{ "data": { "id": "yJ2UZKFwANg4ScxlV", "actId": "uAivkcIOWnHGsAnKT", "userId": "IYgBDiXtHOijAaUel", "startedAt": "2026-10-29T06:56:52.092Z", "finishedAt": "2026-10-29T06:57:28.802Z", "status": "SUCCEEDED", "meta": { "origin": "CLI" }, "stats": { "durationMillis": 36529, "runTimeSecs": 36.529, "computeUnits": 0.04058777777777778, "imageSizeBytes": 3143940096 }, "options": { "useCache": true, "betaPackages": false, "memoryMbytes": 4096, "diskMbytes": 8192 }, "createdByOrganizationMemberUserId": "QYo53EZkJk0prePWY", "exitCode": 0, "inputSchema": "{\n \"title\": \"Quora Dataset Builder Input\",\n \"type\": \"object\",\n \"schemaVersion\": 1,\n \"properties\": {\n \"mode\": {\n \"title\": \"Mode\",\n \"type\": \"string\",\n \"editor\": \"select\",\n \"enum\": [\n \"auto\",\n \"byQuestionUrls\",\n \"byAnswerUrls\",\n \"byProfileUrls\",\n \"byTopicUrls\",\n \"bySpaceUrls\",\n \"byPostUrls\",\n \"search\"\n ],\n \"enumTitles\": [\n \"Auto-detect any supported URL\",\n \"Questions and answers\",\n \"Specific answer permalinks\",\n \"Profiles and stats\",\n \"Topics and optional feed\",\n \"Spaces and feeds\",\n \"Standalone posts\",\n \"Best-effort search discovery\"\n ],\n \"default\": \"auto\",\n \"prefill\": \"auto\",\n \"description\": \"Optional dispatcher. auto detects every supported Quora route; typed modes validate startUrls against that route. Typed seed lists still work without mode.\"\n },\n \"scrapeDepth\": {\n \"title\": \"Scrape Depth\",\n \"type\": \"string\",\n \"enum\": [\n \"overview\",\n \"detail\"\n ],\n \"enumTitles\": [\n \"Overview (page metadata only)\",\n \"Detail (answers, comments, feeds)\"\n ],\n \"default\": \"detail\",\n \"prefill\": \"detail\",\n \"description\": \"Overview emits page metadata without answer/comment/feed expansion; detail enables SSR answers plus bounded GraphQL pagination and optional comments/topic feeds.\"\n },\n \"startUrls\": {\n \"title\": \"Quora URLs\",\n \"type\": \"array\",\n \"editor\": \"requestListSources\",\n \"description\": \"Question, answer, profile, topic, Space, or search URLs. Mixed lists are auto-detected; invalid hosts become status rows instead of failing the run.\",\n \"default\": [],\n \"prefill\": [\n {\n \"url\": \"https://www.quora.com/What-is-the-meaning-of-life\"\n }\n ]\n },\n \"searchQueries\": {\n \"title\": \"Search Queries\",\n \"type\": \"array\",\n \"editor\": \"stringList\",\n \"items\": {\n \"type\": \"string\"\n },\n \"default\": [],\n \"description\": \"Best-effort public-index discovery only. Quora native search is login/Cloudflare-gated and robots-disallowed; related-question expansion on a question URL is the reliable discovery axis.\"\n },\n \"questionUrls\": {\n \"title\": \"Question URLs\",\n \"type\": \"array\",\n \"editor\": \"requestListSources\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"url\": {\n \"title\": \"URL\",\n \"description\": \"A Quora URL.\",\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"url\"\n ]\n },\n \"default\": [],\n \"description\": \"Explicit question-page seeds. Only question routes are accepted.\"\n },\n \"answerUrls\": {\n \"title\": \"Answer URLs\",\n \"type\": \"array\",\n \"editor\": \"requestListSources\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"url\": {\n \"title\": \"URL\",\n \"description\": \"A Quora URL.\",\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"url\"\n ]\n },\n \"default\": [],\n \"description\": \"Explicit answer-page seeds. Parent question joins are emitted only from observed evidence.\"\n },\n \"topicUrls\": {\n \"title\": \"Topic URLs\",\n \"type\": \"array\",\n \"editor\": \"requestListSources\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"url\": {\n \"title\": \"URL\",\n \"description\": \"A Quora URL.\",\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"url\"\n ]\n },\n \"default\": [],\n \"description\": \"Explicit Topic-page seeds for bounded visible question discovery.\"\n },\n \"spaceUrls\": {\n \"title\": \"Space URLs\",\n \"type\": \"array\",\n \"editor\": \"requestListSources\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"url\": {\n \"title\": \"URL\",\n \"description\": \"A Quora URL.\",\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"url\"\n ]\n },\n \"default\": [],\n \"description\": \"Explicit Space-page seeds for bounded visible feed discovery.\"\n },\n \"profileUrls\": {\n \"title\": \"Profile URLs\",\n \"type\": \"array\",\n \"editor\": \"requestListSources\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"url\": {\n \"title\": \"URL\",\n \"description\": \"A Quora URL.\",\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"url\"\n ]\n },\n \"default\": [],\n \"description\": \"Explicit profile-page seeds. Only profile routes are accepted; emitted as normalized profile rows exactly like a profile route discovered from startUrls.\"\n },\n \"postUrls\": {\n \"title\": \"Post URLs\",\n \"type\": \"array\",\n \"editor\": \"requestListSources\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"url\": {\n \"title\": \"URL\",\n \"description\": \"A Quora URL.\",\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"url\"\n ]\n },\n \"default\": [],\n \"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_*).\"\n },\n \"resultTypes\": {\n \"title\": \"Result Types\",\n \"type\": \"array\",\n \"description\": \"Select normalized entities, explicit graph relationships, relationship-collection counts, status rows, and the final run manifest.\",\n \"editor\": \"select\",\n \"items\": {\n \"type\": \"string\",\n \"enum\": [\n \"question\",\n \"answer\",\n \"comment\",\n \"profile\",\n \"profile_activity\",\n \"topic\",\n \"topic_post\",\n \"space\",\n \"space_feed_item\",\n \"entity_edge\",\n \"relationship_collection\",\n \"status\",\n \"run_manifest\"\n ]\n },\n \"default\": [\n \"question\",\n \"answer\",\n \"comment\",\n \"profile\",\n \"profile_activity\",\n \"topic\",\n \"topic_post\",\n \"space\",\n \"space_feed_item\",\n \"entity_edge\",\n \"status\",\n \"run_manifest\"\n ]\n },\n \"outputFormat\": {\n \"title\": \"Output Format\",\n \"type\": \"string\",\n \"enum\": [\n \"normalized\",\n \"nested\",\n \"flat\",\n \"edges\"\n ],\n \"enumTitles\": [\n \"Normalized (one row per entity)\",\n \"Nested (answers under questions)\",\n \"Flat (entity rows with parent context)\",\n \"Edges (relationship rows)\"\n ],\n \"default\": \"normalized\",\n \"prefill\": \"normalized\",\n \"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.\"\n },\n \"dedupeMode\": {\n \"title\": \"Deduplication Mode\",\n \"type\": \"string\",\n \"enum\": [\n \"canonical\",\n \"none\"\n ],\n \"enumTitles\": [\n \"Canonical (deduplicate by ID/URL)\",\n \"None (keep every observed row)\"\n ],\n \"default\": \"canonical\",\n \"prefill\": \"canonical\",\n \"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.\"\n },\n \"onlyNewItems\": {\n \"title\": \"Only New or Changed Items\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"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.\"\n },\n \"includeUnchanged\": {\n \"title\": \"Include Unchanged Items\",\n \"type\": \"boolean\",\n \"default\": true,\n \"prefill\": true,\n \"description\": \"Retain unchanged semantic entities when incremental state is enabled; output projection does not alter comparison hashes.\"\n },\n \"stateStoreId\": {\n \"title\": \"Incremental State Store ID\",\n \"type\": \"string\",\n \"editor\": \"textfield\",\n \"default\": \"\",\n \"description\": \"Apify key-value store for canonical entity snapshots. Required when onlyNewItems is enabled; never store cookies or credentials here.\"\n },\n \"outputFields\": {\n \"title\": \"Output Fields\",\n \"type\": \"array\",\n \"editor\": \"stringList\",\n \"items\": {\n \"type\": \"string\"\n },\n \"default\": [],\n \"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.\",\n \"maxItems\": 3000\n },\n \"includeFieldEvidence\": {\n \"title\": \"Include Field Evidence\",\n \"type\": \"boolean\",\n \"default\": true,\n \"prefill\": true,\n \"description\": \"Include field_sources and fields_present maps. Disable only when a smaller payload is required; semantic values and protected access fields remain unchanged.\"\n },\n \"includeUnresolvedEdges\": {\n \"title\": \"Include Unresolved Edges\",\n \"type\": \"boolean\",\n \"default\": true,\n \"prefill\": true,\n \"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.\"\n },\n \"relationshipTypes\": {\n \"title\": \"Relationship Types\",\n \"type\": \"array\",\n \"editor\": \"select\",\n \"items\": {\n \"type\": \"string\",\n \"enum\": [\n \"profile_follows_profile\",\n \"profile_followed_by_profile\",\n \"profile_follows_question\",\n \"profile_follows_space\",\n \"profile_follows_topic\",\n \"profile_has_expertise\",\n \"question_followed_by_profile\",\n \"question_wants_answers_from_profile\",\n \"answer_upvoted_by_profile\",\n \"space_followed_by_profile\",\n \"space_has_contributor\",\n \"space_has_moderator\",\n \"space_has_admin\",\n \"space_contains_post\",\n \"space_contains_question\",\n \"space_contains_unanswered_question\",\n \"profile_authored_answer\",\n \"profile_authored_question\",\n \"profile_authored_post\",\n \"question_has_topic\",\n \"question_has_answer\",\n \"answer_belongs_to_question\",\n \"answer_authored_by_profile\",\n \"comment_belongs_to_answer\",\n \"comment_reply_to_comment\",\n \"comment_authored_by_profile\",\n \"post_authored_by_profile\",\n \"post_in_space\",\n \"profile_has_activity\",\n \"space_has_feed_item\"\n ]\n },\n \"default\": [],\n \"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.\"\n },\n \"includeProfileEdges\": {\n \"title\": \"Include Profile Relationship Collections\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"description\": \"Enable explicitly labeled profile follower/following/followed-question/Space/Topic relationship collections. This does not prove a complete list.\"\n },\n \"includeQuestionFollowerEdges\": {\n \"title\": \"Include Question Follower Collections\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"description\": \"Enable explicitly labeled question follower or want-answer collections. Sensitive identity rows also require the privacy gate.\"\n },\n \"includeAnswerUpvoterEdges\": {\n \"title\": \"Include Answer Upvoter Collections\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"description\": \"High-sensitivity opt-in for explicitly labeled answer upvoter identities; requires includeSensitiveRelationshipData=true.\"\n },\n \"includeSensitiveRelationshipData\": {\n \"title\": \"Sensitive Relationship Data\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"description\": \"Explicit privacy gate required for follower, want-answer, and upvoter identity edges.\"\n },\n \"includeTargetMetadata\": {\n \"title\": \"Include Explicit Target Metadata\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"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.\"\n },\n \"includeRelationshipCounts\": {\n \"title\": \"Include Relationship Collection Counts\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"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.\"\n },\n \"includeSpaceRoleEdges\": {\n \"title\": \"Include Space Role Edges\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"description\": \"Enable explicitly labeled Space contributor, moderator, and admin collections.\"\n },\n \"includeSpaceContentEdges\": {\n \"title\": \"Include Space Content Edges\",\n \"type\": \"boolean\",\n \"default\": true,\n \"prefill\": true,\n \"description\": \"Retain bounded explicit Space post/question membership edges; this never claims a complete Space inventory.\"\n },\n \"maxRelationshipItemsPerCollection\": {\n \"title\": \"Maximum Relationship Items per Collection\",\n \"type\": \"integer\",\n \"default\": 500,\n \"minimum\": 0,\n \"maximum\": 5000,\n \"description\": \"Bound explicit links emitted from each labeled relationship collection. Zero emits no relationship-collection edges and never means an empty collection.\"\n },\n \"maxQuestions\": {\n \"title\": \"Maximum Questions\",\n \"type\": \"integer\",\n \"description\": \"Maximum question seeds or discovered question pages to process.