{"data":{"slug":"common-crawl-targeted-corpus-builder","title":"Common Crawl Targeted Corpus Builder","summary":"Common Crawl Targeted Corpus Builder packages Query domains\/topics, fetch CC pages, clean Markdown, dedupe, language\/license heuristics into a source-governed Apify actor with sample mode, schema, pricing, QA evidence, and marketplac...","buyer_outcome":"Common Crawl Targeted Corpus Builder packages Query domains\/topics, fetch CC pages, clean Markdown, dedupe, language\/license heuristics into a source-governed Apify actor with sample mode, schema, pricing, QA evidence, and marketplace-ready listing assets.","target_audiences":["AI teams","researchers","SEO teams"],"use_cases":["Publish a marketplace-ready product package.","Run dry-run publish validation before live submission.","Use sample outputs and setup docs during buyer onboarding."],"industries":[],"geographies":[],"output_formats":["JSON","CSV","API"],"marketplaces":[{"key":"apify","label":"Apify Store","url":"https:\/\/apify.com\/zentrafoundry\/common-crawl-targeted-corpus-builder","status":"published","primary":true,"cta_label":"Open on Apify","ctaLabel":"Open on Apify","public_safe":true,"publicSafe":true}],"marketplace_availability":[{"key":"apify","label":"Apify Store","status":"published","status_label":"Published","action_label":"Open on Apify","url":"https:\/\/apify.com\/zentrafoundry\/common-crawl-targeted-corpus-builder","clickable":true,"coverage":"published_product"},{"key":"google_workspace_marketplace","label":"Google Workspace Marketplace","status":"published","status_label":"Available through published app","action_label":"Install from Google Workspace","url":"https:\/\/workspace.google.com\/marketplace\/app\/zentra\/20298059700","clickable":true,"coverage":"application_covered"},{"key":"cloudflare","label":"Cloudflare Edge Commerce","status":"published","status_label":"Not Yet Published","action_label":"Not Yet Published","url":null,"clickable":false,"coverage":"application_covered"},{"key":"github_marketplace","label":"GitHub Marketplace","status":"under_review","status_label":"Awaiting Marketplace Review","action_label":"Awaiting Marketplace Review","url":null,"clickable":false,"coverage":"application_covered"}],"primary_cta":{"key":"apify","label":"Apify Store","url":"https:\/\/apify.com\/zentrafoundry\/common-crawl-targeted-corpus-builder","status":"published","primary":true,"cta_label":"Open on Apify","ctaLabel":"Open on Apify","public_safe":true,"publicSafe":true},"sample":{"rows":[{"status":"fixture_validated","summary":"Deterministic fixture Summary for Common Crawl Targeted Corpus Builder","sourceUrl":"https:\/\/apify.com\/zentrafoundry\/common-crawl-targeted-corpus-builder","entityName":"Deterministic fixture Entity Name for Common Crawl Targeted Corpus Builder","entityType":"common_crawl_targeted_corpus_builder_entity_type","signalType":"common_crawl_targeted_corpus_builder_signal_type","effectiveAt":"2026-07-01","jurisdiction":"Deterministic fixture Jurisdiction for Common Crawl Targeted Corpus Builder","recordIdentifier":"Deterministic fixture Record Identifier for Common Crawl Targeted Corpus Builder","recommendedAction":"Deterministic fixture Recommended Action for Common Crawl Targeted Corpus Builder"},{"status":"fixture_validated 2","summary":"Deterministic fixture Summary for Common Crawl Targeted Corpus Builder 2","sourceUrl":"https:\/\/apify.com\/zentrafoundry\/common-crawl-targeted-corpus-builder","entityName":"Deterministic fixture Entity Name for Common Crawl Targeted Corpus Builder 2","entityType":"common_crawl_targeted_corpus_builder_entity_type 2","signalType":"common_crawl_targeted_corpus_builder_signal_type 2","effectiveAt":"2026-07-01","jurisdiction":"Deterministic fixture Jurisdiction for Common Crawl Targeted Corpus Builder 2","recordIdentifier":"Deterministic fixture Record Identifier for Common Crawl Targeted Corpus Builder 2","recommendedAction":"Deterministic fixture Recommended Action for Common Crawl Targeted Corpus Builder 2"},{"status":"fixture_validated 3","summary":"Deterministic fixture