@taodigital/crawler 0.0.0-stage → 1.2.0
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/Dockerfile +82 -0
- package/README.md +10 -2
- package/dist/accessibility-auditor.d.ts +29 -0
- package/dist/accessibility-auditor.js +57 -0
- package/dist/accessibility-auditor.js.map +7 -0
- package/dist/accessibility-tree-crawler.d.ts +44 -0
- package/dist/accessibility-tree-crawler.js +156 -0
- package/dist/accessibility-tree-crawler.js.map +7 -0
- package/dist/advanced-ui-probes.d.ts +47 -0
- package/dist/advanced-ui-probes.js +310 -0
- package/dist/advanced-ui-probes.js.map +7 -0
- package/dist/ai-login.d.ts +32 -0
- package/dist/ai-login.js +250 -0
- package/dist/ai-login.js.map +7 -0
- package/dist/auth-token-rotator.d.ts +47 -0
- package/dist/auth-token-rotator.js +58 -0
- package/dist/auth-token-rotator.js.map +7 -0
- package/dist/auth.d.ts +20 -0
- package/dist/auth.js +348 -0
- package/dist/auth.js.map +7 -0
- package/dist/browser-extension.d.ts +37 -0
- package/dist/browser-extension.js +113 -0
- package/dist/browser-extension.js.map +7 -0
- package/dist/captcha-solver.d.ts +16 -0
- package/dist/captcha-solver.js +105 -0
- package/dist/captcha-solver.js.map +7 -0
- package/dist/color-contrast.d.ts +30 -0
- package/dist/color-contrast.js +78 -0
- package/dist/color-contrast.js.map +7 -0
- package/dist/content-chunker.d.ts +18 -0
- package/dist/content-chunker.js +152 -0
- package/dist/content-chunker.js.map +7 -0
- package/dist/content-dedup.d.ts +23 -0
- package/dist/content-dedup.js +60 -0
- package/dist/content-dedup.js.map +7 -0
- package/dist/cookie-consent.d.ts +25 -0
- package/dist/cookie-consent.js +78 -0
- package/dist/cookie-consent.js.map +7 -0
- package/dist/cookie-jar.d.ts +20 -0
- package/dist/cookie-jar.js +61 -0
- package/dist/cookie-jar.js.map +7 -0
- package/dist/crawl-session-manager.d.ts +44 -0
- package/dist/crawl-session-manager.js +145 -0
- package/dist/crawl-session-manager.js.map +7 -0
- package/dist/crawler.d.ts +233 -0
- package/dist/crawler.js +6239 -0
- package/dist/crawler.js.map +7 -0
- package/dist/crud-interaction.d.ts +31 -0
- package/dist/crud-interaction.js +264 -0
- package/dist/crud-interaction.js.map +7 -0
- package/dist/custom-js-injector.d.ts +42 -0
- package/dist/custom-js-injector.js +50 -0
- package/dist/custom-js-injector.js.map +7 -0
- package/dist/dark-mode-capture.d.ts +23 -0
- package/dist/dark-mode-capture.js +75 -0
- package/dist/dark-mode-capture.js.map +7 -0
- package/dist/dead-link-detector.d.ts +37 -0
- package/dist/dead-link-detector.js +50 -0
- package/dist/dead-link-detector.js.map +7 -0
- package/dist/dropdown-enumerator.d.ts +20 -0
- package/dist/dropdown-enumerator.js +230 -0
- package/dist/dropdown-enumerator.js.map +7 -0
- package/dist/element-hash.d.ts +9 -0
- package/dist/element-hash.js +9 -0
- package/dist/element-hash.js.map +7 -0
- package/dist/email-otp.d.ts +42 -0
- package/dist/email-otp.js +177 -0
- package/dist/email-otp.js.map +7 -0
- package/dist/engine-router.d.ts +47 -0
- package/dist/engine-router.js +94 -0
- package/dist/engine-router.js.map +7 -0
- package/dist/export/bulk-export.d.ts +26 -0
- package/dist/export/bulk-export.js +76 -0
- package/dist/export/bulk-export.js.map +7 -0
- package/dist/export/vector-export.d.ts +76 -0
- package/dist/export/vector-export.js +85 -0
- package/dist/export/vector-export.js.map +7 -0
- package/dist/extractors/advanced.d.ts +64 -0
- package/dist/extractors/advanced.js +265 -0
- package/dist/extractors/advanced.js.map +7 -0
- package/dist/extractors/artifact-envelope.d.ts +63 -0
- package/dist/extractors/artifact-envelope.js +63 -0
- package/dist/extractors/artifact-envelope.js.map +7 -0
- package/dist/extractors/branding-extractor.d.ts +46 -0
- package/dist/extractors/branding-extractor.js +104 -0
- package/dist/extractors/branding-extractor.js.map +7 -0
- package/dist/extractors/summary-extractor.d.ts +10 -0
- package/dist/extractors/summary-extractor.js +36 -0
- package/dist/extractors/summary-extractor.js.map +7 -0
- package/dist/failure-analysis-agent.d.ts +16 -0
- package/dist/failure-analysis-agent.js +42 -0
- package/dist/failure-analysis-agent.js.map +7 -0
- package/dist/feature-flag-detector.d.ts +30 -0
- package/dist/feature-flag-detector.js +55 -0
- package/dist/feature-flag-detector.js.map +7 -0
