@crawlith/core 0.1.1 → 0.1.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/LICENSE +201 -0
- package/README.md +70 -0
- package/dist/analysis/analyze.d.ts +29 -8
- package/dist/analysis/analyze.js +325 -221
- package/dist/analysis/clustering.d.ts +23 -0
- package/dist/analysis/clustering.js +206 -0
- package/dist/analysis/content.d.ts +1 -1
- package/dist/analysis/content.js +11 -5
- package/dist/analysis/duplicate.d.ts +34 -0
- package/dist/analysis/duplicate.js +305 -0
- package/dist/analysis/heading.d.ts +116 -0
- package/dist/analysis/heading.js +356 -0
- package/dist/analysis/images.d.ts +1 -1
- package/dist/analysis/images.js +6 -5
- package/dist/analysis/links.d.ts +1 -1
- package/dist/analysis/links.js +8 -8
- package/dist/{scoring/orphanSeverity.d.ts → analysis/orphan.d.ts} +12 -23
- package/dist/{scoring/orphanSeverity.js → analysis/orphan.js} +9 -3
- package/dist/analysis/scoring.js +4 -1
- package/dist/analysis/seo.d.ts +8 -4
- package/dist/analysis/seo.js +41 -30
- package/dist/analysis/soft404.d.ts +17 -0
- package/dist/analysis/soft404.js +62 -0
- package/dist/analysis/structuredData.d.ts +1 -1
- package/dist/analysis/structuredData.js +5 -4
- package/dist/application/index.d.ts +2 -0
- package/dist/application/index.js +2 -0
- package/dist/application/usecase.d.ts +3 -0
- package/dist/application/usecase.js +1 -0
- package/dist/application/usecases.d.ts +114 -0
- package/dist/application/usecases.js +201 -0
- package/dist/audit/index.js +1 -1
- package/dist/audit/transport.d.ts +1 -1
- package/dist/audit/transport.js +5 -4
- package/dist/audit/types.d.ts +1 -0
- package/dist/constants.d.ts +17 -0
- package/dist/constants.js +23 -0
- package/dist/core/scope/scopeManager.js +3 -0
- package/dist/crawler/crawl.d.ts +2 -2
- package/dist/crawler/crawler.d.ts +17 -5
- package/dist/crawler/crawler.js +259 -94
- package/dist/crawler/fetcher.d.ts +1 -1
- package/dist/crawler/fetcher.js +6 -6
- package/dist/crawler/metricsRunner.d.ts +21 -1
- package/dist/crawler/metricsRunner.js +181 -60
- package/dist/crawler/normalize.d.ts +41 -0
- package/dist/crawler/normalize.js +119 -3
- package/dist/crawler/parser.d.ts +1 -3
- package/dist/crawler/parser.js +2 -49
- package/dist/crawler/resolver.d.ts +11 -0
- package/dist/crawler/resolver.js +67 -0
- package/dist/crawler/sitemap.d.ts +4 -1
- package/dist/crawler/sitemap.js +24 -18
- package/dist/crawler/trap.d.ts +5 -1
- package/dist/crawler/trap.js +23 -2
- package/dist/db/CrawlithDB.d.ts +110 -0
- package/dist/db/CrawlithDB.js +500 -0
- package/dist/db/graphLoader.js +15 -32
- package/dist/db/index.d.ts +9 -1
- package/dist/db/index.js +39 -31
- package/dist/db/migrations.d.ts +2 -0
- package/dist/db/{schema.js → migrations.js} +90 -43
- package/dist/db/pluginRegistry.d.ts +9 -0
- package/dist/db/pluginRegistry.js +19 -0
- package/dist/db/repositories/EdgeRepository.d.ts +5 -0
- package/dist/db/repositories/EdgeRepository.js +7 -0
- package/dist/db/repositories/MetricsRepository.d.ts +13 -8
- package/dist/db/repositories/MetricsRepository.js +14 -6
- package/dist/db/repositories/PageRepository.d.ts +5 -3
- package/dist/db/repositories/PageRepository.js +68 -17
- package/dist/db/repositories/SiteRepository.d.ts +6 -0
