{ "openapi": "3.0.1", "info": { "title": "Quora Dataset Builder", "description": "Build bounded normalized Quora datasets from public URLs or native search seeds.", "version": "1.0", "x-build-id": "zCThrDbgZHBTgJiO8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/crawlerbros~quora-dataset-builder/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-crawlerbros-quora-dataset-builder", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/crawlerbros~quora-dataset-builder/runs": { "post": { "operationId": "runs-sync-crawlerbros-quora-dataset-builder", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/crawlerbros~quora-dataset-builder/run-sync": { "post": { "operationId": "run-sync-crawlerbros-quora-dataset-builder", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "scrapeDepth": { "title": "Scrape Depth", "enum": [ "overview", "detail" ], "type": "string", "description": "Overview emits page-level summaries without answer/comment/activity/feed expansion; detail preserves the current bounded traversal.", "default": "detail" }, "startUrls": { "title": "Quora URLs", "type": "array", "description": "Question, answer, profile, topic, Space, or native search URLs.", "default": [], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "searchQueries": { "title": "Search Queries", "type": "array", "description": "Native Quora search seeds. Search cards are followed only when their visible URLs are supported.", "items": { "type": "string" }, "default": [] }, "questionUrls": { "title": "Question URLs", "type": "array", "description": "Explicit question-page seeds. Only question routes are accepted.", "items": { "type": "object", "properties": { "url": { "title": "URL", "description": "A Quora URL.", "type": "string" } }, "required": [ "url" ] }, "default": [] }, "answerUrls": { "title": "Answer URLs", "type": "array", "description": "Explicit answer-page seeds. Parent question joins are emitted only from observed evidence.", "items": { "type": "object", "properties": { "url": { "title": "URL", "description": "A Quora URL.", "type": "string" } }, "required": [ "url" ] }, "default": [] }, "topicUrls": { "title": "Topic URLs", "type": "array", "description": "Explicit Topic-page seeds for bounded visible question discovery.", "items": { "type": "object", "properties": { "url": { "title": "URL", "description": "A Quora URL.", "type": "string" } }, "required": [ "url" ] }, "default": [] }, "spaceUrls": { "title": "Space URLs", "type": "array", "description": "Explicit Space-page seeds for bounded visible feed discovery.", "items": { "type": "object", "properties": { "url": { "title": "URL", "description": "A Quora URL.", "type": "string" } }, "required": [ "url" ] }, "default": [] }, "profileUrls": { "title": "Profile URLs", "type": "array", "description": "Explicit profile-page seeds. Only profile routes are accepted; emitted as normalized profile rows exactly like a profile route discovered from startUrls.", "items": { "type": "object", "properties": { "url": { "title": "URL", "description": "A Quora URL.", "type": "string" } }, "required": [ "url" ] }, "default": [] }, "postUrls": { "title": "Post URLs", "type": "array", "description": "Explicit standalone Post-page seeds. Only post routes are accepted; emitted with the same topic_post field family topic-discovered posts use (post_title, post_body, post_author_*).", "items": { "type": "object", "properties": { "url": { "title": "URL", "description": "A Quora URL.", "type": "string" } }, "required": [ "url" ] }, "default": [] }, "resultTypes": { "title": "Result Types", "type": "array", "description": "Select normalized entities, explicit graph relationships, relationship-collection counts, status rows, and the final run manifest.", "items": { "type": "string", "enum": [ "question", "answer", "comment", "profile", "profile_activity", "topic", "topic_post", "space", "space_feed_item", "entity_edge", "relationship_collection", "status", "run_manifest" ] }, "default": [ "question", "answer", "comment", "profile", "profile_activity", "topic", "topic_post", "space", "space_feed_item", "entity_edge", "status", "run_manifest" ] }, "outputFormat": { "title": "Output Format", "enum": [ "normalized", "nested", "flat", "edges" ], "type": "string", "description": "Projection after one canonical extraction path. Nested groups emitted answers and comments under explicit question/answer parents; flat keeps entity rows with parent context; edges emits explicit edge rows plus status rows.", "default": "normalized" }, "dedupeMode": { "title": "Deduplication Mode", "enum": [ "canonical", "none" ], "type": "string", "description": "canonical suppresses overlapping entity rows by stable ID or canonical URL (default); none preserves every observed non-status row. The run manifest reports duplicate_records_suppressed.", "default": "canonical" }, "onlyNewItems": { "title": "Only New or Changed Items", "type": "boolean", "description": "Annotate canonical entity rows with new/changed/unchanged/scope_mismatch state and suppress only unchanged semantic rows when includeUnchanged is false. Requires stateStoreId; status, graph, and manifest rows remain visible.", "default": false }, "includeUnchanged": { "title": "Include Unchanged