- package/dist/filter-pagination-crawler.d.ts +52 -0
- package/dist/filter-pagination-crawler.js +299 -0
- package/dist/filter-pagination-crawler.js.map +7 -0
- package/dist/form-detector.d.ts +34 -0
- package/dist/form-detector.js +58 -0
- package/dist/form-detector.js.map +7 -0
- package/dist/frontier.d.ts +40 -0
- package/dist/frontier.js +103 -0
- package/dist/frontier.js.map +7 -0
- package/dist/gap-pass.d.ts +36 -0
- package/dist/gap-pass.js +115 -0
- package/dist/gap-pass.js.map +7 -0
- package/dist/graphql-detector.d.ts +39 -0
- package/dist/graphql-detector.js +86 -0
- package/dist/graphql-detector.js.map +7 -0
- package/dist/http-engine.d.ts +80 -0
- package/dist/http-engine.js +318 -0
- package/dist/http-engine.js.map +7 -0
- package/dist/incremental-diff.d.ts +116 -0
- package/dist/incremental-diff.js +137 -0
- package/dist/incremental-diff.js.map +7 -0
- package/dist/index.d.ts +52 -0
- package/dist/index.js +83 -0
- package/dist/index.js.map +7 -0
- package/dist/input-fuzzer.d.ts +30 -0
- package/dist/input-fuzzer.js +105 -0
- package/dist/input-fuzzer.js.map +7 -0
- package/dist/interactive-probe.d.ts +144 -0
- package/dist/interactive-probe.js +865 -0
- package/dist/interactive-probe.js.map +7 -0
- package/dist/job-queue.d.ts +297 -0
- package/dist/job-queue.js +3812 -0
- package/dist/job-queue.js.map +7 -0
- package/dist/js-coverage.d.ts +29 -0
- package/dist/js-coverage.js +56 -0
- package/dist/js-coverage.js.map +7 -0
- package/dist/js-router-detector.d.ts +17 -0
- package/dist/js-router-detector.js +90 -0
- package/dist/js-router-detector.js.map +7 -0
- package/dist/language-detector.d.ts +22 -0
- package/dist/language-detector.js +57 -0
- package/dist/language-detector.js.map +7 -0
- package/dist/link-classifier.d.ts +23 -0
- package/dist/link-classifier.js +40 -0
- package/dist/link-classifier.js.map +7 -0
- package/dist/live-view.d.ts +36 -0
- package/dist/live-view.js +105 -0
- package/dist/live-view.js.map +7 -0
- package/dist/locator-extractor.d.ts +46 -0
- package/dist/locator-extractor.js +220 -0
- package/dist/locator-extractor.js.map +7 -0
- package/dist/logger.d.ts +2 -0
- package/dist/logger.js +10 -0
- package/dist/logger.js.map +7 -0
- package/dist/markdown-extract.d.ts +8 -0
- package/dist/markdown-extract.js +54 -0
- package/dist/markdown-extract.js.map +7 -0
- package/dist/multi-context-handler.d.ts +55 -0
- package/dist/multi-context-handler.js +182 -0
- package/dist/multi-context-handler.js.map +7 -0
- package/dist/native-crawler.d.ts +69 -0
- package/dist/native-crawler.js +839 -0
- package/dist/native-crawler.js.map +7 -0
- package/dist/nested-window-crawler.d.ts +41 -0
- package/dist/nested-window-crawler.js +172 -0
- package/dist/nested-window-crawler.js.map +7 -0
- package/dist/network-action-correlator.d.ts +47 -0
- package/dist/network-action-correlator.js +209 -0
- package/dist/network-action-correlator.js.map +7 -0
- package/dist/network-observer.d.ts +49 -0
- package/dist/network-observer.js +149 -0
- package/dist/network-observer.js.map +7 -0
- package/dist/network-throttle.d.ts +25 -0
- package/dist/network-throttle.js +34 -0
- package/dist/network-throttle.js.map +7 -0
- package/dist/openapi-generator.d.ts +49 -0
- package/dist/openapi-generator.js +89 -0
- package/dist/openapi-generator.js.map +7 -0
- package/dist/pdf-extractor.d.ts +28 -0
- package/dist/pdf-extractor.js +81 -0
- package/dist/pdf-extractor.js.map +7 -0
- package/dist/performance-metrics-collector.d.ts +50 -0
- package/dist/performance-metrics-collector.js +155 -0
- package/dist/performance-metrics-collector.js.map +7 -0
- package/dist/performance-metrics.d.ts +52 -0
- package/dist/performance-metrics.js +83 -0
- package/dist/performance-metrics.js.map +7 -0
- package/dist/phash.d.ts +50 -0
- package/dist/phash.js +136 -0
- package/dist/phash.js.map +7 -0
- package/dist/pii-scrubber.d.ts +21 -0
- package/dist/pii-scrubber.js +75 -0
- package/dist/pii-scrubber.js.map +7 -0
- package/dist/playwright-recorder.d.ts +39 -0
- package/dist/playwright-recorder.js +123 -0
- package/dist/playwright-recorder.js.map +7 -0
- package/dist/policies/crawl-safety.d.ts +9 -0
- package/dist/policies/crawl-safety.js +41 -0
- package/dist/policies/crawl-safety.js.map +7 -0