\",\n \"default\": 25,\n \"minimum\": 0,\n \"maximum\": 1000,\n \"prefill\": 10\n },\n \"maxAnswersPerQuestion\": {\n \"title\": \"Maximum Answers per Question\",\n \"type\": \"integer\",\n \"description\": \"Maximum answer rows retained per question after SSR and GraphQL pagination.\",\n \"default\": 10,\n \"minimum\": 0,\n \"maximum\": 500,\n \"prefill\": 5\n },\n \"maxAnswers\": {\n \"title\": \"Maximum Answers Total\",\n \"type\": \"integer\",\n \"default\": 0,\n \"minimum\": 0,\n \"maximum\": 50000,\n \"description\": \"Global answer-row cap applied after per-question caps. Zero means no configured global answer cap.\"\n },\n \"includeQuestion\": {\n \"title\": \"Include Question Rows\",\n \"type\": \"boolean\",\n \"default\": true,\n \"prefill\": true,\n \"description\": \"Retain normalized question parent rows when selected in resultTypes.\"\n },\n \"includeAuthor\": {\n \"title\": \"Include Author Rows\",\n \"type\": \"boolean\",\n \"default\": true,\n \"prefill\": true,\n \"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.\"\n },\n \"includeAuthorSnapshot\": {\n \"title\": \"Include Author Snapshot\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"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.\"\n },\n \"includeTopics\": {\n \"title\": \"Include Topic Links\",\n \"type\": \"boolean\",\n \"default\": true,\n \"prefill\": true,\n \"description\": \"Retain explicit topic links and topic relationships where observed.\"\n },\n \"includeSpaces\": {\n \"title\": \"Include Space Rows\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"description\": \"Retain Space rows and SSR feed items. Explicit spaceUrls enable this automatically.\"\n },\n \"includeComments\": {\n \"title\": \"Include Comment Rows\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"description\": \"Opt-in comment rows from Quora's public comment-area GraphQL. robots-sensitive; off by default. When enabled and maxCommentsPerAnswer is 0, the documented fallback is 10 per answer.\"\n },\n \"includeEngagementBreakdown\": {\n \"title\": \"Include Engagement Breakdown\",\n \"type\": \"boolean\",\n \"default\": true,\n \"prefill\": true,\n \"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.\"\n },\n \"includeRelatedContent\": {\n \"title\": \"Include Answer Related Content\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"description\": \"Retain links inside an explicitly labeled related/attached region scoped to answer cards; unlabeled navigation and neighboring regions are excluded.\"\n },\n \"maxRelatedContent\": {\n \"title\": \"Maximum Answer Related Content\",\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 100,\n \"default\": 20,\n \"description\": \"Bound eligible related-content links per answer when enabled; zero emits no related-content items.\"\n },\n \"topCommentsOnly\": {\n \"title\": \"Top-Labeled Comments Only\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"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.\"\n },\n \"commentSortOrder\": {\n \"title\": \"Comment Sort Order\",\n \"type\": \"string\",\n \"enum\": [\n \"observed\",\n \"upvotes_desc\",\n \"reactions_desc\",\n \"replies_desc\",\n \"newest\"\n ],\n \"enumTitles\": [\n \"Observed order\",\n \"Most upvotes\",\n \"Most reactions\",\n \"Most replies\",\n \"Newest first\"\n ],\n \"default\": \"observed\",\n \"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.\"\n },\n \"includeReplyGraph\": {\n \"title\": \"Include Reply Graph\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"description\": \"Enable comment rows plus one-level nested reply extraction from repliesConnection. Requires includeComments.\"\n },\n \"includeMedia\": {\n \"title\": \"Include Media URLs\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"description\": \"Request explicitly rendered media URL fields scoped to question roots, answer/comment nodes, and Topic post cards where the page exposes them.\"\n },\n \"includeFeedText\": {\n \"title\": \"Include Space Feed Text\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"description\": \"Request bounded visible text from explicitly linked Space feed cards; page-level text and complete feed history are excluded.\"\n },\n \"includeOutboundLinks\": {\n \"title\": \"Include Outbound Links\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"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.\"\n },\n \"includeEntityGraph\": {\n \"title\": \"Include Entity Graph\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"description\": \"Emit explicit relationship rows even when entity_edge is not listed in resultTypes.\"\n },\n \"maxCommentsPerAnswer\": {\n \"title\": \"Maximum Comments per Answer\",\n \"type\": \"integer\",\n \"description\": \"Maximum comment rows retained per answer when comments are enabled. Schema default 0 is kept for compatibility; comments-enabled runs treat 0 as 10.\",\n \"default\": 0,\n \"minimum\": 0,\n \"maximum\": 500,\n \"prefill\": 0\n },\n \"maxCommentDepth\": {\n \"title\": \"Maximum Comment Depth\",\n \"type\": \"integer\",\n \"description\": \"Maximum nested reply depth when includeCommentReplies/includeReplyGraph is enabled.\",\n \"default\": 20,\n \"minimum\": 0,\n \"maximum\": 100,\n \"prefill\": 20\n },\n \"maxItems\": {\n \"title\": \"Maximum Entity Rows\",\n \"type\": \"integer\",\n \"default\": 0,\n \"minimum\": 0,\n \"maximum\": 5000,\n \"description\": \"Cap for normalized entity/status rows before graph and manifest rows.\"\n },\n \"maxGraphEdges\": {\n \"title\": \"Maximum Graph Edges\",\n \"type\": \"integer\",\n \"description\": \"Independent cap for deterministic entity_edge rows.\",\n \"default\": 5000,\n \"minimum\": 0,\n \"maximum\": 50000,\n \"prefill\": 1000\n },\n \"maxScrollAttempts\": {\n \"title\": \"Maximum Scroll Attempts\",\n \"type\": \"integer\",\n \"description\": \"Bounded lazy-render scroll budget applied during detail traversal; scroll attempts and termination state are reported.\",\n \"default\": 5,\n \"minimum\": 0,\n \"maximum\": 20\n },\n \"maxLoadMoreAttempts\": {\n \"title\": \"Maximum Load-more Attempts\",\n \"type\": \"integer\",\n \"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.\",\n \"default\": 0,\n \"minimum\": 0,\n \"maximum\": 20\n },\n \"includeRawEvidence\": {\n \"title\": \"Include Raw Evidence\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"description\": \"Add bounded document hash and optional HTML bytes to each page-level entity row.\"\n },\n \"includeHtml\": {\n \"title\": \"Include HTML\",\n \"type\": \"boolean\",\n \"description\": \"Include bounded raw-document HTML when raw evidence is enabled and bounded answer-card HTML when answer cards are extracted.\",\n \"default\": false,\n \"prefill\": false\n },\n \"maxHtmlBytes\": {\n \"title\": \"Maximum HTML Bytes\",\n \"type\": \"integer\",\n \"description\": \"Maximum UTF-8 bytes retained for optional raw HTML evidence.\",\n \"default\": 100000,\n \"minimum\": 1000,\n \"maximum\": 2000000\n },\n \"requestDelay\": {\n \"title\": \"Request Delay\",\n \"type\": \"number\",\n \"description\": \"Delay between page batches in seconds; this is not an anti-bot bypass guarantee.\",\n \"default\": 1,\n \"minimum\": 0,\n \"maximum\": 30\n },\n \"maxConcurrency\": {\n \"title\": \"Maximum Concurrent Seeds\",\n \"type\": \"integer\",\n \"description\": \"Maximum independent seed pages processed concurrently in deterministic batches. Each seed owns a page; discovered seeds merge in batch order.\",\n \"default\": 1,\n \"minimum\": 1,\n \"maximum\": 3\n },\n \"maxNavigationRetries\": {\n \"title\": \"Maximum Navigation Retries\",\n \"type\": \"integer\",\n \"default\": 2,\n \"minimum\": 0,\n \"maximum\": 3,\n \"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.\"\n },\n \"language\": {\n \"title\": \"Language\",\n \"type\": \"string\",\n \"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.\",\n \"enum\": [\n \"auto\",\n \"en\",\n \"es\",\n \"fr\",\n \"de\",\n \"pt\",\n \"it\",\n \"ja\",\n \"ko\",\n \"hi\",\n \"id\",\n \"nl\",\n \"pl\",\n \"tr\",\n \"vi\",\n \"zh\",\n \"ru\",\n \"en-US\",\n \"en-GB\",\n \"de-DE\",\n \"fr-FR\",\n \"es-ES\",\n \"pt-BR\",\n \"it-IT\",\n \"ja-JP\",\n \"ko-KR\",\n \"hi-IN\",\n \"tr-TR\",\n \"zh-CN\",\n \"zh-TW\",\n \"ru-RU\"\n ],\n \"enumTitles\": [\n \"Automatic\",\n \"English\",\n \"Spanish\",\n \"French\",\n \"German\",\n \"Portuguese\",\n \"Italian\",\n \"Japanese\",\n \"Korean\",\n \"Hindi\",\n \"Indonesian\",\n \"Dutch\",\n \"Polish\",\n \"Turkish\",\n \"Vietnamese\",\n \"Chinese\",\n \"Russian\",\n \"English (US)\",\n \"English (UK)\",\n \"German (Germany)\",\n \"French (France)\",\n \"Spanish (Spain)\",\n \"Portuguese (Brazil)\",\n \"Italian (Italy)\",\n \"Japanese (Japan)\",\n \"Korean (Korea)\",\n \"Hindi (India)\",\n \"Turkish (Turkey)\",\n \"Chinese (Simplified)\",\n \"Chinese (Traditional)\",\n \"Russian (Russia)\"\n ],\n \"default\": \"auto\"\n },\n \"proxyConfiguration\": {\n \"title\": \"Proxy Configuration (optional)\",\n \"type\": \"object\",\n \"description\": \"Optional proxy override. The actor starts with a direct connection, retries a fresh session on 403/429, then uses Apify AUTO datacenter proxies, and only falls back to RESIDENTIAL as a proven last resort. Leave this unset; a missing proxyConfiguration never stops the run.\",\n \"editor\": \"proxy\"\n },\n \"redactSensitiveQueryParams\": {\n \"title\": \"Redact Sensitive URL Query Values\",\n \"type\": \"boolean\",\n \"default\": true,\n \"prefill\": true,\n \"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.\"\n },\n \"rawEvidenceRetentionDays\": {\n \"title\": \"Raw Evidence Retention Days\",\n \"type\": \"integer\",\n \"default\": 30,\n \"minimum\": 0,\n \"maximum\": 30,\n \"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.\"\n },\n \"maxRawEvidenceBytes\": {\n \"title\": \"Maximum Raw Evidence Bytes\",\n \"type\": \"integer\",\n \"default\": 100000,\n \"minimum\": 1000,\n \"maximum\": 2000000,\n \"description\": \"Hard upper byte cap for returned raw HTML after the maxHtmlBytes cap.\"\n },\n \"maxItemsPerSource\": {\n \"title\": \"Maximum Items Per Source\",\n \"type\": \"integer\",\n \"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.\",\n \"default\": 0,\n \"minimum\": 0,\n \"maximum\": 5000,\n \"prefill\": 0\n },\n \"searchDiscovery\": {\n \"title\": \"Search Discovery\",\n \"type\": \"string\",\n \"editor\": \"select\",\n \"enum\": [\n \"relatedOnly\",\n \"bestEffortIndex\",\n \"off\"\n ],\n \"enumTitles\": [\n \"Related questions only (no third-party engine)\",\n \"Best-effort DuckDuckGo index\",\n \"Disabled\"\n ],\n \"default\": \"relatedOnly\",\n \"prefill\": \"relatedOnly\",\n \"description\": \"How searchQueries are handled. relatedOnly attempts Quora's public search and otherwise emits search_unavailable; bestEffortIndex queries a public web index for indexed Quora URLs. Native Quora search is never claimed.\"\n },\n \"maxRelatedQuestions\": {\n \"title\": \"Maximum Related Questions\",\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 100,\n \"default\": 20,\n \"prefill\": 0,\n \"description\": \"Related questions to enqueue per question/topic seed. The page usually exposes 26-35; zero disables related-question discovery.\"\n },\n \"searchResultsPerQuery\": {\n \"title\": \"Search Results per Query\",\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 50,\n \"default\": 10,\n \"prefill\": 0,\n \"description\": \"Maximum indexed URLs to use per search query when searchDiscovery=bestEffortIndex.\"\n },\n \"maxAnswerPages\": {\n \"title\": \"Maximum Answer GraphQL Pages\",\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 50,\n \"default\": 0,\n \"prefill\": 0,\n \"description\": \"Bound QuestionPagedListPaginationQuery pages. Zero derives a bound from maxAnswersPerQuestion.\"\n },\n \"maxTopicFeedPages\": {\n \"title\": \"Maximum Topic Feed Pages\",\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 20,\n \"default\": 3,\n \"prefill\": 0,\n \"description\": \"Bound topic-feed GraphQL pages when includeTopicFeed is enabled.