Items", "type": "boolean", "description": "Retain unchanged semantic entities when incremental state is enabled; output projection does not alter comparison hashes.", "default": true }, "stateStoreId": { "title": "Incremental State Store ID", "type": "string", "description": "Apify key-value store for canonical entity snapshots. Required when onlyNewItems is enabled; never store cookies or credentials here.", "default": "" }, "outputFields": { "title": "Output Fields", "maxItems": 3000, "type": "array", "description": "Optional allowlist for compact rows, including bounded dotted paths through nested collections (for example answers.answer_text, comments.comment_text, feed.feed_text, or contributors.contributor_name where applicable). Child identity/URL fields and the actor identity, access/status, source, traversal, graph, filter, and parser-envelope fields remain protected.", "items": { "type": "string" }, "default": [] }, "includeFieldEvidence": { "title": "Include Field Evidence", "type": "boolean", "description": "Include field_sources and fields_present maps. Disable only when a smaller payload is required; semantic values and protected access fields remain unchanged.", "default": true }, "includeUnresolvedEdges": { "title": "Include Unresolved Edges", "type": "boolean", "description": "Retain relationship rows whose endpoint URL was not explicitly observed, with unresolved_reason. Disabling this suppresses only those edge rows and does not imply complete relationships.", "default": true }, "relationshipTypes": { "title": "Relationship Types", "type": "array", "description": "Explicit relationship-type allowlist for the newly ported follower/following/want-answers/upvoter/space-role relationship collections. Empty leaves the existing always-on content-membership/authorship edges untouched (question_has_topic, answer_authored_by, comment_belongs_to_answer, profile_has_activity, space_has_feed_item, etc.); this allowlist only gates the additional collections below. Sensitive follower/want-answer/upvoter types also require includeSensitiveRelationshipData and their matching collection opt-in.", "items": { "type": "string", "enum": [ "profile_follows_profile", "profile_followed_by_profile", "profile_follows_question", "profile_follows_space", "profile_follows_topic", "profile_has_expertise", "question_followed_by_profile", "question_wants_answers_from_profile", "answer_upvoted_by_profile", "space_followed_by_profile", "space_has_contributor", "space_has_moderator", "space_has_admin", "space_contains_post", "space_contains_question", "space_contains_unanswered_question", "profile_authored_answer", "profile_authored_question", "profile_authored_post", "question_has_topic", "question_has_answer", "answer_belongs_to_question", "answer_authored_by_profile", "comment_belongs_to_answer", "comment_reply_to_comment", "comment_authored_by_profile", "post_authored_by_profile", "post_in_space", "profile_has_activity", "space_has_feed_item" ] }, "default": [] }, "includeProfileEdges": { "title": "Include Profile Relationship Collections", "type": "boolean", "description": "Enable explicitly labeled profile follower/following/followed-question/Space/Topic relationship collections. This does not prove a complete list.", "default": false }, "includeQuestionFollowerEdges": { "title": "Include Question Follower Collections", "type": "boolean", "description": "Enable explicitly labeled question follower or want-answer collections. Sensitive identity rows also require the privacy gate.", "default": false }, "includeAnswerUpvoterEdges": { "title": "Include Answer Upvoter Collections", "type": "boolean", "description": "High-sensitivity opt-in for explicitly labeled answer upvoter identities; requires includeSensitiveRelationshipData=true.", "default": false }, "includeSensitiveRelationshipData": { "title": "Sensitive Relationship Data", "type": "boolean", "description": "Explicit privacy gate required for follower, want-answer, and upvoter identity edges.", "default": false }, "includeTargetMetadata": { "title": "Include Explicit Target Metadata", "type": "boolean", "description": "Retain explicitly visible target link text and image (to_name, to_image_url) on relationship edges. URLs remain evidence; no target navigation or recursive target scraping is performed.", "default": false }, "includeRelationshipCounts": { "title": "Include Relationship Collection Counts", "type": "boolean", "description": "Emit privacy-preserving relationship_collection rows with the real observed total (collection_total_text/collection_total_value) but no target identities. Requires relationship_collection in resultTypes. Observed totals are not always a server-confirmed count.", "default": false }, "includeSpaceRoleEdges": { "title": "Include Space Role Edges", "type": "boolean", "description": "Enable explicitly labeled Space contributor, moderator, and admin collections.", "default": false }, "includeSpaceContentEdges": { "title": "Include Space Content Edges", "type": "boolean", "description": "Retain bounded explicit Space post/question membership edges; this never claims a complete Space inventory.", "default": true }, "maxRelationshipItemsPerCollection": { "title": "Maximum Relationship Items per