- package/dist/profiles/domain-profile.d.ts +19 -0
- package/dist/profiles/domain-profile.js +160 -0
- package/dist/profiles/domain-profile.js.map +7 -0
- package/dist/proxy.d.ts +50 -0
- package/dist/proxy.js +165 -0
- package/dist/proxy.js.map +7 -0
- package/dist/rate-limiter.d.ts +31 -0
- package/dist/rate-limiter.js +64 -0
- package/dist/rate-limiter.js.map +7 -0
- package/dist/redirect-tracker.d.ts +37 -0
- package/dist/redirect-tracker.js +65 -0
- package/dist/redirect-tracker.js.map +7 -0
- package/dist/redis-frontier.d.ts +48 -0
- package/dist/redis-frontier.js +126 -0
- package/dist/redis-frontier.js.map +7 -0
- package/dist/redis-queue.d.ts +48 -0
- package/dist/redis-queue.js +165 -0
- package/dist/redis-queue.js.map +7 -0
- package/dist/response-cache.d.ts +38 -0
- package/dist/response-cache.js +140 -0
- package/dist/response-cache.js.map +7 -0
- package/dist/responsive-detector.d.ts +29 -0
- package/dist/responsive-detector.js +46 -0
- package/dist/responsive-detector.js.map +7 -0
- package/dist/retry-policy.d.ts +20 -0
- package/dist/retry-policy.js +54 -0
- package/dist/retry-policy.js.map +7 -0
- package/dist/robots-txt.d.ts +9 -0
- package/dist/robots-txt.js +77 -0
- package/dist/robots-txt.js.map +7 -0
- package/dist/screen-reader.d.ts +15 -0
- package/dist/screen-reader.js +48 -0
- package/dist/screen-reader.js.map +7 -0
- package/dist/screenshot-masker.d.ts +28 -0
- package/dist/screenshot-masker.js +62 -0
- package/dist/screenshot-masker.js.map +7 -0
- package/dist/seo-checker.d.ts +33 -0
- package/dist/seo-checker.js +91 -0
- package/dist/seo-checker.js.map +7 -0
- package/dist/service-worker-interceptor.d.ts +36 -0
- package/dist/service-worker-interceptor.js +136 -0
- package/dist/service-worker-interceptor.js.map +7 -0
- package/dist/session-capture.d.ts +39 -0
- package/dist/session-capture.js +274 -0
- package/dist/session-capture.js.map +7 -0
- package/dist/session-export.d.ts +49 -0
- package/dist/session-export.js +117 -0
- package/dist/session-export.js.map +7 -0
- package/dist/shadow-dom-crawler.d.ts +35 -0
- package/dist/shadow-dom-crawler.js +132 -0
- package/dist/shadow-dom-crawler.js.map +7 -0
- package/dist/sitemap-writer.d.ts +21 -0
- package/dist/sitemap-writer.js +47 -0
- package/dist/sitemap-writer.js.map +7 -0
- package/dist/sitemap.d.ts +51 -0
- package/dist/sitemap.js +160 -0
- package/dist/sitemap.js.map +7 -0
- package/dist/skyvern.d.ts +56 -0
- package/dist/skyvern.js +129 -0
- package/dist/skyvern.js.map +7 -0
- package/dist/sqs-queue.d.ts +13 -0
- package/dist/sqs-queue.js +115 -0
- package/dist/sqs-queue.js.map +7 -0
- package/dist/sso-token.d.ts +29 -0
- package/dist/sso-token.js +76 -0
- package/dist/sso-token.js.map +7 -0
- package/dist/state-graph.d.ts +59 -0
- package/dist/state-graph.js +193 -0
- package/dist/state-graph.js.map +7 -0
- package/dist/stealth/human-behavior.d.ts +20 -0
- package/dist/stealth/human-behavior.js +202 -0
- package/dist/stealth/human-behavior.js.map +7 -0
- package/dist/telemetry.d.ts +34 -0
- package/dist/telemetry.js +77 -0
- package/dist/telemetry.js.map +7 -0
- package/dist/test-executor.d.ts +81 -0
- package/dist/test-executor.js +443 -0
- package/dist/test-executor.js.map +7 -0
- package/dist/tls-fingerprint.d.ts +50 -0
- package/dist/tls-fingerprint.js +81 -0
- package/dist/tls-fingerprint.js.map +7 -0
- package/dist/url-pattern-completer.d.ts +28 -0
- package/dist/url-pattern-completer.js +122 -0
- package/dist/url-pattern-completer.js.map +7 -0
- package/dist/visual-diff-verdict.d.ts +40 -0
- package/dist/visual-diff-verdict.js +27 -0
- package/dist/visual-diff-verdict.js.map +7 -0
- package/dist/webhook-notifier.d.ts +30 -0
- package/dist/webhook-notifier.js +76 -0
- package/dist/webhook-notifier.js.map +7 -0
- package/dist/websocket-detector.d.ts +24 -0
- package/dist/websocket-detector.js +60 -0
- package/dist/websocket-detector.js.map +7 -0
- package/dist/worker.d.ts +1 -0
- package/dist/worker.js +33 -0
- package/dist/worker.js.map +7 -0
- package/package.json +49 -4
- package/src/accessibility-auditor.ts +102 -0
- package/src/accessibility-tree-crawler.ts +246 -0
- package/src/advanced-ui-probes.ts +470 -0
- package/src/ai-login.ts +298 -0
- package/src/auth-token-rotator.ts +89 -0
- package/src/auth.ts +418 -0