- package/dist/db/repositories/SiteRepository.js +4 -0
- package/dist/db/repositories/SnapshotRepository.d.ts +12 -5
- package/dist/db/repositories/SnapshotRepository.js +48 -10
- package/dist/db/reset.d.ts +9 -0
- package/dist/db/reset.js +32 -0
- package/dist/db/statements.d.ts +12 -0
- package/dist/db/statements.js +40 -0
- package/dist/diff/compare.d.ts +0 -5
- package/dist/diff/compare.js +0 -12
- package/dist/diff/service.d.ts +16 -0
- package/dist/diff/service.js +41 -0
- package/dist/domain/index.d.ts +4 -0
- package/dist/domain/index.js +4 -0
- package/dist/events.d.ts +8 -0
- package/dist/graph/graph.d.ts +20 -42
- package/dist/graph/graph.js +12 -16
- package/dist/graph/hits.d.ts +23 -0
- package/dist/graph/hits.js +111 -0
- package/dist/graph/metrics.d.ts +0 -4
- package/dist/graph/metrics.js +19 -15
- package/dist/graph/pagerank.d.ts +17 -4
- package/dist/graph/pagerank.js +126 -93
- package/dist/index.d.ts +27 -9
- package/dist/index.js +27 -9
- package/dist/lock/lockManager.d.ts +1 -0
- package/dist/lock/lockManager.js +15 -0
- package/dist/plugin-system/plugin-cli.d.ts +10 -0
- package/dist/plugin-system/plugin-cli.js +31 -0
- package/dist/plugin-system/plugin-config.d.ts +16 -0
- package/dist/plugin-system/plugin-config.js +36 -0
- package/dist/plugin-system/plugin-loader.d.ts +17 -0
- package/dist/plugin-system/plugin-loader.js +122 -0
- package/dist/plugin-system/plugin-registry.d.ts +25 -0
- package/dist/plugin-system/plugin-registry.js +167 -0
- package/dist/plugin-system/plugin-types.d.ts +205 -0
- package/dist/plugin-system/plugin-types.js +1 -0
- package/dist/ports/index.d.ts +9 -0
- package/dist/ports/index.js +1 -0
- package/dist/report/export.d.ts +3 -0
- package/dist/report/export.js +81 -0
- package/dist/report/insight.d.ts +27 -0
- package/dist/report/insight.js +103 -0
- package/dist/scoring/health.d.ts +17 -11
- package/dist/scoring/health.js +183 -140
- package/dist/utils/chalk.d.ts +6 -0
- package/dist/utils/chalk.js +41 -0
- package/dist/utils/secureConfig.d.ts +23 -0
- package/dist/utils/secureConfig.js +128 -0
- package/package.json +10 -4
- package/CHANGELOG.md +0 -13
- package/dist/db/schema.d.ts +0 -2
- package/dist/graph/cluster.d.ts +0 -6
- package/dist/graph/cluster.js +0 -221
- package/dist/graph/duplicate.d.ts +0 -10
- package/dist/graph/duplicate.js +0 -302
- package/dist/scoring/hits.d.ts +0 -10
- package/dist/scoring/hits.js +0 -131
- package/scripts/copy-assets.js +0 -37
- package/src/analysis/analysis_list.html +0 -35
- package/src/analysis/analysis_page.html +0 -123
- package/src/analysis/analyze.ts +0 -505
- package/src/analysis/content.ts +0 -62
- package/src/analysis/images.ts +0 -28
- package/src/analysis/links.ts +0 -41
- package/src/analysis/scoring.ts +0 -66
- package/src/analysis/seo.ts +0 -82
- package/src/analysis/structuredData.ts +0 -62
- package/src/analysis/templates.ts +0 -9
- package/src/audit/dns.ts +0 -49
- package/src/audit/headers.ts +0 -98
- package/src/audit/index.ts +0 -66
- package/src/audit/scoring.ts +0 -232
- package/src/audit/transport.ts +0 -258
- package/src/audit/types.ts +0 -102
- package/src/core/network/proxyAdapter.ts +0 -21
- package/src/core/network/rateLimiter.ts +0 -39