Collection", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Bound explicit links emitted from each labeled relationship collection. Zero emits no relationship-collection edges and never means an empty collection.", "default": 500 }, "maxQuestions": { "title": "Maximum Questions", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Maximum question seeds or discovered question pages to process.", "default": 25 }, "maxAnswersPerQuestion": { "title": "Maximum Answers per Question", "minimum": 0, "maximum": 500, "type": "integer", "description": "Maximum visible answer rows retained from each question page.", "default": 10 }, "maxAnswers": { "title": "Maximum Answers Total", "minimum": 0, "maximum": 50000, "type": "integer", "description": "Global answer-row cap applied after per-question caps. Zero means no configured global answer cap.", "default": 0 }, "includeQuestion": { "title": "Include Question Rows", "type": "boolean", "description": "Retain normalized question parent rows when selected in resultTypes.", "default": true }, "includeAuthor": { "title": "Include Author Rows", "type": "boolean", "description": "Retain visible author fields and profile/profile-activity rows. When false, author fields and author rows are removed from the emitted shape; no contact enrichment is performed.", "default": true }, "includeAuthorSnapshot": { "title": "Include Author Snapshot", "type": "boolean", "description": "Opt into bounded public profile snapshots for visible author profile links; profile access/status is separate from answer/comment success and never includes contact enrichment.", "default": false }, "includeTopics": { "title": "Include Topic Links", "type": "boolean", "description": "Retain explicit topic links and topic relationships where observed.", "default": true }, "includeSpaces": { "title": "Include Space Rows", "type": "boolean", "description": "Retain Space rows and feed items where the source route exposes them.", "default": false }, "includeComments": { "title": "Include Comment Rows", "type": "boolean", "description": "Enable bounded visible comment output when the per-answer cap is positive.", "default": false }, "includeEngagementBreakdown": { "title": "Include Engagement Breakdown", "type": "boolean", "description": "Retain explicitly labeled per-comment reaction breakdowns alongside aggregate reaction labels. Raw labels are preserved and typed companions are added only when the localized number is unambiguous.", "default": true }, "includeRelatedContent": { "title": "Include Answer Related Content", "type": "boolean", "description": "Retain links inside an explicitly labeled related/attached region scoped to answer cards; unlabeled navigation and neighboring regions are excluded.", "default": false }, "maxRelatedContent": { "title": "Maximum Answer Related Content", "minimum": 0, "maximum": 100, "type": "integer", "description": "Bound eligible related-content links per answer when enabled; zero emits no related-content items.", "default": 20 }, "topCommentsOnly": { "title": "Top-Labeled Comments Only", "type": "boolean", "description": "Retain only comments with an explicit visible Top/Most helpful/Popular comments label. Unknown comments are excluded and counted; votes and position are not used as top evidence.", "default": false }, "commentSortOrder": { "title": "Comment Sort Order", "enum": [ "observed", "upvotes_desc", "reactions_desc", "replies_desc", "newest" ], "type": "string", "description": "Order builder comment rows by observed order or an explicitly typed metric/timestamp. Unknown selected metrics remain in stable fallback order and are counted.", "default": "observed" }, "includeReplyGraph": { "title": "Include Reply Graph", "type": "boolean", "description": "Enable bounded visible nested comment replies and explicit parent paths; this also enables comment rows. Hidden or unexpanded replies are not inferred.", "default": false }, "includeMedia": { "title": "Include Media URLs", "type": "boolean", "description": "Request explicitly rendered media URL fields scoped to question roots, answer/comment nodes, and Topic post cards where the page exposes them.", "default": false }, "includeFeedText": { "title": "Include Space Feed Text", "type": "boolean", "description": "Request bounded visible text from explicitly linked Space feed cards; page-level text and complete feed history are excluded.", "default": false }, "includeOutboundLinks": { "title": "Include Outbound Links", "type": "boolean", "description": "Request visible non-Quora links scoped to question roots, answer/comment nodes, and Topic post cards; Quora links, comment permalinks, and links outside the owning scope are excluded.", "default": false }, "includeEntityGraph": { "title": "Include Entity Graph", "type": "boolean", "description": "Emit explicit relationship rows even when entity_edge is not listed in resultTypes.", "default": false }, "maxCommentsPerAnswer": { "title": "Maximum Comments per Answer", "minimum": 0, "maximum": 500, "type": "integer", "description": "Maximum visible comment rows retained per answer when enabled.", "default": 0 }, "maxCommentDepth": { "title": "Maximum Comment Depth", "minimum": 0, "maximum": 100, "type": "integer", "description": "Maximum