- package/src/browser-extension.ts +186 -0
- package/src/captcha-solver.ts +143 -0
- package/src/color-contrast.ts +116 -0
- package/src/content-chunker.ts +170 -0
- package/src/content-dedup.ts +99 -0
- package/src/cookie-consent.ts +106 -0
- package/src/cookie-jar.ts +91 -0
- package/src/crawl-session-manager.ts +231 -0
- package/src/crawler.ts +7123 -0
- package/src/crawler.ts.rej +12 -0
- package/src/crud-interaction.ts +386 -0
- package/src/custom-js-injector.ts +93 -0
- package/src/dark-mode-capture.ts +110 -0
- package/src/dead-link-detector.ts +76 -0
- package/src/dropdown-enumerator.ts +312 -0
- package/src/element-hash.ts +16 -0
- package/src/email-otp.ts +252 -0
- package/src/engine-router.ts +141 -0
- package/src/export/bulk-export.ts +85 -0
- package/src/export/vector-export.ts +160 -0
- package/src/extractors/advanced.ts +309 -0
- package/src/extractors/artifact-envelope.ts +111 -0
- package/src/extractors/branding-extractor.ts +159 -0
- package/src/extractors/summary-extractor.ts +49 -0
- package/src/failure-analysis-agent.ts +51 -0
- package/src/feature-flag-detector.ts +97 -0
- package/src/filter-pagination-crawler.ts +500 -0
- package/src/form-detector.ts +103 -0
- package/src/frontier.test.ts +64 -0
- package/src/frontier.ts +144 -0
- package/src/gap-pass.ts +165 -0
- package/src/graphql-detector.ts +129 -0
- package/src/http-engine.ts +453 -0
- package/src/incremental-diff.ts +259 -0
- package/src/index.ts +52 -0
- package/src/input-fuzzer.ts +129 -0
- package/src/interactive-probe.ts +1136 -0
- package/src/job-queue.test.ts +187 -0
- package/src/job-queue.ts +4504 -0
- package/src/js-coverage.ts +87 -0
- package/src/js-router-detector.ts +112 -0
- package/src/language-detector.ts +82 -0
- package/src/link-classifier.ts +65 -0
- package/src/live-view.ts +146 -0
- package/src/locator-extractor.ts +309 -0
- package/src/logger.ts +9 -0
- package/src/markdown-extract.test.ts +73 -0
- package/src/markdown-extract.ts +76 -0
- package/src/multi-context-handler.ts +296 -0
- package/src/native-crawler.ts +1108 -0
- package/src/nested-window-crawler.ts +310 -0
- package/src/network-action-correlator.ts +320 -0
- package/src/network-observer.ts +204 -0
- package/src/network-throttle.ts +69 -0
- package/src/openapi-generator.ts +135 -0
- package/src/pdf-extractor.ts +123 -0
- package/src/performance-metrics-collector.ts +243 -0
- package/src/performance-metrics.ts +134 -0
- package/src/phash.ts +184 -0
- package/src/pii-scrubber.ts +99 -0
- package/src/playwright-recorder.ts +170 -0
- package/src/policies/crawl-safety.ts +52 -0
- package/src/profiles/domain-profile.ts +190 -0
- package/src/proxy.ts +238 -0
- package/src/rate-limiter.ts +87 -0
- package/src/redirect-tracker.ts +97 -0
- package/src/redis-frontier.ts +143 -0
- package/src/redis-queue.ts +208 -0
- package/src/response-cache.ts +150 -0
- package/src/responsive-detector.ts +92 -0
- package/src/retry-policy.ts +87 -0
- package/src/robots-txt.ts +96 -0
- package/src/screen-reader.ts +98 -0
- package/src/screenshot-masker.ts +98 -0
- package/src/seo-checker.ts +134 -0
- package/src/service-worker-interceptor.ts +185 -0
- package/src/session-capture.ts +335 -0
- package/src/session-export.test.ts +75 -0
- package/src/session-export.ts +172 -0
- package/src/shadow-dom-crawler.ts +198 -0
- package/src/sitemap-writer.ts +65 -0
- package/src/sitemap.test.ts +127 -0
- package/src/sitemap.ts +233 -0
- package/src/skyvern.ts +199 -0
- package/src/sqs-queue.ts +129 -0
- package/src/sso-token.ts +120 -0
- package/src/state-graph.ts +280 -0
- package/src/stealth/human-behavior.ts +227 -0
- package/src/telemetry.ts +122 -0
- package/src/test-executor.test.ts +72 -0
- package/src/test-executor.ts +578 -0
- package/src/tls-fingerprint.ts +111 -0
- package/src/url-pattern-completer.ts +161 -0
- package/src/vendor.d.ts +20 -0
- package/src/visual-diff-verdict.test.ts +80 -0
- package/src/visual-diff-verdict.ts +59 -0
- package/src/webhook-notifier.ts +109 -0
- package/src/websocket-detector.ts +83 -0
- package/src/worker.ts +50 -0
- package/tsconfig.json +13 -0
- package/types/accessibility-auditor.d.ts +29 -0
- package/types/accessibility-tree-crawler.d.ts +44 -0
- package/types/advanced-ui-probes.d.ts +47 -0
- package/types/ai-login.d.ts +32 -0
- package/types/auth-token-rotator.d.ts +47 -0
- package/types/auth.d.ts +20 -0
- package/types/browser-extension.d.ts +37 -0
- package/types/bull-worker.d.ts +6 -0
- package/types/captcha-solver.d.ts +16 -0
- package/types/color-contrast.d.ts +30 -0
- package/types/content-chunker.d.ts +18 -0
- package/types/content-dedup.d.ts +23 -0
- package/types/cookie-consent.d.ts +25 -0
- package/types/cookie-jar.d.ts +20 -0
- package/types/crawl-session-manager.d.ts +44 -0
- package/types/crawler.d.ts +233 -0
- package/types/crud-interaction.d.ts +31 -0
- package/types/custom-js-injector.d.ts +42 -0
- package/types/dark-mode-capture.d.ts +23 -0
- package/types/dead-link-detector.d.ts +37 -0
- package/types/dropdown-enumerator.d.ts +20 -0
- package/types/element-hash.d.ts +9 -0
- package/types/email-otp.d.ts +42 -0
- package/types/engine-router.d.ts +47 -0
- package/types/export/bulk-export.d.ts +26 -0
- package/types/export/vector-export.d.ts +76 -0
- package/types/extractors/advanced.d.ts +64 -0
- package/types/extractors/artifact-envelope.d.ts +63 -0
- package/types/extractors/branding-extractor.d.ts +46 -0
- package/types/extractors/summary-extractor.d.ts +10 -0
- package/types/failure-analysis-agent.d.ts +16 -0
- package/types/feature-flag-detector.d.ts +30 -0
- package/types/filter-pagination-crawler.d.ts +52 -0
- package/types/form-detector.d.ts +34 -0
- package/types/frontier.d.ts +40 -0
- package/types/gap-pass.d.ts +36 -0
- package/types/graphql-detector.d.ts +39 -0
- package/types/http-engine.d.ts +80 -0
- package/types/incremental-diff.d.ts +116 -0
- package/types/index.d.ts +52 -0
- package/types/input-fuzzer.d.ts +30 -0
- package/types/interactive-probe.d.ts +144 -0
- package/types/job-queue.d.ts +308 -0
- package/types/js-coverage.d.ts +29 -0
- package/types/js-router-detector.d.ts +17 -0
- package/types/language-detector.d.ts +22 -0
- package/types/link-classifier.d.ts +23 -0
- package/types/live-view.d.ts +36 -0
- package/types/locator-extractor.d.ts +46 -0
- package/types/logger.d.ts +2 -0
- package/types/markdown-extract.d.ts +8 -0
- package/types/multi-context-handler.d.ts +55 -0
- package/types/native-crawler.d.ts +69 -0
- package/types/nested-window-crawler.d.ts +41 -0
- package/types/network-action-correlator.d.ts +47 -0
- package/types/network-observer.d.ts +49 -0
- package/types/network-throttle.d.ts +25 -0
- package/types/openapi-generator.d.ts +49 -0
- package/types/pdf-extractor.d.ts +28 -0
- package/types/performance-metrics-collector.d.ts +50 -0
- package/types/performance-metrics.d.ts +52 -0
- package/types/phash.d.ts +50 -0
- package/types/pii-scrubber.d.ts +21 -0
- package/types/playwright-recorder.d.ts +39 -0
- package/types/policies/crawl-safety.d.ts +9 -0
- package/types/profiles/domain-profile.d.ts +19 -0
- package/types/proxy.d.ts +50 -0
- package/types/rate-limiter.d.ts +31 -0
- package/types/redirect-tracker.d.ts +37 -0
- package/types/redis-frontier.d.ts +48 -0
- package/types/redis-queue.d.ts +48 -0
- package/types/response-cache.d.ts +38 -0
- package/types/responsive-detector.d.ts +29 -0
- package/types/retry-policy.d.ts +20 -0
- package/types/robots-txt.d.ts +9 -0
- package/types/screen-reader.d.ts +15 -0
- package/types/screenshot-masker.d.ts +28 -0
- package/types/seo-checker.d.ts +33 -0
- package/types/service-worker-interceptor.d.ts +36 -0
- package/types/session-capture.d.ts +39 -0
- package/types/session-export.d.ts +49 -0
- package/types/shadow-dom-crawler.d.ts +35 -0
- package/types/sitemap-writer.d.ts +21 -0
- package/types/sitemap.d.ts +51 -0
- package/types/skyvern.d.ts +56 -0
- package/types/sqs-queue.d.ts +13 -0
- package/types/sso-token.d.ts +29 -0
- package/types/state-graph.d.ts +59 -0
- package/types/stealth/human-behavior.d.ts +20 -0
- package/types/telemetry.d.ts +34 -0
- package/types/test-executor.d.ts +84 -0
- package/types/tls-fingerprint.d.ts +50 -0
- package/types/url-pattern-completer.d.ts +28 -0
- package/types/visual-diff-verdict.d.ts +40 -0
- package/types/webhook-notifier.d.ts +30 -0
- package/types/websocket-detector.d.ts +24 -0
- package/types/worker.d.ts +1 -0
|
@@ -0,0 +1,296 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* Multi-context browser handling — detects and records new tabs, iframes,
|
|
3
|
+
* popups, and file downloads triggered during a page crawl.