Summary for Common Crawl Targeted Corpus Builder 3","sourceUrl":"https:\/\/apify.com\/zentrafoundry\/common-crawl-targeted-corpus-builder","entityName":"Deterministic fixture Entity Name for Common Crawl Targeted Corpus Builder 3","entityType":"common_crawl_targeted_corpus_builder_entity_type 3","signalType":"common_crawl_targeted_corpus_builder_signal_type 3","effectiveAt":"2026-07-01","jurisdiction":"Deterministic fixture Jurisdiction for Common Crawl Targeted Corpus Builder 3","recordIdentifier":"Deterministic fixture Record Identifier for Common Crawl Targeted Corpus Builder 3","recommendedAction":"Deterministic fixture Recommended Action for Common Crawl Targeted Corpus Builder 3"}],"title":"Regulatory Status Signal sample rows","fields":["entityName","entityType","jurisdiction","recordIdentifier","signalType","status","effectiveAt","sourceUrl","summary","recommendedAction"],"source":"product_output_contract","row_count":3,"sample_type":"deterministic_public_source_fixture","record_label":"regulatory_status_signal","refreshed_at":"2026-07-31T00:57:12.000000Z","sample_status":"valid_public_sample","missing_reason":null,"sample_available":true},"schema_preview":{"fields":[{"name":"entityName","type":"string","required":true,"description":"Publicly registered entity or regulated subject."},{"name":"entityType","type":"string","required":true,"description":"Normalized regulated entity type."},{"name":"jurisdiction","type":"string","required":true,"description":"Public authority jurisdiction."},{"name":"recordIdentifier","type":"string","required":true,"description":"Stable public registry or regulatory record identifier."},{"name":"signalType","type":"string","required":true,"description":"Normalized public regulatory change type."},{"name":"status","type":"string","required":true,"description":"Current normalized public record status."},{"name":"effectiveAt","type":"string","required":true,"description":"Effective date of the public regulatory status."},{"name":"sourceUrl","type":"string","required":true,"description":"Public registry or authority source URL."},{"name":"summary","type":"string","required":true,"description":"Buyer-facing summary of the public regulatory change."},{"name":"recommendedAction","type":"string","required":true,"description":"Suggested buyer review step."}],"source":"product_output_contract","field_count":10,"schema_hash":"35fc9f18e8b40f1a38f7d9acc52733c9f4f3a85b","record_label":"regulatory_status_signal","manifest_path":"apify:\/\/actors\/zentrafoundry\/common-crawl-targeted-corpus-builder","required_fields":["entityName","entityType","jurisdiction","recordIdentifier","signalType","status","effectiveAt","sourceUrl","summary","recommendedAction"]},"update_cadence":"Catalog release","freshness_label":"2026-08-17T10:00:15.119197Z","provenance":[{"label":"Foundry revenue-ready product catalog","source":"Generated route-native product metadata"}],"quality":{"content_score":100,"requires_owner_review":true,"source":"zentra_products"},"pricing_hint":{"model":"Apify actor + public-safe sample dataset + marketplace package","visible":true,"currency":"EUR"},"pricing_events":[],"related_products":[],"related_use_cases":[],"is_bundle":false,"bundle_type":null,"bundle_family":null,"bundle_version":null,"member_count":0,"member_products":[],"bundle_coverage":{"apify_actor":{"family":"corpus_builder","outputs":["default","chunks","summary"]}},"flags":[],"route":"apify","category":"apify_actor_product","is_visible":true,"is_x402_eligible":true,"is_x402_ready":true,"content_score":100,"canonical_path":"\/actors\/common-crawl-targeted-corpus-builder","api_path":"\/api\/public\/foundry\/products\/common-crawl-targeted-corpus-builder","seo":{"title":"Common Crawl Targeted Corpus Builder","description":"Common Crawl Targeted Corpus Builder packages Query domains\/topics, fetch CC pages, clean Markdown, dedupe, language\/license heuristics into a source-governed Apify actor with sample mode, schema, pricing, QA evidence, and marketplac...","noindex":false},"last_updated_at":"2026-08-17T12:00:15+02:00"}}