- package/src/core/network/redirectController.ts +0 -47
- package/src/core/network/responseLimiter.ts +0 -34
- package/src/core/network/retryPolicy.ts +0 -57
- package/src/core/scope/domainFilter.ts +0 -45
- package/src/core/scope/scopeManager.ts +0 -52
- package/src/core/scope/subdomainPolicy.ts +0 -39
- package/src/core/security/ipGuard.ts +0 -171
- package/src/crawler/crawl.ts +0 -9
- package/src/crawler/crawler.ts +0 -601
- package/src/crawler/extract.ts +0 -39
- package/src/crawler/fetcher.ts +0 -251
- package/src/crawler/metricsRunner.ts +0 -137
- package/src/crawler/normalize.ts +0 -108
- package/src/crawler/parser.ts +0 -190
- package/src/crawler/sitemap.ts +0 -76
- package/src/crawler/trap.ts +0 -96
- package/src/db/graphLoader.ts +0 -135
- package/src/db/index.ts +0 -75
- package/src/db/repositories/EdgeRepository.ts +0 -43
- package/src/db/repositories/MetricsRepository.ts +0 -63
- package/src/db/repositories/PageRepository.ts +0 -228
- package/src/db/repositories/SiteRepository.ts +0 -43
- package/src/db/repositories/SnapshotRepository.ts +0 -99
- package/src/db/schema.ts +0 -177
- package/src/diff/compare.ts +0 -84
- package/src/events.ts +0 -16
- package/src/graph/cluster.ts +0 -246
- package/src/graph/duplicate.ts +0 -350
- package/src/graph/graph.ts +0 -192
- package/src/graph/metrics.ts +0 -125
- package/src/graph/pagerank.ts +0 -126
- package/src/graph/simhash.ts +0 -76
- package/src/index.ts +0 -33
- package/src/lock/hashKey.ts +0 -51
- package/src/lock/lockManager.ts +0 -132
- package/src/lock/pidCheck.ts +0 -13
- package/src/report/crawl.html +0 -879
- package/src/report/crawlExport.ts +0 -58
- package/src/report/crawl_template.ts +0 -9
- package/src/report/html.ts +0 -27
- package/src/scoring/health.ts +0 -241
- package/src/scoring/hits.ts +0 -153
- package/src/scoring/orphanSeverity.ts +0 -176
- package/src/utils/version.ts +0 -18
- package/tests/__snapshots__/orphanSeverity.test.ts.snap +0 -49
- package/tests/analysis.unit.test.ts +0 -142
- package/tests/analyze.integration.test.ts +0 -133
- package/tests/analyze_markdown.test.ts +0 -98
- package/tests/audit/audit.test.ts +0 -101
- package/tests/audit/dns.test.ts +0 -31
- package/tests/audit/headers.test.ts +0 -45
- package/tests/audit/scoring.test.ts +0 -133
- package/tests/audit/security.test.ts +0 -12
- package/tests/audit/transport.test.ts +0 -111
- package/tests/clustering.test.ts +0 -118
- package/tests/clustering_risk.test.ts +0 -118
- package/tests/crawler.test.ts +0 -364
- package/tests/db/index.test.ts +0 -134
- package/tests/db/repositories.test.ts +0 -115
- package/tests/db.test.ts +0 -159
- package/tests/db_repos.test.ts +0 -72
- package/tests/diff.test.ts +0 -67
- package/tests/duplicate.test.ts +0 -110
- package/tests/extract.test.ts +0 -86
- package/tests/fetcher.test.ts +0 -110
- package/tests/fetcher_safety.test.ts +0 -91
- package/tests/fixtures/analyze-crawl.json +0 -26
- package/tests/graph/graph.test.ts +0 -100
- package/tests/graphLoader.test.ts +0 -124
- package/tests/hits.test.ts +0 -134
- package/tests/html_report.test.ts +0 -59
- package/tests/ipGuard.test.ts +0 -73
- package/tests/lock/lockManager.test.ts +0 -198
- package/tests/metrics.test.ts +0 -196
- package/tests/normalize.test.ts +0 -88