|
|
4
|
+
* This lets ZeTa discover cross-origin flows, OAuth redirects, embedded
|
|
5
|
+
* third-party content, and downloadable resources that single-page HTTP
|
|
6
|
+
* crawlers would miss entirely.
|
|
7
|
+
*/
|
|
8
|
+
|
|
9
|
+
import type { Page, BrowserContext } from 'playwright';
|
|
10
|
+
|
|
11
|
+
export interface NewTabRecord {
|
|
12
|
+
url: string;
|
|
13
|
+
linkText: string;
|
|
14
|
+
isInternal: boolean;
|
|
15
|
+
httpStatus?: number;
|
|
16
|
+
}
|
|
17
|
+
|
|
18
|
+
export interface IframeRecord {
|
|
19
|
+
src: string;
|
|
20
|
+
crossOrigin: boolean;
|
|
21
|
+
sandboxed: boolean;
|
|
22
|
+
sandboxValue: string | null;
|
|
23
|
+
accessible: boolean;
|
|
24
|
+
contentSample: string;
|
|
25
|
+
hasForm: boolean;
|
|
26
|
+
}
|
|
27
|
+
|
|
28
|
+
export interface PopupRecord {
|
|
29
|
+
url: string;
|
|
30
|
+
triggerLabel: string;
|
|
31
|
+
isOAuthLike: boolean;
|
|
32
|
+
}
|
|
33
|
+
|
|
34
|
+
export interface DownloadRecord {
|
|
35
|
+
filename: string;
|
|
36
|
+
downloadUrl: string;
|
|
37
|
+
triggerLabel: string;
|
|
38
|
+
}
|
|
39
|
+
|
|
40
|
+
export interface MultiContextResult {
|
|
41
|
+
newTabs: NewTabRecord[];
|
|
42
|
+
iframes: IframeRecord[];
|
|
43
|
+
popups: PopupRecord[];
|
|
44
|
+
downloads: DownloadRecord[];
|
|
45
|
+
}
|
|
46
|
+
|
|
47
|
+
// ---------------------------------------------------------------------------
|
|
48
|
+
// Internal helpers
|
|
49
|
+
// ---------------------------------------------------------------------------
|
|
50
|
+
|
|
51
|
+
async function enumerateIframes(
|
|
52
|
+
page: Page,
|
|
53
|
+
seedUrl: string,
|
|
54
|
+
): Promise<IframeRecord[]> {
|
|
55
|
+
const records: IframeRecord[] = [];
|
|
56
|
+
try {
|
|
57
|
+
const seedHost = new URL(seedUrl).hostname;
|
|
58
|
+
const iframeLocators = await page.locator('iframe').all();
|
|
59
|
+
const limited = iframeLocators.slice(0, 20);
|
|
60
|
+
|
|
61
|
+
for (let idx = 0; idx < limited.length; idx++) {
|
|
62
|
+
try {
|
|
63
|
+
const loc = limited[idx];
|
|
64
|
+
const src = (await loc.getAttribute('src')) ?? '';
|
|
65
|
+
const sandboxValue = await loc.getAttribute('sandbox');
|
|
66
|
+
const sandboxed = sandboxValue !== null;
|
|
67
|
+
|
|
68
|
+
let crossOrigin = false;
|
|
69
|
+
if (src) {
|
|
70
|
+
try {
|
|
71
|
+
const iframeHost = new URL(src, seedUrl).hostname;
|
|
72
|
+
crossOrigin = iframeHost !== seedHost;
|
|
73
|
+
} catch {
|
|
74
|
+
crossOrigin = false;
|
|
75
|
+
}
|
|
76
|
+
}
|
|
77
|
+
|
|
78
|
+
let accessible = false;
|
|
79
|
+
let contentSample = '';
|
|
80
|
+
let hasForm = false;
|
|
81
|
+
|
|
82
|
+
try {
|
|
83
|
+
const fl = page.frameLocator('iframe').nth(idx);
|
|
84
|
+
const body = await fl.locator('body').textContent({ timeout: 2000 });
|
|
85
|
+
if (body !== null) {
|
|
86
|
+
accessible = true;
|
|
87
|
+
contentSample = body.trim().slice(0, 300);
|
|
88
|
+
}
|
|
89
|
+
const formCount = await fl.locator('form, input, textarea, select').count();
|
|
90
|
+
hasForm = formCount > 0;
|
|
91
|
+
} catch {
|
|
92
|
+
// cross-origin or sandboxed — not accessible from parent frame
|
|
93
|
+
}
|
|
94
|
+
|
|
95
|
+
records.push({
|
|
96
|
+
src,
|
|
97
|
+
crossOrigin,
|
|
98
|
+
sandboxed,
|
|
99
|
+
sandboxValue,
|
|
100
|
+
accessible,
|
|
101
|
+
contentSample,
|
|
102
|
+
hasForm,
|
|
103
|
+
});
|
|
104
|
+
} catch {
|
|
105
|
+