visible nested reply depth when includeReplyGraph is enabled; reaching the bound is not complete history.", "default": 20 }, "maxItems": { "title": "Maximum Entity Rows", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Cap for normalized entity/status rows before graph and manifest rows.", "default": 0 }, "maxGraphEdges": { "title": "Maximum Graph Edges", "minimum": 0, "maximum": 50000, "type": "integer", "description": "Independent cap for deterministic entity_edge rows.", "default": 5000 }, "maxScrollAttempts": { "title": "Maximum Scroll Attempts", "minimum": 0, "maximum": 20, "type": "integer", "description": "Bounded lazy-render scroll budget applied during detail traversal; scroll attempts and termination state are reported.", "default": 5 }, "maxLoadMoreAttempts": { "title": "Maximum Load-more Attempts", "minimum": 0, "maximum": 20, "type": "integer", "description": "Bound exact visible continuation-control clicks on direct question, answer, topic, and Space collection pages independently from scrolling. Search seeds fan out through their discovered child URLs and retain their own source accounting.", "default": 0 }, "includeRawEvidence": { "title": "Include Raw Evidence", "type": "boolean", "description": "Add bounded document hash and optional HTML bytes to each page-level entity row.", "default": false }, "includeHtml": { "title": "Include HTML", "type": "boolean", "description": "Include bounded raw-document HTML when raw evidence is enabled and bounded answer-card HTML when answer cards are extracted.", "default": false }, "maxHtmlBytes": { "title": "Maximum HTML Bytes", "minimum": 1000, "maximum": 2000000, "type": "integer", "description": "Maximum UTF-8 bytes retained for optional raw HTML evidence.", "default": 100000 }, "requestDelay": { "title": "Request Delay", "minimum": 0, "maximum": 30, "type": "number", "description": "Delay between page batches in seconds; this is not an anti-bot bypass guarantee.", "default": 1 }, "maxConcurrency": { "title": "Maximum Concurrent Seeds", "minimum": 1, "maximum": 3, "type": "integer", "description": "Maximum independent seed pages processed concurrently in deterministic batches. Each seed owns a page; discovered seeds merge in batch order.", "default": 1 }, "maxNavigationRetries": { "title": "Maximum Navigation Retries", "minimum": 0, "maximum": 3, "type": "integer", "description": "Bounded retries after navigation exceptions (e.g. a transient proxy-tunnel handshake failure); exponential backoff is reported in navigation_retry_delays_seconds. Defaults to 2 for reliability.", "default": 2 }, "language": { "title": "Language", "enum": [ "auto", "en", "es", "fr", "de", "pt", "it", "ja", "ko", "hi", "id", "nl", "pl", "tr", "vi", "zh", "ru", "en-US", "en-GB", "de-DE", "fr-FR", "es-ES", "pt-BR", "it-IT", "ja-JP", "ko-KR", "hi-IN", "tr-TR", "zh-CN", "zh-TW", "ru-RU" ], "type": "string", "description": "Browser language hint. Short language codes and supported regional aliases are accepted and normalize to the short code; auto keeps the actor default. This does not translate content or prove access.", "default": "auto" }, "cookies": { "title": "Authorized Cookies", "type": "array", "description": "Optional secret cookies for content the caller is authorized to access.", "items": { "type": "object" } }, "cookieString": { "title": "Optional Cookie Header String", "type": "string", "description": "Optional browser-exported name=value; name2=value2 header. Parsed locally into authorized session cookies; the raw header is never emitted or logged." }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Apify proxy routing. Quora's anti-bot layer blocks the free Datacenter/Automatic tier on roughly half of all real requests (cloud-verified), so this actor always routes through RESIDENTIAL proxies for reliable results regardless of what is selected here — leave this on the default Residential selection unless you need to supply your own proxy URLs.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "redactSensitiveQueryParams": { "title": "Redact Sensitive URL Query Values", "type": "boolean", "description": "Redact narrow credential-like query parameter values in emitted URLs, graph endpoints, redirect chains, and raw HTML. The original document hash remains based on the captured document.", "default": true }, "rawEvidenceRetentionDays": { "title": "Raw Evidence Retention Days", "minimum": 0, "maximum": 30, "type": "integer", "description": "When zero, suppress raw_html snapshots while retaining hash, size, and redaction diagnostics. Positive values permit bounded HTML for the requested run; external Apify dataset/run retention still applies.", "default": 30 }, "maxRawEvidenceBytes": { "title": "Maximum Raw Evidence Bytes", "minimum": 1000, "maximum": 2000000, "type": "integer", "description": "Hard upper byte cap for returned raw HTML after the maxHtmlBytes cap.", "default": 100000 }, "maxItemsPerSource": { "title": "Maximum Items Per Source", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Maximum semantic records emitted from each direct URL, query, or typed source. Status and run-manifest rows are preserved. Use 0 for no per-source cap.", "default": 0 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }