM,CAAC;QAC1B,aAAa,EAAE,MAAM,CAAC;QACtB,cAAc,EAAE,MAAM,EAAE,CAAC;QACzB,aAAa,EAAE,MAAM,EAAE,CAAC;QACxB,cAAc,EAAE,MAAM,EAAE,CAAC;QACzB,uBAAuB,EAAE,MAAM,CAAC;KACjC,CAAC;IACF,MAAM,EAAE;QACN,SAAS,EAAE;YACT,OAAO,EAAE,OAAO,CAAC;YACjB,QAAQ,EAAE,OAAO,CAAC;YAClB,cAAc,EAAE,OAAO,CAAC;YACxB,QAAQ,EAAE,OAAO,CAAC;YAClB,MAAM,EAAE,OAAO,CAAC;YAChB,MAAM,EAAE,MAAM,EAAE,CAAC;SAClB,CAAC;QACF,WAAW,EAAE;YACX,OAAO,EAAE,OAAO,CAAC;YACjB,OAAO,EAAE,OAAO,CAAC;YACjB,QAAQ,EAAE,OAAO,CAAC;YAClB,cAAc,EAAE,OAAO,CAAC;YACxB,QAAQ,EAAE,OAAO,CAAC;YAClB,MAAM,EAAE,MAAM,EAAE,CAAC;SAClB,CAAC;KACH,CAAC;IACF,SAAS,EAAE;QACT,YAAY,EAAE,OAAO,CAAC;QACtB,YAAY,CAAC,EAAE,MAAM,CAAC;QACtB,aAAa,EAAE,OAAO,CAAC;QACvB,aAAa,CAAC,EAAE,MAAM,EAAE,CAAC;QACzB,WAAW,EAAE,OAAO,CAAC;QACrB,UAAU,EAAE,OAAO,CAAC;QACpB,OAAO,EAAE,OAAO,CAAC;QACjB,SAAS,CAAC,EAAE,MAAM,CAAC;KACpB,CAAC;CACH,CAAC;AA0BF,qBAAa,gBAAgB;IAC3B,OAAO,CAAC,MAAM,CAA8B;IAC5C,OAAO,CAAC,eAAe,CAAwB;IAC/C,OAAO,CAAC,UAAU,CAAiC;IACnD,OAAO,CAAC,gBAAgB,CAAwD;gBAEpE,MAAM,GAAE,iBAAsB;YAc5B,wBAAwB;YAmBxB,oBAAoB;IAQ5B,OAAO,CAAC,IAAI,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,GAAG,OAAO,CAAC,cAAc,CAAC;IAW/D,gBAAgB,CAAC,IAAI,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,UAAU,GAAE,MAAM,EAAO,GAAG,OAAO,CAAC,cAAc,CAAC;YAgB3F,kBAAkB;IAkBhC,OAAO,CAAC,0BAA0B;IAalC,OAAO,CAAC,0BAA0B;IAwDlC,OAAO,CAAC,aAAa;IAsFrB,OAAO,CAAC,iBAAiB;IA6DzB,OAAO,CAAC,iBAAiB;IA4DzB,OAAO,CAAC,uBAAuB;IA8B/B,OAAO,CAAC,YAAY;IAQpB,cAAc,IAAI,MAAM,GAAG,IAAI;IAIzB,iBAAiB,CAAC,IAAI,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,GAAG,OAAO,CAAC,eAAe,GAAG,IAAI,CAAC;CAYxF;AAED,eAAe,gBAAgB,CAAC"}
|
|
@@ -0,0 +1,121 @@
|
|
|
1
|
+
import type { SitemapParserConfig, SitemapEntry, ParseOptions, SitemapStats, ProbeResult, FetcherResult } from './sitemap-parser.js';
|
|
2
|
+
type ReckerSitemapUrl = {
|
|
3
|
+
loc: string;
|
|
4
|
+
lastmod?: string;
|
|
5
|
+
changefreq?: 'always' | 'hourly' | 'daily' | 'weekly' | 'monthly' | 'yearly' | 'never';
|
|
6
|
+
priority?: number;
|
|
7
|
+
images?: Array<{
|
|
8
|
+
loc: string;
|
|
9
|
+
caption?: string;
|
|
10
|
+
title?: string;
|
|
11
|
+
}>;
|
|
12
|
+
videos?: Array<{
|
|
13
|
+
thumbnailLoc: string;
|
|
14
|
+
title: string;
|
|
15
|
+
description: string;
|
|
16
|
+
contentLoc?: string;
|
|
17
|
+
playerLoc?: string;
|
|
18
|
+
}>;
|
|
19
|
+
news?: {
|
|
20
|
+
publicationName: string;
|
|
21
|
+
publicationLanguage: string;
|
|
22
|
+
publicationDate: string;
|
|
23
|
+
title: string;
|
|
24
|
+
};
|
|
25
|
+
alternates?: Array<{
|
|
26
|
+
hreflang: string;
|
|
27
|
+
href: string;
|
|
28
|
+
}>;
|
|
29
|
+
};
|
|
30
|
+
type ReckerSitemapIndex = {
|
|
31
|
+
loc: string;
|
|
32
|
+
lastmod?: string;
|
|
33
|
+
};
|
|
34
|
+
type ReckerSitemapParseResult = {
|
|
35
|
+
type: 'urlset' | 'sitemapindex' | 'unknown';
|
|
36
|
+
valid: boolean;
|
|
37
|
+
errors: string[];
|
|
38
|
+
warnings: string[];
|
|
39
|
+
urls: ReckerSitemapUrl[];
|
|
40
|
+
sitemaps: ReckerSitemapIndex[];
|
|
41
|
+
urlCount: number;
|
|
42
|
+
size: number;
|
|
43
|
+
compressed: boolean;
|
|
44
|
+
};
|
|
45
|
+
type ReckerSitemapValidationIssue = {
|
|
46
|
+
type: 'error' | 'warning' | 'info';
|
|
47
|
+
code: string;
|
|
48
|
+
message: string;
|
|
49
|
+
url?: string;
|
|
50
|
+
recommendation?: string;
|
|
51
|
+
};
|
|
52
|
+
type ReckerSitemapValidationResult = {
|
|
53
|
+
valid: boolean;
|
|
54
|
+
issues: ReckerSitemapValidationIssue[];
|
|
55
|
+
parseResult: ReckerSitemapParseResult;
|
|
56
|
+
};
|
|
57
|
+
export interface SitemapValidationDetails {
|
|
58
|
+
valid: boolean;
|
|
59
|
+
issues: ReckerSitemapValidationIssue[];
|
|
60
|
+
type: 'urlset' | 'sitemapindex' | 'unknown';
|
|
61
|
+
urlCount: number;
|
|
62
|
+
size: number;
|
|
63
|
+
compressed: boolean;
|
|
64
|
+
errors: string[];
|
|
65
|
+
warnings: string[];
|
|
66
|
+
}
|
|
67
|
+
export interface SitemapEntryExtended extends SitemapEntry {
|
|
68
|
+
news?: {
|
|
69
|
+
publicationName: string;
|
|
70
|
+
publicationLanguage: string;
|
|
71
|
+
publicationDate: string;
|
|
72
|
+
title: string;
|
|
73
|
+
};
|
|
74
|
+
alternates?: Array<{
|
|
75
|
+
hreflang: string;
|
|
76
|
+
href: string;
|
|
77
|
+
}>;
|
|
78
|
+
}
|
|
79
|
+
export declare class ReckerSitemapValidator {
|
|
80
|
+
private config;
|
|
81
|
+
private _context;
|
|
82
|
+
private cache;
|
|
83
|
+
private fetcher;
|
|
84
|
+
private _httpClient;
|
|
85
|
+
private stats;
|
|
86
|
+
private reckerAvailable;
|
|
87
|
+
private parseSitemap;
|
|
88
|
+
private validateSitemap;
|
|
89
|
+
private discoverSitemaps;
|
|
90
|
+
private fetchAndValidateSitemap;
|
|
91
|
+
private fallbackParser;
|
|
92
|
+
constructor(config?: SitemapParserConfig);
|
|
93
|
+
private _checkReckerAvailability;
|
|
94
|
+
private _getFallbackParser;
|
|
95
|
+
setFetcher(fetcher: (url: string) => Promise<FetcherResult>): void;
|
|
96
|
+
parse(sitemapUrl: string, options?: ParseOptions): Promise<SitemapEntry[]>;
|
|
97
|
+
private _parseReckerIndex;
|
|
98
|
+
private _mapReckerUrlsToEntries;
|
|
99
|
+
private _getHttpClient;
|
|
100
|
+
private _fetch;
|
|
101
|
+
private _decompress;
|
|
102
|
+
getStats(): SitemapStats;
|
|
103
|
+
clearCache(url?: string): void;
|
|
104
|
+
resetStats(): void;
|
|
105
|
+
discoverFromRobotsTxt(robotsTxtUrl: string): Promise<string[]>;
|
|
106
|
+
probeCommonLocations(baseUrl: string): Promise<ProbeResult[]>;
|
|
107
|
+
validate(sitemapUrl: string): Promise<SitemapValidationDetails | null>;
|
|
108
|
+
validateContent(content: string, baseUrl?: string): Promise<ReckerSitemapValidationResult | null>;
|
|
109
|
+
parseContent(content: string, compressed?: boolean): ReckerSitemapParseResult | null;
|
|
110
|
+
getValidationIssues(sitemapUrl: string): Promise<ReckerSitemapValidationIssue[]>;
|
|
111
|
+
getNewsEntries(sitemapUrl: string): Promise<SitemapEntryExtended[]>;
|
|
112
|
+
getAlternateLanguages(sitemapUrl: string): Promise<Map<string, SitemapEntryExtended[]>>;
|
|
113
|
+
discoverAll(baseUrl: string): Promise<{
|
|
114
|
+
fromRobots: string[];
|
|
115
|
+
fromProbing: ProbeResult[];
|
|
116
|
+
all: string[];
|
|
117
|
+
}>;
|
|
118
|
+
isReckerEnabled(): boolean;
|
|
119
|
+
}
|
|
120
|
+
export default ReckerSitemapValidator;
|
|
121
|
+
//# sourceMappingURL=recker-sitemap-validator.d.ts.map
|