\"\n },\n \"maxSpaceFeedBundles\": {\n \"title\": \"Maximum Space Feed Bundles\",\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 20,\n \"default\": 4,\n \"prefill\": 1,\n \"description\": \"Bound Space feed bundles read from the SSR multifeed.\"\n },\n \"includeCommentReplies\": {\n \"title\": \"Include Comment Replies\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"description\": \"Include nested repliesConnection rows. Requires includeComments. Comments are robots-sensitive and opt-in; zero-row/blocked results produce a status row.\"\n },\n \"includeQuoraPlusPreview\": {\n \"title\": \"Include Quora+ Preview Answers\",\n \"type\": \"boolean\",\n \"default\": true,\n \"prefill\": true,\n \"description\": \"Emit preview-only answers flagged answer_is_quora_plus/answer_text_completeness=preview. The gated remainder is never fetched or presented as full text.\"\n },\n \"includeProfileStats\": {\n \"title\": \"Include Profile Stats\",\n \"type\": \"boolean\",\n \"default\": true,\n \"prefill\": true,\n \"description\": \"Emit follower/following/answer/question/post/view counts, joined date, credentials and expertise topics for profile rows.\"\n },\n \"includeTopicStats\": {\n \"title\": \"Include Topic Stats\",\n \"type\": \"boolean\",\n \"default\": true,\n \"prefill\": true,\n \"description\": \"Emit topic follower count and most-viewed authors for topic rows.\"\n },\n \"includeSpaceStats\": {\n \"title\": \"Include Space Stats\",\n \"type\": \"boolean\",\n \"default\": true,\n \"prefill\": true,\n \"description\": \"Emit Space follower/member/contributor/moderator/admin counts, description, icon and cover.\"\n },\n \"includePostStats\": {\n \"title\": \"Include Post Stats\",\n \"type\": \"boolean\",\n \"default\": true,\n \"prefill\": true,\n \"description\": \"Emit post upvotes/views/shares/comments, effective access and question-summary flag.\"\n },\n \"includeAnswerStats\": {\n \"title\": \"Include Answer Stats\",\n \"type\": \"boolean\",\n \"default\": true,\n \"prefill\": true,\n \"description\": \"Emit answer counters, dates, AI flag, effective access and Quora+ preview flags.\"\n },\n \"includeTopicFeed\": {\n \"title\": \"Include Topic Feed\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"description\": \"Opt into the browser topic-feed GraphQL endpoint. robots-sensitive: keep off unless you accept that compliance caveat.\"\n },\n \"includeQuestionAudit\": {\n \"title\": \"Include Question Audit\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"description\": \"Opt into the public question /log page to fill question_created_at, question_view_count and the asker fields. robots.txt disallows /*/log for generic agents; the actor never includes this in the default prefill.\"\n },\n \"includeProfileHistory\": {\n \"title\": \"Include Profile History\",\n \"type\": \"boolean\",\n \"default\": false,\n \"prefill\": false,\n \"description\": \"Opt into the public profile answer/question tab GraphQL and emit bounded profile_activity rows. robots-sensitive and rate-sensitive; on a 400/403 the run keeps a profile_history_unavailable status row.\"\n },\n \"maxProfileHistoryPages\": {\n \"title\": \"Maximum Profile History Pages\",\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 20,\n \"default\": 0,\n \"prefill\": 0,\n \"description\": \"Bound for each profile history list (answers and questions) when includeProfileHistory is enabled. Zero derives three pages; one page is roughly ten items.\"\n },\n \"maxRelationshipPages\": {\n \"title\": \"Maximum Identity List Pages\",\n \"type\": \"integer\",\n \"minimum\": 0,\n \"maximum\": 20,\n \"default\": 3,\n \"prefill\": 0,\n \"description\": \"Bound for each public identity-list query (question followers, answer upvoters, profile followers/following, Space roles) after the relationship allowlist and privacy gates. Zero is treated as one page.\"\n }\n }\n}", "readme": "# Quora Question, Answer & Relationship Dataset Builder\n\nBuild a structured Quora dataset from direct links or best-effort search discovery. Point it at question, answer, profile, Topic, Space, or Post URLs and it returns normalized rows for every entity it finds, with the question → answer → comment chain and author/topic links kept intact. Choose how deep to go, how the rows are shaped, and which relationship or feed data to include.\n\nThis is an independent, third-party actor. It is not affiliated with, endorsed by, or licensed by Quora, Inc. No Quora account, login, session cookie, or paid proxy is used or required.\n\n## What this actor does\n\n- Accepts question, answer, profile, Topic, Space, and Post URLs directly, plus best-effort search discovery. Typed seed lists (`questionUrls`, `answerUrls`, `topicUrls`, `spaceUrls`, `profileUrls`, `postUrls`) override route auto-detection.\n- Empty fields are omitted; a missing field means the source did not expose it, never `null` or a sentinel.\n- Parses Quora's server-rendered Relay payloads and double-decodes the `window.ansFrontendGlobals.data.inlineQueryResults` `.push()` strings; it does not depend on CSS classes or DOM selectors for the core fields.\n- Paginates question answers with Quora's public `QuestionPagedListPaginationQuery` cursor, up to `maxAnswersPerQuestion` / `maxAnswers` / `maxAnswerPages`. Every paginated answer is checked against the page question (title/path, `linkedQuestion`, `originalQuestionIfDifferent`, and the answer permalink), so unrelated promoted answers cannot become dataset rows while legitimate merged variants still pass.\n- Paginates comment areas and nested replies through `AllCommentsListQuery` (10+ pages with `after` cursors), with `maxCommentsPerAnswer` as the hard cap; this is opt-in and robots-sensitive.\n- Optionally reads a Topic feed, a Space SSR multifeed, profile statistics, Topic statistics, and Post metrics.\n- Optionally reads the public question `/log` audit for created time, view count, and asker identity (`includeQuestionAudit`), and paginates profile answer/question history (`includeProfileHistory`).\n- Optionally resolves public identity lists for question followers, answer upvoters, profile followers/following, and Space roles through explicitly requested relationship types and the sensitive-data gate.\n- Walks the question → answer → comment chain and keeps the links between them (`entity_edge` rows), so you can rebuild the conversation tree.\n- Offers four output shapes via `outputFormat`: `normalized` (separate rows per entity, default), `nested` (answers grouped under their question, comments under their answer), `flat`, and `edges` (relationship rows plus any status rows).\n- Reports a `status` row (rather than guessing) whenever a page is blocked, login-gated, removed, or otherwise inaccessible, and a `run_manifest` row summarizing the whole run.\n- Leaves empty content fields out of each row rather than filling them with a guess. `0` and `false` are kept as real values.\n- Never emits cookie/credential material. URLs are redacted when `redactSensitiveQueryParams` is on.\n\n## Output per record\n\nEvery row carries `content_type` (`question`, `answer`, `comment`, `profile`, `profile_activity`, `topic`, `topic_post`, `space`, `space_feed_item`, `entity_edge`, `relationship_collection`, `status`, or `run_manifest`), plus shared fields: `record_id`, `title`, `url`, `canonical_url`, `source_url`, `access_state`, `scrape_timestamp`, `requested_depth`, `observed_depth`, `detail_expansion_state`, `output_format`, `matched_input`, `matched_input_kind`, and (when search seeds were used) `source_query`/`source_queries`.\n\nEvery row also carries run-context fields describing how it was collected: `source_observations`/`source_observation_count`, `redirect_chain`, `url_redaction_state`/`url_redactions`, `proxy_used`, `proxy_path_used`, `proxy_resolution_state`, `session_cookie_count`, `session_input_state`, `session_cookie_expiry_state`, `request_delay_seconds`, `browser_locale`, `requested_language`, `navigation_retries`/`navigation_retry_delays_seconds`, `parser_version` and `parser_strategy`. With `includeFieldEvidence` on (default), rows also get `field_sources` (where each value came from) and `fields_present`.\n\n`access_state` is `public` for normal pages. Other values include `login_required`, `cloudflare_challenge`, `rate_limited`, `not_found`, `removed`, `unavailable`, `quora_plus_or_gated`, `quora_plus_preview`, `redirected_to_search`, `unsupported_url`, `search_unavailable`, `answer_pagination_limited`, `answer_pagination_unavailable`, `comments_unavailable`, `comments_capped`, `topic_feed_unavailable`, `topic_feed_capped`, `space_feed_capped`, `profile_history_limited`, `profile_history_unavailable`, `question_audit_unavailable`, `relationship_identity_unavailable`, `relationship_identity_capped`, `relationship_identities_not_observed`, `state_store_unavailable`, `state_store_uncommitted` and `network_error`.\n\n**Question row** — `question_url`, `question_id`, `question_answer_count` (label) / `question_answer_count_value` (parsed number) / `question_answer_count_scraped` (rows actually collected), `question_follower_count` / `question_follower_count_value` (when the public payload exposes it), `related_questions` (`qid`, `title`, `url`), `question_created_at`, `question_updated_at`, `question_view_count`, `question_audit_state`, `question_merge_count`, `question_age_days`/`question_age_state`, `last_answered_at` + `last_answered_at_evidence`, `question_author_name`/`_url`/`_image_url`/`_id`/`_is_verified`/`_is_anonymous`/`_credentials` (from a visible author card or the opt-in `/log` audit), `question_image_urls`/`_video_urls`/`_outbound_links` (opt-in), `answer_count`, `answer_limit_reached`, `topics`, `topic_links`.\n\n**Answer row** — `answer_id`, `answer_node_id`, `answer_url`, `answer_text`, `answer_html` (opt-in, derived from rich text), `answer_media_urls`/`_image_urls`/`_video_urls`/`_outbound_links` (opt-in), `answer_translation_state`/`_label`, `answer_original_url`, `answer_is_anonymous`, `answer_author_is_verified`, `answer_author_follower_count` (when present), `answer_created_at`/`_updated_at`, `answer_age_days`/`_state`, `answer_visibility`, `answer_text_completeness`, `answer_is_collapsed`, `answer_is_quora_plus`, `answer_access_option`, `answer_effective_access`, `answer_is_top_labeled`, `answer_rank`/`_rank_source`, `answer_upvote_count`/`_value`, `answer_comment_count`/`_value`, `answer_view_count`/`_value`, `answer_share_count`/`_value`, `reaction_breakdown` (opt-in), `is_ai_answer`/`ai_label_text`/`ai_label_source`, `related_content`/`_count`/`_observed_count`/`_limit_reached` (opt-in), `answer_jsonld_type`, `author_name`/`_url`/`_image_url`/`_id`/`_credentials`.\n\n**Comment row** — `comment_id`, `comment_url`, `comment_text`, `comment_source` (`graphql_comment_area`), `comment_author_name`/`_image_url`/`_id`/`_credentials`/`_is_verified`, `comment_is_anonymous`, `comment_timestamp`/`_created_at`, `comment_age_days`/`_state`, `comment_visibility`, `comment_upvote_count`/`_value`, `comment_reaction_count`/`_value`, `comment_reply_count`/`_value`, `comment_reaction_breakdown`, `comment_media_urls`/`_image_urls`/`_video_urls`/`_outbound_links`, `comment_is_top_labeled`, `comment_rank`/`_rank_source`, `comment_sort_order`, `comment_depth`, `comment_depth_limit_reached`, `comment_is_reply`, `parent_comment_id`/`_url`, `comment_reply_path`, `comment_container_id`, `comment_items_observed_count`/`_emitted_count`, `comment_limit_reached`, `comment_page_limited`.\n\n**Profile row** — `profile_url`, `profile_name`, `profile_bio`, `profile_image_url`, `profile_author_id`, `profile_is_verified`, `profile_is_restricted`, `profile_account_status`, `profile_is_anonymous`, `profile_is_deceased`, `profile_snapshot_state`, plus `profile_follower_count`, `profile_following_count`, `profile_answer_count`, `profile_question_count`, `profile_post_count`, `profile_total_content_views`, `profile_month_content_views`, `profile_joined_at`, `profile_credential`, `profile_work_credentials`, `profile_school_credentials`, `profile_location_credentials`, `profile_expertise_topics`, `profile_history_limited` when the visible feed is truncated or the opt-in history is capped, and `profile_history_state` (`not_requested`/`observed`/`capped`/`rate_limited`/`unavailable`/`empty`) when history is requested.