- package/tests/orphanSeverity.test.ts +0 -160
- package/tests/pagerank.test.ts +0 -98
- package/tests/parser.test.ts +0 -117
- package/tests/proxy_safety.test.ts +0 -57
- package/tests/redirect_safety.test.ts +0 -77
- package/tests/renderAnalysisCsv.test.ts +0 -183
- package/tests/safety.test.ts +0 -126
- package/tests/scope.test.ts +0 -84
- package/tests/scoring.test.ts +0 -60
- package/tests/sitemap.test.ts +0 -100
- package/tests/soft404.test.ts +0 -41
- package/tests/ssrf_fix.test.ts +0 -69
- package/tests/trap.test.ts +0 -39
- package/tests/visualization_data.test.ts +0 -46
- package/tsconfig.json +0 -11
|
@@ -1,5 +1,6 @@
|
|
|
1
1
|
import { Graph } from '../graph/graph.js';
|
|
2
2
|
import { EngineContext } from '../events.js';
|
|
3
|
+
import { PluginRegistry } from '../plugin-system/plugin-registry.js';
|
|
3
4
|
export interface CrawlOptions {
|
|
4
5
|
limit: number;
|
|
5
6
|
depth: number;
|
|
@@ -7,7 +8,7 @@ export interface CrawlOptions {
|
|
|
7
8
|
ignoreRobots?: boolean;
|
|
8
9
|
stripQuery?: boolean;
|
|
9
10
|
previousGraph?: Graph;
|
|
10
|
-
sitemap?: string;
|
|
11
|
+
sitemap?: string | boolean;
|
|
11
12
|
debug?: boolean;
|
|
12
13
|
detectSoft404?: boolean;
|
|
13
14
|
detectTraps?: boolean;
|
|
@@ -19,12 +20,16 @@ export interface CrawlOptions {
|
|
|
19
20
|
proxyUrl?: string;
|
|
20
21
|
maxRedirects?: number;
|
|
21
22
|
userAgent?: string;
|
|
22
|
-
|
|
23
|
+
snapshotRunType?: 'completed' | 'incremental' | 'single';
|
|
24
|
+
registry?: PluginRegistry;
|
|
25
|
+
plugins?: any[];
|
|
26
|
+
robots?: any;
|
|
23
27
|
}
|
|
24
28
|
export declare class Crawler {
|
|
25
29
|
private startUrl;
|
|
26
30
|
private options;
|
|
27
31
|
private context;
|
|
32
|
+
private registry?;
|
|
28
33
|
private visited;
|
|
29
34
|
private uniqueQueue;
|
|
30
35
|
private queue;
|
|
@@ -41,27 +46,34 @@ export declare class Crawler {
|
|
|
41
46
|
private metricsRepo;
|
|
42
47
|
private siteId;
|
|
43
48
|
private snapshotId;
|
|
49
|
+
private reusingSnapshot;
|
|
50
|
+
private runType;
|
|
44
51
|
private rootOrigin;
|
|
45
52
|
private discoveryDepths;
|
|
46
53
|
private pageBuffer;
|
|
47
54
|
private edgeBuffer;
|
|
48
55
|
private metricsBuffer;
|
|
56
|
+
private pendingSitemaps;
|
|
57
|
+
private edgesFound;
|
|
58
|
+
private lastProgressEmitAt;
|
|
59
|
+
private progressPhase;
|
|
49
60
|
private scopeManager;
|
|
50
61
|
private fetcher;
|
|
51
62
|
private parser;
|
|
52
63
|
private sitemapFetcher;
|
|
53
|
-
private trapDetector;
|
|
54
64
|
private robots;
|
|
55
65
|
constructor(startUrl: string, options: CrawlOptions, context?: EngineContext);
|
|
66
|
+
private toStorageUrl;
|
|
56
67
|
initialize(): Promise<void>;
|
|
57
68
|
setupModules(): void;
|
|
58
|
-
fetchRobots
|
|
69
|
+
private fetchRobots;
|
|
59
70
|
shouldEnqueue(url: string, depth: number): boolean;
|
|
60
|
-
addToQueue(u: string, d: number): void;
|
|
71
|
+
addToQueue(u: string, d: number, data?: any): void;
|
|
61
72
|
seedQueue(): Promise<void>;
|
|
62
73
|
private bufferPage;
|
|
63
74
|
private flushPages;
|
|
64
75
|
private bufferEdge;
|
|
76
|
+
private emitProgress;
|
|
65
77
|
private flushEdges;
|
|
66
78
|
private bufferMetrics;
|
|
67
79
|
private flushMetrics;
|