// skip individual iframe errors
|
|
106
|
+
}
|
|
107
|
+
}
|
|
108
|
+
} catch {
|
|
109
|
+
// skip entirely if locator fails
|
|
110
|
+
}
|
|
111
|
+
return records;
|
|
112
|
+
}
|
|
113
|
+
|
|
114
|
+
async function detectPopups(page: Page, result: MultiContextResult): Promise<void> {
|
|
115
|
+
try {
|
|
116
|
+
const candidates = [
|
|
117
|
+
...await page.locator('[onclick*="window.open"]').all(),
|
|
118
|
+
...await page.locator('button:has-text("Open in")').all(),
|
|
119
|
+
];
|
|
120
|
+
const limited = candidates.slice(0, 3);
|
|
121
|
+
|
|
122
|
+
for (const trigger of limited) {
|
|
123
|
+
try {
|
|
124
|
+
const triggerLabel = (await trigger.textContent())?.trim() ?? '';
|
|
125
|
+
const outcome = await Promise.all([
|
|
126
|
+
page.waitForEvent('popup', { timeout: 2000 }),
|
|
127
|
+
trigger.click(),
|
|
128
|
+
]).catch(() => null);
|
|
129
|
+
|
|
130
|
+
if (!outcome) continue;
|
|
131
|
+
const popup = outcome[0] as Page;
|
|
132
|
+
if (!popup) continue;
|
|
133
|
+
|
|
134
|
+
const url = popup.url();
|
|
135
|
+
let isOAuthLike = false;
|
|
136
|
+
try {
|
|
137
|
+
const host = new URL(url).hostname;
|
|
138
|
+
isOAuthLike = /google|github|microsoft|okta|auth0/.test(host);
|
|
139
|
+
} catch {
|
|
140
|
+
// not a valid URL
|
|
141
|
+
}
|
|
142
|
+
|
|
143
|
+
result.popups.push({ url, triggerLabel, isOAuthLike });
|
|
144
|
+
await popup.close().catch(() => {});
|
|
145
|
+
} catch {
|
|
146
|
+
// skip this trigger
|
|
147
|
+
}
|
|
148
|
+
}
|
|
149
|
+
} catch {
|
|
150
|
+
// skip popup detection entirely
|
|
151
|
+
}
|
|
152
|
+
}
|
|
153
|
+
|
|
154
|
+
async function detectDownloads(page: Page, result: MultiContextResult): Promise<void> {
|
|
155
|
+
try {
|
|
156
|
+
const candidates = [
|
|
157
|
+
...await page.locator('a[download]').all(),
|
|
158
|
+
...await page.locator('button:has-text("Export")').all(),
|
|
159
|
+
...await page.locator('button:has-text("Download")').all(),
|
|
160
|
+
];
|
|
161
|
+
const limited = candidates.slice(0, 3);
|
|
162
|
+
|
|
163
|
+
for (const trigger of limited) {
|
|
164
|
+
try {
|
|
165
|
+
const triggerLabel = (await trigger.textContent())?.trim() ?? '';
|
|
166
|
+
const outcome = await Promise.all([
|
|
167
|
+
page.waitForEvent('download', { timeout: 2000 }),
|
|
168
|
+
trigger.click(),
|
|
169
|
+
]).catch(() => null);
|
|
170
|
+
|
|
171
|
+
if (!outcome) continue;
|
|
172
|
+
const download = outcome[0] as unknown as import('playwright').Download;
|
|
173
|
+
if (!download) continue;
|
|
174
|
+
|
|
175
|
+
const filename = download.suggestedFilename();
|
|
176
|
+
const downloadUrl = download.url();
|
|
177
|
+
await download.cancel().catch(() => {});
|
|
178
|
+
|
|
179
|
+
result.downloads.push({ filename, downloadUrl, triggerLabel });
|
|
180
|
+
} catch {
|
|
181
|
+
// skip this trigger
|
|
182
|
+
}
|
|
183
|
+
}
|
|
184
|
+
} catch {
|
|
185
|
+
// skip download detection entirely
|
|
186
|
+
}
|
|
187
|
+
}
|
|
188
|
+
|
|
189
|
+
// ---------------------------------------------------------------------------
|
|
190
|
+
// Exported functions
|
|
191
|
+
// ---------------------------------------------------------------------------
|
|
192
|
+
|
|
193
|
+
/**
|
|
194
|
+
* Attaches a listener to the BrowserContext that records every new tab
|
|
195
|
+
* opened while the listener is active. Returns an unsubscribe function.
|
|
196
|
+
*
|
|
197
|
+
* Call this before navigating / clicking so that tabs opened during the
|
|
198
|
+
* crawl are captured, then call the returned function to stop listening.
|
|
199
|
+
*/
|
|
200
|
+
export function attachNewTabListener(
|
|
201
|
+
context: BrowserContext,
|
|
202
|
+
seedUrl: string,
|
|
203
|
+
result: MultiContextResult,
|
|
204
|
+
): () => void {
|
|
205
|
+
let seedHost = '';
|
|
206
|
+
try {
|
|
207
|
+
seedHost = new URL(seedUrl).hostname;
|
|
208
|
+
} catch {
|
|
209
|
+
// leave empty — all tabs will be treated as external
|
|
210
|
+
}
|
|
211
|
+
|
|
212
|
+
const handler = async (newPage: Page) => {
|
|
213
|
+
try {
|
|
214
|
+
await newPage.waitForLoadState('networkidle', { timeout: 10000 }).catch(() => {});
|
|
215
|
+
const url = newPage.url();
|
|
216
|
+
|
|
217
|
+
if (!url || url === 'about:blank') {
|
|
218
|
+
await newPage.close().catch(() => {});
|
|
219
|
+
return;
|
|
220
|
+
}
|
|
221
|
+
|
|
222
|
+
let isInternal = false;
|
|
223
|
+
let httpStatus: number | undefined;
|
|
224
|
+
|
|
225
|
+
try {
|
|
226
|
+
const tabHost = new URL(url).hostname;
|
|
227
|
+
isInternal = tabHost === seedHost;
|
|
228
|
+
} catch {
|
|
229
|
+
// non-parseable URL — treat as external
|
|
230
|
+
}
|
|
231
|
+
|
|
232
|
+
if (!isInternal) {
|
|
233
|
+
try {
|
|
234
|
+
const controller = new AbortController();
|
|
235
|
+
const timer = setTimeout(() => controller.abort(), 3000);
|
|
236
|
+
const resp = await fetch(url, { method: 'HEAD', signal: controller.signal });
|
|
237
|
+
clearTimeout(timer);
|
|
238
|
+
httpStatus = resp.status;
|
|
239
|
+
} catch {
|
|
240
|
+
// network unreachable or CORS — leave httpStatus undefined
|
|
241
|
+
}
|
|
242
|
+
}
|
|
243
|
+
|
|
244
|
+
// linkText is not available at context level; caller fills it if needed
|
|
245
|
+
result.newTabs.push({ url, linkText: '', isInternal, httpStatus });
|
|
246
|
+
await newPage.close().catch(() => {});
|
|
247
|
+
} catch {
|
|
248
|
+
// swallow handler errors so the listener stays alive
|
|
249
|
+
}
|
|
250
|
+
};
|
|
251
|
+
|
|
252
|
+
context.on('page', handler);
|
|
253
|
+
return () => context.off('page', handler);
|
|
254
|
+
}
|
|
255
|
+
|
|
256
|
+
/**
|
|
257
|
+
* Probes the current page for multi-context browser events: iframes,
|
|
258
|
+
* popup windows, and file downloads.
|
|
259
|
+
*
|
|
260
|
+
* New-tab tracking is intentionally excluded here — it must be set up at
|
|
261
|
+
* the crawler level (before navigation) using `attachNewTabListener`.
|
|
262
|
+
*/
|
|
263
|
+
export async function probeMultiContext(
|
|
264
|
+
page: Page,
|
|
265
|
+
context: BrowserContext,
|
|
266
|
+
seedUrl: string,
|
|
267
|
+
): Promise<MultiContextResult> {
|
|
268
|
+
void context; // reserved for future use (e.g. routing overrides)
|
|
269
|
+
|
|
270
|
+
const result: MultiContextResult = {
|
|
271
|
+
newTabs: [],
|
|
272
|
+
iframes: [],
|
|
273
|
+
popups: [],
|
|
274
|
+
downloads: [],
|
|
275
|
+
};
|
|
276
|
+
|
|
277
|
+
try {
|
|
278
|
+
result.iframes = await enumerateIframes(page, seedUrl);
|
|
279
|
+
} catch {
|
|
280
|
+
// keep empty
|
|
281
|
+
}
|
|
282
|
+
|
|
283
|
+
try {
|
|
284
|
+
await detectPopups(page, result);
|
|
285
|
+
} catch {
|
|
286
|
+
// keep empty
|
|
287
|
+
}
|
|
288
|
+
|
|
289
|
+
try {
|
|
290
|
+
await detectDownloads(page, result);
|
|
291
|
+
} catch {
|
|
292
|
+
// keep empty
|
|
293
|
+
}
|
|
294
|
+
|
|
295
|
+
return result;
|
|
296
|
+
}
|