\n\n**Profile-activity row** — `activity_url`, `activity_type`, `activity_source`, `activity_question_url`/`_title`/`_id`, `activity_answer_id`, `created_at`, `author_name`/`_url`/`_image_url`/`_id`/`_credentials`.\n\n**Topic row** — `topic_url`, `topic_id`, `topic_follower_count`, `topic_most_viewed_authors` (`uid`, `name`, `url`, `follower_count`, `num_views`, `num_public_most_viewed_answers`, `credential`), `topic_photo_url`, `topic_default_photo_url`, `topic_has_leaderboard`, and `topic_feed_state` (`not_requested`/`observed`/`capped`/`unavailable`).\n\n**Topic-Post row** — `post_url`, `post_pid`, `post_node_id`, `post_title` (explicit title or first content line), `post_body`, `post_media_urls`/`_image_urls`/`_video_urls`/`_outbound_links` (opt-in), `post_author_name`/`_url`/`_image_url`/`_id`/`_credentials`/`_is_verified`/`_is_anonymous`/`_follower_count`, `post_question_url`/`_title`, `topic_url`, `post_created_at`/`_updated_at`, `post_age_days`/`_state`, `post_updated_age_days`/`_state`, `post_upvote_count`, `post_view_count`, `post_share_count`, `post_comment_count`, `post_effective_access`, `post_is_question_summary`.\n\n**Space row** — `space_url`, `space_id`, `space_follower_count`, `space_all_time_followers` (conditional), `space_member_count`, `space_contributor_count`, `space_moderator_count`, `space_admin_count`, `space_description`, `space_icon_url`, `space_cover_url`, `space_item_count`, `space_feed_capped`, `space_ads_skipped`.\n\n**Space feed-item row** — `feed_url`, `feed_type`, `feed_title`, `feed_text` (opt-in), `feed_post_pid`/`feed_post_node_id` (post stories), `feed_author_name`/`_url`/`_image_url`/`_id`/`_credentials`/`_is_verified`/`_is_anonymous`, `feed_created_at`, `feed_age_days`/`_state`, `feed_upvote_count`, `feed_view_count`, `feed_share_count`, `feed_comment_count`, `feed_effective_access`, `feed_is_ai_answer`, `feed_question_url`/`_title`, `media_urls`/`image_urls`/`video_urls`/`outbound_links` (opt-in).\n\n**Relationship row (`entity_edge`)** — `relationship`, `edge_id`, `from_record_id`/`_content_type`/`_url`/`_id`, `to_record_id`/`_content_type`/`_url`/`_id`/`_name`/`_image_url`, `node_image_url`, `edge_state`, `unresolved_reason`, `edge_evidence_field`, `relationship_collection_key`, `collection_total_text`/`_value`.\n\n**Relationship-count row (`relationship_collection`)** — `relationship_collection_key`, `collection_total_text`, `collection_total_value`, `edge_evidence_field`.\n\n**Status row** — `access_state`, `http_status`, `error`, `source_url`, and for pages that failed to load `final_url`, `scrape_duration_ms`, `navigation_attempts`, `navigation_retries`. Run-level status rows (`url: run://quora-dataset-builder`) report a state store that could not be read (`state_store_unavailable`), state that was not saved because a source did not finish (`state_store_uncommitted`), or a run that produced no real rows (`no_records_emitted`).\n\n**Option-dependent fields** — with a `stateStoreId`, entity rows add `event_type` (`new`/`changed`/`unchanged`/`scope_mismatch`), `state_snapshot_hash`, `previous_snapshot_hash`, `state_scope_fingerprint`, `state_store_state`, `only_new_items`, `include_unchanged`. With `includeRawEvidence`, page-level rows add `raw_html_sha256`, `raw_html_bytes`, `raw_html_truncated`, `raw_html_returned_bytes`, `raw_html_redaction_state`, `raw_html_redactions`, `raw_evidence_state`, `raw_evidence_retention_days`, plus `raw_html` when `includeHtml` is also on and `rawEvidenceRetentionDays` is above zero. In `nested` format, question rows carry `answers` arrays (each answer with its `comments`) and `nested_*` count fields. With `maxItemsPerSource` set, rows add `max_items_per_source` and per-source cap fields.\n\n**Run-manifest row** — one per run, summarizing counts and the settings actually applied: `run_started_at`/`_finished_at`/`_duration_ms`, `records_emitted`, `source_pages_attempted`, `content_type_counts`, `access_state_counts`, `input_accounting`, `requested_result_types`, `requested_output_fields`, `dedupe_mode`, `duplicate_records_suppressed`, `proxy_path_used`, `proxy_resolution_state`, `search_discovery_source`, `search_discovery_hits`, `answer_gql_pages`, `answer_pagination_state`, `answer_pagination_unrelated_suppressed`, `comment_gql_pages`, `topic_feed_pages`, `space_feed_bundles`, `quora_plus_preview_count`, `comment_cap_hit_count`, `topic_feed_cap_hit_count`, `profile_history_pages`, `profile_history_state`, `relationship_identity_pages`, `relationship_identity_requests`, `relationship_identity_states`, `question_audit_state`, `question_audit_attempts`, `legacy_input_notes`, `hard_limits`, `gql_calls`, `query_hashes`, and the per-run values of your own input settings echoed back for reconciliation.\n\n## Trimming rows, depth, sessions and caps\n\n- **Field allowlist.** `outputFields` keeps only the fields you name, applied after extraction; an empty list returns the full row. Nested projection is supported with dotted paths such as `answers.answer_text` or `answers.comments.comment_text` in `nested` output. Child identity/URL fields stay in place, and `content_type`, identity, access/status, depth, timing and parser fields are always protected so a trimmed row can still be traced. `output_projection` on each row reads `full` or `selected`, and the run manifest records the requested fields. `includeFieldEvidence` toggles the `field_sources`/`fields_present` maps.\n- **Depth.** `scrapeDepth: \"detail\"` (default) runs the capped traversal; `overview` emits page-level summaries without answer, comment, profile-activity or Space-feed expansion. Every row reports `requested_depth`, `observed_depth` and `detail_expansion_state`. `bounded` means a configured cap was reached, not that Quora's full history was collected, and blocked pages report `observed_depth: \"status\"`.\n- **Caps.** `maxAnswersPerQuestion` bounds each question, `maxAnswers` is a global answer cap, `maxAnswerPages` bounds GraphQL pages explicitly, `maxItems` caps entity/status rows before graph/manifest rows, `maxItemsPerSource` caps each source, and `maxGraphEdges` caps relationship rows. When `maxItems`/`maxGraphEdges` is 0 the corresponding cap is off. `maxRelationshipItemsPerCollection` bounds each labeled relationship collection, `maxRelationshipPages` bounds each public identity-list query, and `maxProfileHistoryPages` bounds each profile answer/question list. `answer_pagination_limited` is emitted only when a configured page cap or a GraphQL rate limit stopped pagination; an exhausted source is not reported as a cap.\n- **Comments.** Set `includeComments: true`. When `maxCommentsPerAnswer` is 0, the documented fallback is 10 per answer. The actor calls `AllCommentsListQuery` with `after` cursors and a page size derived from your cap (up to 50), so a 24-comment answer is collected as 10 + 10 + 4 when the server pages at ten. `includeCommentReplies` (or `includeReplyGraph`) expands nested replies up to `maxCommentDepth`; `comment_page_limited` is set only when a cap is actually hit, and a `comments_capped` status row follows. If the paginated query fails, the actor falls back to the first-page loader rather than inventing rows. Comments use Quora's comment-area GraphQL, which `robots.txt` disallows for generic agents: keep this opt-in and review your own compliance posture.\n- **Topic feed.** Set `includeTopicFeed: true` to call the topic page's own public GraphQL feed. `maxTopicFeedPages` bounds pages. This path is also robots-sensitive; keep it opt-in.\n- **Question audit.** `includeQuestionAudit: true` reads the question's public `/log` page for `question_created_at`, `question_view_count`, `question_merge_count`, and the asker name/uid/profile/credential. It retries a transient 403 once, then keeps `question_audit_state: \"unavailable\"` and a `question_audit_unavailable` status row. `/log` is robots-disallowed for generic agents and is never part of the daily prefill.\n- **Profile history.** `includeProfileHistory: true` paginates `UserProfileAnswersMostRecent_RecentAnswers_Query` and `UserProfileQuestionsList_Questions_Query` and emits bounded `profile_activity` rows. `maxProfileHistoryPages` (default 0 = three pages per list) and `requestDelay` (used as a 1.5–2.5 s GraphQL pace when above zero) bound the work. A cap sets `profile_history_limited`; a 400/403 sets `profile_history_state: \"rate_limited\"` and a `profile_history_unavailable` status row instead of fabricated rows.\n- **Identity lists.** Identity rows are emitted only when `relationshipTypes` explicitly requests them, the matching family flag is on, and `includeSensitiveRelationshipData` is on for sensitive types. The public GraphQL operations cover profile followers/following people/questions/Spaces/Topics, question followers, answer upvoters, and Space admins/contributors/moderators/followers. `maxRelationshipItemsPerCollection` and `maxRelationshipPages` bound every list; Space role calls run from a `www.quora.com` page context. These lists are robots-sensitive and rate-sensitive; a failure keeps a `relationship_identity_unavailable` or `relationship_identities_not_observed` status row, and a page/item cap adds `relationship_identity_capped`.\n- **Sessions and proxies.** No account, login, cookie, or session secret is used. The transport ladder is direct (`curl_cffi`, fresh session per attempt) → optional user proxy override → Apify AUTO datacenter → RESIDENTIAL only as a hardcoded last resort after the free rungs fail. A missing `proxyConfiguration` never stops the run, and there is no paid default. `proxy_path_used` reports the rung that worked.\n- **Exact field names.** Every output field this actor can emit is listed under [Output per record](#output-per-record) above. Fields whose source is absent on a given page are omitted, not set to null or a sentinel.\n\n## Complete schema input inventory\n\nEvery input is optional. The daily prefill uses one public question URL with a small answer cap, comments and feeds off, and no paid proxy.\n\n| Field | Type | Default | Description |\n|---|---|---|---|\n| `mode` | string | `auto` | `auto` / `byQuestionUrls` / `byAnswerUrls` / `byProfileUrls` / `byTopicUrls` / `bySpaceUrls` / `byPostUrls` / `search`; typed modes validate seed routes |\n| `scrapeDepth` | string | `detail` | `overview` (page-level summary only) or `detail` (full capped traversal) |\n| `startUrls` | array | `[]` | Question, answer, profile, Topic, Space, or Post URLs; mixed lists are auto-detected and invalid hosts become status rows |\n| `searchQueries` | array | `[]` | Best-effort discovery terms; Quora's native search is login/Cloudflare-gated and is never claimed |\n| `questionUrls` | array | `[]` | Typed question seeds |\n| `answerUrls` | array | `[]` | Typed answer-permalink seeds |\n| `topicUrls` | array | `[]` | Typed Topic seeds |\n| `spaceUrls` | array | `[]` | Typed Space seeds; automatically enables Space output |\n| `profileUrls` | array | `[]` | Typed profile seeds |\n| `postUrls` | array | `[]` | Typed standalone Post seeds |\n| `resultTypes` | array | `[\"question\",\"answer\",\"comment\",\"profile\",\"profile_activity\",\"topic\",\"topic_post\",\"space\",\"space_feed_item\",\"entity_edge\",\"status\",\"run_manifest\"]` | Which `content_type` values to include |\n| `outputFormat` | string | `normalized` | `normalized` / `nested` / `flat` / `edges` |\n| `dedupeMode` | string | `canonical` | `canonical` (merge duplicate entities by canonical URL/ID) or `none` |\n| `onlyNewItems` | boolean | `false` | With `stateStoreId`, suppress rows unchanged since the last run |\n| `includeUnchanged` | boolean | `true` | Keep unchanged rows when `onlyNewItems` is on |\n| `stateStoreId` | string | - | Apify key-value store name for incremental re-scraping; required when `onlyNewItems` is on |\n| `outputFields` | array | `[]` | Optional field allowlist for smaller rows; identity/status fields are always kept |\n| `includeFieldEvidence` | boolean | `true` | Include `field_sources`/`fields_present` on each row |\n| `includeUnresolvedEdges` | boolean | `true` | Keep relationship rows whose target could not be matched |\n| `relationshipTypes` | array | `[]` | Allowlist of labeled relationship collections to expand (follower, following, want-answers, upvoter, Space role); identity-revealing types also need `includeSensitiveRelationshipData` and the matching family opt-in |\n| `includeProfileEdges` | boolean | `false` | Per-family opt-in for profile follower/following/question/space/topic relationships |\n| `includeQuestionFollowerEdges` | boolean | `false` | Per-family opt-in for question follower/want-answer identities (sensitive) |\n| `includeAnswerUpvoterEdges` | boolean | `false` | Per-family opt-in for answer upvoter identities (requires `includeSensitiveRelationshipData`) |\n| `includeSensitiveRelationshipData` | boolean | `false` | Privacy gate required for identity-revealing relationship collections |\n| `includeTargetMetadata` | boolean | `false` | Keep the visible name/image of each relationship target |\n| `includeRelationshipCounts` | boolean | `false` | Emit privacy-preserving member-count rows; also add `relationship_collection` to `resultTypes` |\n| `includeSpaceRoleEdges` | boolean | `false` | Keep Space contributor/moderator/admin edges |\n| `includeSpaceContentEdges` | boolean | `true` | Keep Space to post/question membership edges and feed-item membership |\n| `maxRelationshipItemsPerCollection` | integer | `500` | Cap per labeled relationship collection |\n| `maxQuestions` | integer | `25` | How many discovered question links get queued on top of your own seed URLs |\n| `maxAnswersPerQuestion` | integer | `10` | Maximum answer rows kept per question after SSR and GraphQL pagination |\n| `maxAnswers` | integer | `0` | Global answer cap across the whole run (`0` = no cap) |\n| `includeQuestion` | boolean | `true` | Keep question entities in the output |\n| `includeAuthor` | boolean | `true` | Keep author/profile entities and author fields in the output |\n| `includeAuthorSnapshot` | boolean | `false` | Fetch a bounded profile snapshot for each visible answer author |\n| `includeTopics` | boolean | `true` | Keep topic entities and topic links |\n| `includeSpaces` | boolean | `false` | Keep Space and Space feed-item rows; switched on automatically when a Space URL is used in `startUrls` or `spaceUrls` |\n| `includeComments` | boolean | `false` | Opt-in comment rows with `AllCommentsListQuery` cursor pagination; robots-sensitive |\n| `includeEngagementBreakdown` | boolean | `true` | Include per-reaction breakdowns alongside aggregate counts |\n| `includeRelatedContent` | boolean | `false` | Collect explicitly attached answer related-content links when Quora's public payload exposes them; otherwise they are omitted |\n| `maxRelatedContent` | integer | `20` | Bound related-content links per answer when enabled; zero emits no related-content items |\n| `topCommentsOnly` | boolean | `false` | Keep only comments explicitly labeled Top/Most helpful |\n| `commentSortOrder` | string | `observed` | `observed` / `upvotes_desc` / `reactions_desc` / `replies_desc` / `newest` |\n| `includeReplyGraph` | boolean | `false` | Compatibility alias that enables comments and nested replies |\n| `includeMedia` | boolean | `false` | Include image/video URL fields where available |\n| `includeFeedText` | boolean | `false` | Include visible text on Space feed cards |\n| `includeOutboundLinks` | boolean | `false` | Include non-Quora links found in rich text |\n| `includeEntityGraph` | boolean | `false` | Emit relationship rows even when `entity_edge` is not in `resultTypes` |\n| `maxCommentsPerAnswer` | integer | `0` | Comments kept per answer; when comments are on and this is 0, the fallback is 10; the cap is the pagination limit, not a page size |\n| `maxCommentDepth` | integer | `20` | Maximum nested reply depth when replies are enabled; 0 disables replies |\n| `maxItems` | integer | `0` | Cap on entity/status rows before graph and manifest rows (`0` = no cap) |\n| `maxGraphEdges` | integer | `5000` | Cap on relationship rows (`0` = no edges) |\n| `maxScrollAttempts` | integer | `5` | Scroll attempts per page in detail mode |\n| `maxLoadMoreAttempts` | integer | `0` | \"Load more\" button clicks per page |\n| `includeRawEvidence` | boolean | `false` | Attach a document hash and size/redaction metadata for auditing |\n| `includeHtml` | boolean | `false` | Retain bounded raw HTML on page-level rows and derived answer HTML |\n| `maxHtmlBytes` | integer | `100000` | Upper bound for retained or derived HTML |\n| `requestDelay` | number | `1` | Delay in seconds between page batches |\n| `maxConcurrency` | integer | `1` | Independent seeds processed in parallel (values above 3 are treated as 3) |\n| `maxNavigationRetries` | integer | `2` | Retries after a failed page load (max 3) |\n| `language` | string | `auto` | Browser language hint (`en`, `es`, `fr`, ...); not a translation guarantee |\n| `proxyConfiguration` | object | - | Optional proxy override. The free ladder runs first; there is no paid default |\n| `redactSensitiveQueryParams` | boolean | `true` | Redact credential-like query values and fragment credentials from emitted URLs/HTML |\n| `rawEvidenceRetentionDays` | integer | `30` | Retention label for raw HTML evidence; 0 keeps metadata only |\n| `maxRawEvidenceBytes` | integer | `100000` | Size bound for raw HTML evidence |\n| `maxItemsPerSource` | integer | `0` | Cap on records from each individual source URL/query (`0` = no cap) |\n| `searchDiscovery` | string | `relatedOnly` | `relatedOnly` (related questions only) / `bestEffortIndex` (third-party index) / `off` |\n| `maxRelatedQuestions` | integer | `20` | Related questions enqueued per question seed |\n| `searchResultsPerQuery` | integer | `10` | Maximum best-effort index results per query |\n| `maxAnswerPages` | integer | `0` | Explicit answer GraphQL page cap; 0 derives from `maxAnswersPerQuestion` |\n| `maxTopicFeedPages` | integer | `3` | Topic-feed GraphQL page cap when `includeTopicFeed` is on (minimum one page) |\n| `maxSpaceFeedBundles` | integer | `4` | Space feed bundles read from the SSR multifeed |\n| `includeCommentReplies` | boolean | `false` | Expand nested `repliesConnection` comment replies |\n| `includeQuoraPlusPreview` | boolean | `true` | Emit Quora+ preview answers with preview flags; when false, omit them |\n| `includeProfileStats` | boolean | `true` | Emit profile follower/following/answer/question/post/view/joined/credential fields |\n| `includeTopicStats` | boolean | `true` | Emit Topic follower count and most-viewed authors |\n| `includeSpaceStats` | boolean | `true` | Emit Space counters, description, icon and cover |\n| `includePostStats` | boolean | `true` | Emit Post counters, effective access and question-summary flag |\n| `includeAnswerStats` | boolean | `true` | Emit answer counters, dates, AI flag and effective access |\n| `includeTopicFeed` | boolean | `false` | Browser GraphQL Topic feed; opt-in and robots-sensitive |\n| `includeQuestionAudit` | boolean | `false` | Read the public question `/log` for created time, view count, merge count, and asker identity; robots-sensitive opt-in |\n| `includeProfileHistory` | boolean | `false` | Paginate the public profile answer/question tabs into bounded `profile_activity` rows; robots- and rate-sensitive opt-in |\n| `maxProfileHistoryPages` | integer | `0` | Cap per profile history list; 0 derives three pages (about 30 items per list) |\n| `maxRelationshipPages` | integer | `3` | Cap per public identity-list query after the relationship allowlist and privacy gates |\n\n## Example inputs\n\n### Example: full detail for a question\n\n```json\n{\n \"questionUrls\": [{ \"url\": \"https://www.quora.com/What-is-the-best-way-to-learn-Python\" }],\n \"maxAnswersPerQuestion\": 20,\n \"includeComments\": true,\n \"maxCommentsPerAnswer\": 10\n}\n```\n\n### Example: best-effort search discovery, compact nested output\n\n```json\n{\n \"searchQueries\": [\"machine learning career advice\"],\n \"searchDiscovery\": \"relatedOnly\",\n \"maxQuestions\": 10,\n \"outputFormat\": \"nested\",\n \"maxAnswersPerQuestion\": 5\n}\n```\n\n### Example: a Space's content and follower count\n\n```json\n{\n \"spaceUrls\": [{ \"url\": \"https://www.quora.com/q/example-space\" }],\n \"resultTypes\": [\"space\", \"space_feed_item\", \"relationship_collection\", \"run_manifest\"],\n \"includeRelationshipCounts\": true,\n \"relationshipTypes\": [\"space_has_contributor\"]\n}\n```\n\n### Example: incremental re-scrape of the same question\n\n```json\n{\n \"questionUrls\": [{ \"url\": \"https://www.quora.com/What-is-the-best-way-to-learn-Python\" }],\n \"onlyNewItems\": true,\n \"includeUnchanged\": false,\n \"stateStoreId\": \"python-question-watch\"\n}\n```\n\n## Use cases\n\n- **Content research** — pull full question-answer-comment threads on a topic for analysis\n- **Community monitoring** — re-scrape the same questions on a schedule and keep only rows flagged `new`/`changed`\n- **Knowledge graph building** — use `outputFormat: \"edges\"` to load the question/answer/topic relationship graph into a graph database\n- **Influencer and expert tracking** — follow a profile's visible answers and its public follower/following/content statistics\n- **Space analysis** — collect a Quora Space's feed, metrics and contributor counts\n\n## FAQ\n\n**Do I need a Quora account?**\nNo. Direct public question, answer, profile, Topic, Space, and Post pages are read without login. The actor never asks for, stores, or emits cookies or session secrets.\n\n**Why did I get a `status` row instead of question/answer data?**\nQuora showed a login wall, Cloudflare challenge, a removed page, or an unsupported redirect for that URL. The actor reports this honestly as a `status` row instead of guessing at data that was not there. A run with zero real rows also gets a `no_records_emitted` status row and a non-success status message.\n\n**Why do I sometimes get fewer answers than `maxAnswersPerQuestion`?**\nThe actor reads the server-rendered answers, filters out answers whose question is provably unrelated, then paginates the public GraphQL cursor up to your cap. If the question genuinely has fewer answers, the cursor stops; you get the answers that were observable and no `answer_pagination_limited` row, because the source was exhausted rather than capped. `answer_pagination_limited` appears only when `maxAnswerPages`/your cap stopped a non-exhausted source or Quora rate-limited a pagination request, and the page's known `answerCount` is not already satisfied; a non-rate GraphQL failure uses `answer_pagination_unavailable`. Neither case fabricates an answer.\n\n**How do I get question created time, view count, or the asker?**\nSet `includeQuestionAudit: true`. The actor reads the public `//log` page (robots-sensitive, opt-in) and fills `question_created_at`, `question_view_count`, `question_merge_count`, and the `question_author_*` fields. Without it, those fields are omitted rather than guessed. A blocked `/log` leaves `question_audit_state: \"unavailable\"` and a status row.\n\n**How do I get more than the three visible profile history items?**\nSet `includeProfileHistory: true`. The actor paginates the public answer/question tab connections into `profile_activity` rows, bounded by `maxProfileHistoryPages` and paced by `requestDelay`. This GraphQL path is robots- and rate-sensitive; a 400/403 leaves a `profile_history_unavailable` status row and no fabricated rows.\n\n**What is the difference between the four `outputFormat` values?**\n`normalized` keeps every entity as its own row (the default). `nested` groups each question's answers (and each answer's comments) underneath it; rows without a matching parent stay at the top level with an orphan reason. `flat` is like `normalized`, except answer rows also get question context and comment rows get `answer_url`. `edges` returns the relationship rows between entities plus any status rows.\n\n**Can I get a Quora account's followers, question followers, answer upvoters, or Space roles?**\nYes, as explicit opt-ins. Request the relationship type in `relationshipTypes`, turn on the matching family flag (`includeProfileEdges`, `includeQuestionFollowerEdges`, `includeAnswerUpvoterEdges`, or `includeSpaceRoleEdges`), and set `includeSensitiveRelationshipData: true` for follower/upvoter/want-answer types. The actor then calls the public identity-list GraphQL operations, paginates up to `maxRelationshipPages`, and emits only identities whose profile/question/Space/Topic URLs it observed. It may also use visible DOM links as a fallback. These paths are robots- and rate-sensitive; failures produce `relationship_identity_unavailable` or `relationship_identities_not_observed` status rows. It never invents identities.\n\n**What does the incremental re-scrape (`onlyNewItems`) actually compare?**\nIt hashes each entity's semantic content and compares it to the previous run stored under `stateStoreId`, tagging each row `new`, `changed`, `unchanged`, or `scope_mismatch` (the previous run used different settings). Rows are only dropped when `onlyNewItems` is on and `includeUnchanged` is off. Status and manifest rows are never dropped by this setting. If any requested source did not finish, the new state is not saved and a `state_store_uncommitted` status row tells you so.\n\n**Why are some text/media fields missing even with `includeMedia`/`includeHtml` on?**\nThose fields are only populated when Quora's public payload actually contains that content for the entity in question. The toggles request the data; they do not guarantee every entity has it.\n\n**Is search native Quora search?**\nNo. Quora's native `/search?q=` is login/Cloudflare-gated for logged-out clients and is disallowed by `robots.txt`. `searchQueries` uses related-question discovery by default and an optional third-party best-effort index; if no public results are discoverable it emits a `search_unavailable` status row.\n\n**What are the hard limitations?**\nNative Quora search is not available cookielessly: `/search?q=` redirects and the public search GraphQL returns no connection. Quora+ `smart_distribution` answers may be preview/truncated; they are flagged `answer_is_quora_plus` and their observed completeness is reported, and no gated remainder is fabricated. Space all-time views/upvotes/comments are private (tested across ten diverse Spaces), Topic description and question count are absent, and question description is absent. Space `allTimeFollowers` is emitted as `space_all_time_followers` only when the payload carries it (not every Space does).\n\nQuestion created/view/asker, full profile history, comment/reply pagination, and identity lists are technically available through public pages/GraphQL but are **robots-sensitive and/or rate-sensitive opt-ins**; they are off by default and not part of the daily prefill. Be aware that `robots.txt` for generic agents disallows `/` broadly, including `/*_POST`, `/*/log`, `/*/followers`, `/*/following`, and `/*/comments`; product/legal review decides whether to enable those opt-ins. Quora URLs are valid in a browser, but plain HTTP clients can receive a Cloudflare 403 on HEAD/GET; the actor fetches them with TLS impersonation.\n\n**Is this affiliated with Quora?**\nNo. This is an independent, third-party actor that reads public Quora pages; it is not affiliated with or endorsed by Quora, Inc. You are responsible for how you use the data.\n", "actorDefinition": { "actorSpecification": 1, "name": "quora-question-answer-and-relationship-dataset", "title": "Quora Question, Answer & Relationship Dataset Builder", "description": "Build a structured Quora dataset from question, answer, profile, Topic, Space, and Post URLs or search terms, with the question-answer-comment chain and relationship links kept intact.", "version": "1.0", "buildTag": "latest", "meta": { "templateId": "python-playwright" }, "input": { "title": "Quora Dataset Builder Input", "type": "object", "schemaVersion": 1, "properties": { "mode": { "title": "Mode", "type": "string", "editor": "select", "enum": [ "auto", "byQuestionUrls", "byAnswerUrls", "byProfileUrls", "byTopicUrls", "bySpaceUrls", "byPostUrls", "search" ], "enumTitles": [ "Auto-detect any supported URL", "Questions and answers", "Specific answer permalinks", "Profiles and stats", "Topics and optional feed", "Spaces and feeds", "Standalone posts", "Best-effort search discovery" ], "default": "auto", "prefill": "auto", "description": "Optional dispatcher. auto detects every supported Quora route; typed modes validate startUrls against that route. Typed seed lists still work without mode." }, "scrapeDepth": { "title": "Scrape Depth", "type": "string", "enum": [ "overview", "detail" ], "enumTitles": [ "Overview (page metadata only)", "Detail (answers, comments, feeds)" ], "default": "detail", "prefill": "detail", "description": "Overview emits page metadata without answer/comment/feed expansion; detail enables SSR answers plus bounded GraphQL pagination and optional comments/topic feeds." }, "startUrls": { "title": "Quora URLs", "type": "array", "editor": "requestListSources", "description": "Question, answer, profile, topic, Space, or search URLs. Mixed lists are auto-detected; invalid hosts become status rows instead of failing the run.", "default": [], "prefill": [ { "url": "https://www.quora.com/What-is-the-meaning-of-life" } ] }, "searchQueries": { "title": "Search Queries", "type": "array", "editor": "stringList", "items": { "type": "string" }, "default": [], "description": "Best-effort public-index discovery only. Quora native search is login/Cloudflare-gated and robots-disallowed; related-question expansion on a question URL is the reliable discovery axis." }, "questionUrls": { "title": "Question URLs", "type": "array", "editor": "requestListSources", "items": { "type": "object", "properties": { "url": { "title": "URL", "description": "A Quora URL.", "type": "string" } }, "required": [ "url" ] }, "default": [], "description": "Explicit question-page seeds. Only question routes are accepted." }, "answerUrls": { "title": "Answer URLs", "type": "array", "editor": "requestListSources", "items": { "type": "object", "properties": { "url": { "title": "URL", "description": "A Quora URL.", "type": "string" } }, "required": [ "url" ] }, "default": [], "description": "Explicit answer-page seeds. Parent question joins are emitted only from observed evidence." }, "topicUrls": { "title": "Topic URLs", "type": "array", "editor": "requestListSources", "items": { "type": "object", "properties": { "url": { "title": "URL", "description": "A Quora URL.", "type": "string" } }, "required": [ "url" ] }, "default": [], "description": "Explicit Topic-page seeds for bounded visible question discovery." }, "spaceUrls": { "title": "Space URLs", "type": "array", "editor": "requestListSources", "items": { "type": "object", "properties": { "url": { "title": "URL", "description": "A Quora URL.", "type": "string" } }, "required": [ "url" ] }, "default": [], "description": "Explicit Space-page seeds for bounded visible feed discovery." }, "profileUrls": { "title": "Profile URLs", "type": "array", "editor": "requestListSources", "items": { "type": "object", "properties": { "url": { "title": "URL", "description": "A Quora URL.", "type": "string" } }, "required": [ "url" ] }, "default": [], "description": "Explicit profile-page seeds. Only profile routes are accepted; emitted as normalized profile rows exactly like a profile route discovered from startUrls." }, "postUrls": { "title": "Post URLs", "type": "array", "editor": "requestListSources", "items": { "type": "object", "properties": { "url": { "title": "URL", "description": "A Quora URL.", "type": "string" } }, "required": [ "url" ] }, "default": [], "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_*)." }, "resultTypes": { "title": "Result Types", "type": "array", "description": "Select normalized entities, explicit graph relationships, relationship-collection counts, status rows, and the final run manifest.", "editor": "select", "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", "type": "string", "enum": [ "normalized", "nested", "flat", "edges" ], "enumTitles": [ "Normalized (one row per entity)", "Nested (answers under questions)", "Flat (entity rows with parent context)", "Edges (relationship rows)" ], "default": "normalized", "prefill": "normalized", "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." }, "dedupeMode": { "title": "Deduplication Mode", "type": "string", "enum": [ "canonical", "none" ], "enumTitles": [ "Canonical (deduplicate by ID/URL)", "None (keep every observed row)" ], "default": "canonical", "prefill": "canonical", "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." }, "onlyNewItems": { "title": "Only New or Changed Items", "type": "boolean", "default": false, "prefill": false, "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." }, "includeUnchanged": { "title": "Include Unchanged Items", "type": "boolean", "default": true, "prefill": true, "description": "Retain unchanged semantic entities when incremental state is enabled; output projection does not alter comparison hashes." }, "stateStoreId": { "title": "Incremental State Store ID", "type": "string", "editor": "textfield", "default": "", "description": "Apify key-value store for canonical entity snapshots. Required when onlyNewItems is enabled; never store cookies or credentials here." }, "outputFields": { "title": "Output Fields", "type": "array", "editor": "stringList", "items": { "type": "string" }, "default": [], "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.", "maxItems": 3000 }, "includeFieldEvidence": { "title": "Include Field Evidence", "type": "boolean", "default": true, "prefill": true, "description": "Include field_sources and fields_present maps. Disable only when a smaller payload is required; semantic values and protected access fields remain unchanged." }, "includeUnresolvedEdges": { "title": "Include Unresolved Edges", "type": "boolean", "default": true, "prefill": true, "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." }, "relationshipTypes": { "title": "Relationship Types", "type": "array", "editor": "select", "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": [], "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." }, "includeProfileEdges": { "title": "Include Profile Relationship Collections", "type": "boolean", "default": false, "prefill": false, "description": "Enable explicitly labeled profile follower/following/followed-question/Space/Topic relationship collections. This does not prove a complete list." }, "includeQuestionFollowerEdges": { "title": "Include Question Follower Collections", "type": "boolean", "default": false, "prefill": false, "description": "Enable explicitly labeled question follower or want-answer collections. Sensitive identity rows also require the privacy gate." }, "includeAnswerUpvoterEdges": { "title": "Include Answer Upvoter Collections", "type": "boolean", "default": false, "prefill": false, "description": "High-sensitivity opt-in for explicitly labeled answer upvoter identities; requires includeSensitiveRelationshipData=true." }, "includeSensitiveRelationshipData": { "title": "Sensitive Relationship Data", "type": "boolean", "default": false, "prefill": false, "description": "Explicit privacy gate required for follower, want-answer, and upvoter identity edges." }, "includeTargetMetadata": { "title": "Include Explicit Target Metadata", "type": "boolean", "default": false, "prefill": false, "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." }, "includeRelationshipCounts": { "title": "Include Relationship Collection Counts", "type": "boolean", "default": false, "prefill": false, "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." }, "includeSpaceRoleEdges": { "title": "Include Space Role Edges", "type": "boolean", "default": false, "prefill": false, "description": "Enable explicitly labeled Space contributor, moderator, and admin collections." }, "includeSpaceContentEdges": { "title": "Include Space Content Edges", "type": "boolean", "default": true, "prefill": true, "description": "Retain bounded explicit Space post/question membership edges; this never claims a complete Space inventory." }, "maxRelationshipItemsPerCollection": { "title": "Maximum Relationship Items per Collection", "type": "integer", "default": 500, "minimum": 0, "maximum": 5000, "description": "Bound explicit links emitted from each labeled relationship collection. Zero emits no relationship-collection edges and never means an empty collection." }, "maxQuestions": { "title": "Maximum Questions", "type": "integer", "description": "Maximum question seeds or discovered question pages to process.", "default": 25, "minimum": 0, "maximum": 1000, "prefill": 10 }, "maxAnswersPerQuestion": { "title": "Maximum Answers per Question", "type": "integer", "description": "Maximum answer rows retained per question after SSR and GraphQL pagination.", "default": 10, "minimum": 0, "maximum": 500, "prefill": 5 }, "maxAnswers": { "title": "Maximum Answers Total", "type": "integer", "default": 0, "minimum": 0, "maximum": 50000, "description": "Global answer-row cap applied after per-question caps. Zero means no configured global answer cap." }, "includeQuestion": { "title": "Include Question Rows", "type": "boolean", "default": true, "prefill": true, "description": "Retain normalized question parent rows when selected in resultTypes." }, "includeAuthor": { "title": "Include Author Rows", "type": "boolean", "default": true, "prefill": true, "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." }, "includeAuthorSnapshot": { "title": "Include Author Snapshot", "type": "boolean", "default": false, "prefill": false, "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." }, "includeTopics": { "title": "Include Topic Links", "type": "boolean", "default": true, "prefill": true, "description": "Retain explicit topic links and topic relationships where observed." }, "includeSpaces": { "title": "Include Space Rows", "type": "boolean", "default": false, "prefill": false, "description": "Retain Space rows and SSR feed items. Explicit spaceUrls enable this automatically." }, "includeComments": { "title": "Include Comment Rows", "type": "boolean", "default": false, "prefill": false, "description": "Opt-in comment rows from Quora's public comment-area GraphQL. robots-sensitive; off by default. When enabled and maxCommentsPerAnswer is 0, the documented fallback is 10 per answer." }, "includeEngagementBreakdown": { "title": "Include Engagement Breakdown", "type": "boolean", "default": true, "prefill": true, "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." }, "includeRelatedContent": { "title": "Include Answer Related Content", "type": "boolean", "default": false, "prefill": false, "description": "Retain links inside an explicitly labeled related/attached region scoped to answer cards; unlabeled navigation and neighboring regions are excluded." }, "maxRelatedContent": { "title": "Maximum Answer Related Content", "type": "integer", "minimum": 0, "maximum": 100, "default": 20, "description": "Bound eligible related-content links per answer when enabled; zero emits no related-content items." }, "topCommentsOnly": { "title": "Top-Labeled Comments Only", "type": "boolean", "default": false, "prefill": false, "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." }, "commentSortOrder": { "title": "Comment Sort Order", "type": "string", "enum": [ "observed", "upvotes_desc", "reactions_desc", "replies_desc", "newest" ], "enumTitles": [ "Observed order", "Most upvotes", "Most reactions", "Most replies", "Newest first" ], "default": "observed", "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." }, "includeReplyGraph": { "title": "Include Reply Graph", "type": "boolean", "default": false, "prefill": false, "description": "Enable comment rows plus one-level nested reply extraction from repliesConnection. Requires includeComments." }, "includeMedia": { "title": "Include Media URLs", "type": "boolean", "default": false, "prefill": false, "description": "Request explicitly rendered media URL fields scoped to question roots, answer/comment nodes, and Topic post cards where the page exposes them." }, "includeFeedText": { "title": "Include Space Feed Text", "type": "boolean", "default": false, "prefill": false, "description": "Request bounded visible text from explicitly linked Space feed cards; page-level text and complete feed history are excluded." }, "includeOutboundLinks": { "title": "Include Outbound Links", "type": "boolean", "default": false, "prefill": false, "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." }, "includeEntityGraph": { "title": "Include Entity Graph", "type": "boolean", "default": false, "prefill": false, "description": "Emit explicit relationship rows even when entity_edge is not listed in resultTypes." }, "maxCommentsPerAnswer": { "title": "Maximum Comments per Answer", "type": "integer", "description": "Maximum comment rows retained per answer when comments are enabled. Schema default 0 is kept for compatibility; comments-enabled runs treat 0 as 10.", "default": 0, "minimum": 0, "maximum": 500, "prefill": 0 }, "maxCommentDepth": { "title": "Maximum Comment Depth", "type": "integer", "description": "Maximum nested reply depth when includeCommentReplies/includeReplyGraph is enabled.", "default": 20, "minimum": 0, "maximum": 100, "prefill": 20 }, "maxItems": { "title": "Maximum Entity Rows", "type": "integer", "default": 0, "minimum": 0, "maximum": 5000, "description": "Cap for normalized entity/status rows before graph and manifest rows." }, "maxGraphEdges": { "title": "Maximum Graph Edges", "type": "integer", "description": "Independent cap for deterministic entity_edge rows.", "default": 5000, "minimum": 0, "maximum": 50000, "prefill": 1000 }, "maxScrollAttempts": { "title": "Maximum Scroll Attempts", "type": "integer", "description": "Bounded lazy-render scroll budget applied during detail traversal; scroll attempts and termination state are reported.", "default": 5, "minimum": 0, "maximum": 20 }, "maxLoadMoreAttempts": { "title": "Maximum Load-more Attempts", "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, "minimum": 0, "maximum": 20 }, "includeRawEvidence": { "title": "Include Raw Evidence", "type": "boolean", "default": false, "prefill": false, "description": "Add bounded document hash and optional HTML bytes to each page-level entity row." }, "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, "prefill": false }, "maxHtmlBytes": { "title": "Maximum HTML Bytes", "type": "integer", "description": "Maximum UTF-8 bytes retained for optional raw HTML evidence.", "default": 100000, "minimum": 1000, "maximum": 2000000 }, "requestDelay": { "title": "Request Delay", "type": "number", "description": "Delay between page batches in seconds; this is not an anti-bot bypass guarantee.", "default": 1, "minimum": 0, "maximum": 30 }, "maxConcurrency": { "title": "Maximum Concurrent Seeds", "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, "minimum": 1, "maximum": 3 }, "maxNavigationRetries": { "title": "Maximum Navigation Retries", "type": "integer", "default": 2, "minimum": 0, "maximum": 3, "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." }, "language": { "title": "Language", "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.", "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" ], "enumTitles": [ "Automatic", "English", "Spanish", "French", "German", "Portuguese", "Italian", "Japanese", "Korean", "Hindi", "Indonesian", "Dutch", "Polish", "Turkish", "Vietnamese", "Chinese", "Russian", "English (US)", "English (UK)", "German (Germany)", "French (France)", "Spanish (Spain)", "Portuguese (Brazil)", "Italian (Italy)", "Japanese (Japan)", "Korean (Korea)", "Hindi (India)", "Turkish (Turkey)", "Chinese (Simplified)", "Chinese (Traditional)", "Russian (Russia)" ], "default": "auto" }, "proxyConfiguration": { "title": "Proxy Configuration (optional)", "type": "object", "description": "Optional proxy override. The actor starts with a direct connection, retries a fresh session on 403/429, then uses Apify AUTO datacenter proxies, and only falls back to RESIDENTIAL as a proven last resort. Leave this unset; a missing proxyConfiguration never stops the run.", "editor": "proxy" }, "redactSensitiveQueryParams": { "title": "Redact Sensitive URL Query Values", "type": "boolean", "default": true, "prefill": true, "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." }, "rawEvidenceRetentionDays": { "title": "Raw Evidence Retention Days", "type": "integer", "default": 30, "minimum": 0, "maximum": 30, "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." }, "maxRawEvidenceBytes": { "title": "Maximum Raw Evidence Bytes", "type": "integer", "default": 100000, "minimum": 1000, "maximum": 2000000, "description": "Hard upper byte cap for returned raw HTML after the maxHtmlBytes cap." }, "maxItemsPerSource": { "title": "Maximum Items Per Source", "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, "minimum": 0, "maximum": 5000, "prefill": 0 }, "searchDiscovery": { "title": "Search Discovery", "type": "string", "editor": "select", "enum": [ "relatedOnly", "bestEffortIndex", "off" ], "enumTitles": [ "Related questions only (no third-party engine)", "Best-effort DuckDuckGo index", "Disabled" ], "default": "relatedOnly", "prefill": "relatedOnly", "description": "How searchQueries are handled. relatedOnly attempts Quora's public search and otherwise emits search_unavailable; bestEffortIndex queries a public web index for indexed Quora URLs. Native Quora search is never claimed." }, "maxRelatedQuestions": { "title": "Maximum Related Questions", "type": "integer", "minimum": 0, "maximum": 100, "default": 20, "prefill": 0, "description": "Related questions to enqueue per question/topic seed. The page usually exposes 26-35; zero disables related-question discovery." }, "searchResultsPerQuery": { "title": "Search Results per Query", "type": "integer", "minimum": 0, "maximum": 50, "default": 10, "prefill": 0, "description": "Maximum indexed URLs to use per search query when searchDiscovery=bestEffortIndex." }, "maxAnswerPages": { "title": "Maximum Answer GraphQL Pages", "type": "integer", "minimum": 0, "maximum": 50, "default": 0, "prefill": 0, "description": "Bound QuestionPagedListPaginationQuery pages. Zero derives a bound from maxAnswersPerQuestion." }, "maxTopicFeedPages": { "title": "Maximum Topic Feed Pages", "type": "integer", "minimum": 0, "maximum": 20, "default": 3, "prefill": 0, "description": "Bound topic-feed GraphQL pages when includeTopicFeed is enabled." }, "maxSpaceFeedBundles": { "title": "Maximum Space Feed Bundles", "type": "integer", "minimum": 0, "maximum": 20, "default": 4, "prefill": 1, "description": "Bound Space feed bundles read from the SSR multifeed." }, "includeCommentReplies": { "title": "Include Comment Replies", "type": "boolean", "default": false, "prefill": false, "description": "Include nested repliesConnection rows. Requires includeComments. Comments are robots-sensitive and opt-in; zero-row/blocked results produce a status row." }, "includeQuoraPlusPreview": { "title": "Include Quora+ Preview Answers", "type": "boolean", "default": true, "prefill": true, "description": "Emit preview-only answers flagged answer_is_quora_plus/answer_text_completeness=preview. The gated remainder is never fetched or presented as full text." }, "includeProfileStats": { "title": "Include Profile Stats", "type": "boolean", "default": true, "prefill": true, "description": "Emit follower/following/answer/question/post/view counts, joined date, credentials and expertise topics for profile rows." }, "includeTopicStats": { "title": "Include Topic Stats", "type": "boolean", "default": true, "prefill": true, "description": "Emit topic follower count and most-viewed authors for topic rows." }, "includeSpaceStats": { "title": "Include Space Stats", "type": "boolean", "default": true, "prefill": true, "description": "Emit Space follower/member/contributor/moderator/admin counts, description, icon and cover." }, "includePostStats": { "title": "Include Post Stats", "type": "boolean", "default": true, "prefill": true, "description": "Emit post upvotes/views/shares/comments, effective access and question-summary flag." }, "includeAnswerStats": { "title": "Include Answer Stats", "type": "boolean", "default": true, "prefill": true, "description": "Emit answer counters, dates, AI flag, effective access and Quora+ preview flags." }, "includeTopicFeed": { "title": "Include Topic Feed", "type": "boolean", "default": false, "prefill": false, "description": "Opt into the browser topic-feed GraphQL endpoint. robots-sensitive: keep off unless you accept that compliance caveat." }, "includeQuestionAudit": { "title": "Include Question Audit", "type": "boolean", "default": false, "prefill": false, "description": "Opt into the public question /log page to fill question_created_at, question_view_count and the asker fields. robots.txt disallows /*/log for generic agents; the actor never includes this in the default prefill." }, "includeProfileHistory": { "title": "Include Profile History", "type": "boolean", "default": false, "prefill": false, "description": "Opt into the public profile answer/question tab GraphQL and emit bounded profile_activity rows. robots-sensitive and rate-sensitive; on a 400/403 the run keeps a profile_history_unavailable status row." }, "maxProfileHistoryPages": { "title": "Maximum Profile History Pages", "type": "integer", "minimum": 0, "maximum": 20, "default": 0, "prefill": 0, "description": "Bound for each profile history list (answers and questions) when includeProfileHistory is enabled. Zero derives three pages; one page is roughly ten items." }, "maxRelationshipPages": { "title": "Maximum Identity List Pages", "type": "integer", "minimum": 0, "maximum": 20, "default": 3, "prefill": 0, "description": "Bound for each public identity-list query (question followers, answer upvoters, profile followers/following, Space roles) after the relationship allowlist and privacy gates. Zero is treated as one page." } } }, "output": { "actorOutputSchemaVersion": 1, "title": "Quora Question, Answer & Relationship Dataset Builder Output", "description": "Normalized Quora questions, answers, comments, profiles, Spaces, relationship edges, status rows, and a run manifest.", "type": "object", "properties": { "results": { "type": "string", "title": "Results", "description": "All records from the run, in the default dataset.", "template": "{{links.apiDefaultDatasetUrl}}/items" } } }, "readme": "# Quora Question, Answer & Relationship Dataset Builder\n\nBuild a structured Quora dataset from direct links or best-effort search discovery. Point it at question, answer, profile, Topic, Space, or Post URLs and it returns normalized rows for every entity it finds, with the question → answer → comment chain and author/topic links kept intact. Choose how deep to go, how the rows are shaped, and which relationship or feed data to include.\n\nThis is an independent, third-party actor. It is not affiliated with, endorsed by, or licensed by Quora, Inc. No Quora account, login, session cookie, or paid proxy is used or required.\n\n## What this actor does\n\n- Accepts question, answer, profile, Topic, Space, and Post URLs directly, plus best-effort search discovery. Typed seed lists (`questionUrls`, `answerUrls`, `topicUrls`, `spaceUrls`, `profileUrls`, `postUrls`) override route auto-detection.\n- Empty fields are omitted; a missing field means the source did not expose it, never `null` or a sentinel.\n- Parses Quora's server-rendered Relay payloads and double-decodes the `window.ansFrontendGlobals.data.inlineQueryResults` `.push()` strings; it does not depend on CSS classes or DOM selectors for the core fields.\n- Paginates question answers with Quora's public `QuestionPagedListPaginationQuery` cursor, up to `maxAnswersPerQuestion` / `maxAnswers` / `maxAnswerPages`. Every paginated answer is checked against the page question (title/path, `linkedQuestion`, `originalQuestionIfDifferent`, and the answer permalink), so unrelated promoted answers cannot become dataset rows while legitimate merged variants still pass.\n- Paginates comment areas and nested replies through `AllCommentsListQuery` (10+ pages with `after` cursors), with `maxCommentsPerAnswer` as the hard cap; this is opt-in and robots-sensitive.\n- Optionally reads a Topic feed, a Space SSR multifeed, profile statistics, Topic statistics, and Post metrics.\n- Optionally reads the public question `/log` audit for created time, view count, and asker identity (`includeQuestionAudit`), and paginates profile answer/question history (`includeProfileHistory`).\n- Optionally resolves public identity lists for question followers, answer upvoters, profile followers/following, and Space roles through explicitly requested relationship types and the sensitive-data gate.\n- Walks the question → answer → comment chain and keeps the links between them (`entity_edge` rows), so you can rebuild the conversation tree.\n- Offers four output shapes via `outputFormat`: `normalized` (separate rows per entity, default), `nested` (answers grouped under their question, comments under their answer), `flat`, and `edges` (relationship rows plus any status rows).\n- Reports a `status` row (rather than guessing) whenever a page is blocked, login-gated, removed, or otherwise inaccessible, and a `run_manifest` row summarizing the whole run.\n- Leaves empty content fields out of each row rather than filling them with a guess. `0` and `false` are kept as real values.\n- Never emits cookie/credential material. URLs are redacted when `redactSensitiveQueryParams` is on.\n\n## Output per record\n\nEvery row carries `content_type` (`question`, `answer`, `comment`, `profile`, `profile_activity`, `topic`, `topic_post`, `space`, `space_feed_item`, `entity_edge`, `relationship_collection`, `status`, or `run_manifest`), plus shared fields: `record_id`, `title`, `url`, `canonical_url`, `source_url`, `access_state`, `scrape_timestamp`, `requested_depth`, `observed_depth`, `detail_expansion_state`, `output_format`, `matched_input`, `matched_input_kind`, and (when search seeds were used) `source_query`/`source_queries`.\n\nEvery row also carries run-context fields describing how it was collected: `source_observations`/`source_observation_count`, `redirect_chain`, `url_redaction_state`/`url_redactions`, `proxy_used`, `proxy_path_used`, `proxy_resolution_state`, `session_cookie_count`, `session_input_state`, `session_cookie_expiry_state`, `request_delay_seconds`, `browser_locale`, `requested_language`, `navigation_retries`/`navigation_retry_delays_seconds`, `parser_version` and `parser_strategy`. With `includeFieldEvidence` on (default), rows also get `field_sources` (where each value came from) and `fields_present`.\n\n`access_state` is `public` for normal pages. Other values include `login_required`, `cloudflare_challenge`, `rate_limited`, `not_found`, `removed`, `unavailable`, `quora_plus_or_gated`, `quora_plus_preview`, `redirected_to_search`, `unsupported_url`, `search_unavailable`, `answer_pagination_limited`, `answer_pagination_unavailable`, `comments_unavailable`, `comments_capped`, `topic_feed_unavailable`, `topic_feed_capped`, `space_feed_capped`, `profile_history_limited`, `profile_history_unavailable`, `question_audit_unavailable`, `relationship_identity_unavailable`, `relationship_identity_capped`, `relationship_identities_not_observed`, `state_store_unavailable`, `state_store_uncommitted` and `network_error`.\n\n**Question row** — `question_url`, `question_id`, `question_answer_count` (label) / `question_answer_count_value` (parsed number) / `question_answer_count_scraped` (rows actually collected), `question_follower_count` / `question_follower_count_value` (when the public payload exposes it), `related_questions` (`qid`, `title`, `url`), `question_created_at`, `question_updated_at`, `question_view_count`, `question_audit_state`, `question_merge_count`, `question_age_days`/`question_age_state`, `last_answered_at` + `last_answered_at_evidence`, `question_author_name`/`_url`/`_image_url`/`_id`/`_is_verified`/`_is_anonymous`/`_credentials` (from a visible author card or the opt-in `/log` audit), `question_image_urls`/`_video_urls`/`_outbound_links` (opt-in), `answer_count`, `answer_limit_reached`, `topics`, `topic_links`.\n\n**Answer row** — `answer_id`, `answer_node_id`, `answer_url`, `answer_text`, `answer_html` (opt-in, derived from rich text), `answer_media_urls`/`_image_urls`/`_video_urls`/`_outbound_links` (opt-in), `answer_translation_state`/`_label`, `answer_original_url`, `answer_is_anonymous`, `answer_author_is_verified`, `answer_author_follower_count` (when present), `answer_created_at`/`_updated_at`, `answer_age_days`/`_state`, `answer_visibility`, `answer_text_completeness`, `answer_is_collapsed`, `answer_is_quora_plus`, `answer_access_option`, `answer_effective_access`, `answer_is_top_labeled`, `answer_rank`/`_rank_source`, `answer_upvote_count`/`_value`, `answer_comment_count`/`_value`, `answer_view_count`/`_value`, `answer_share_count`/`_value`, `reaction_breakdown` (opt-in), `is_ai_answer`/`ai_label_text`/`ai_label_source`, `related_content`/`_count`/`_observed_count`/`_limit_reached` (opt-in), `answer_jsonld_type`, `author_name`/`_url`/`_image_url`/`_id`/`_credentials`.\n\n**Comment row** — `comment_id`, `comment_url`, `comment_text`, `comment_source` (`graphql_comment_area`), `comment_author_name`/`_image_url`/`_id`/`_credentials`/`_is_verified`, `comment_is_anonymous`, `comment_timestamp`/`_created_at`, `comment_age_days`/`_state`, `comment_visibility`, `comment_upvote_count`/`_value`, `comment_reaction_count`/`_value`, `comment_reply_count`/`_value`, `comment_reaction_breakdown`, `comment_media_urls`/`_image_urls`/`_video_urls`/`_outbound_links`, `comment_is_top_labeled`, `comment_rank`/`_rank_source`, `comment_sort_order`, `comment_depth`, `comment_depth_limit_reached`, `comment_is_reply`, `parent_comment_id`/`_url`, `comment_reply_path`, `comment_container_id`, `comment_items_observed_count`/`_emitted_count`, `comment_limit_reached`, `comment_page_limited`.\n\n**Profile row** — `profile_url`, `profile_name`, `profile_bio`, `profile_image_url`, `profile_author_id`, `profile_is_verified`, `profile_is_restricted`, `profile_account_status`, `profile_is_anonymous`, `profile_is_deceased`, `profile_snapshot_state`, plus `profile_follower_count`, `profile_following_count`, `profile_answer_count`, `profile_question_count`, `profile_post_count`, `profile_total_content_views`, `profile_month_content_views`, `profile_joined_at`, `profile_credential`, `profile_work_credentials`, `profile_school_credentials`, `profile_location_credentials`, `profile_expertise_topics`, `profile_history_limited` when the visible feed is truncated or the opt-in history is capped, and `profile_history_state` (`not_requested`/`observed`/`capped`/`rate_limited`/`unavailable`/`empty`) when history is requested.\n\n**Profile-activity row** — `activity_url`, `activity_type`, `activity_source`, `activity_question_url`/`_title`/`_id`, `activity_answer_id`, `created_at`, `author_name`/`_url`/`_image_url`/`_id`/`_credentials`.\n\n**Topic row** — `topic_url`, `topic_id`, `topic_follower_count`, `topic_most_viewed_authors` (`uid`, `name`, `url`, `follower_count`, `num_views`, `num_public_most_viewed_answers`, `credential`), `topic_photo_url`, `topic_default_photo_url`, `topic_has_leaderboard`, and `topic_feed_state` (`not_requested`/`observed`/`capped`/`unavailable`).\n\n**Topic-Post row** — `post_url`, `post_pid`, `post_node_id`, `post_title` (explicit title or first content line), `post_body`, `post_media_urls`/`_image_urls`/`_video_urls`/`_outbound_links` (opt-in), `post_author_name`/`_url`/`_image_url`/`_id`/`_credentials`/`_is_verified`/`_is_anonymous`/`_follower_count`, `post_question_url`/`_title`, `topic_url`, `post_created_at`/`_updated_at`, `post_age_days`/`_state`, `post_updated_age_days`/`_state`, `post_upvote_count`, `post_view_count`, `post_share_count`, `post_comment_count`, `post_effective_access`, `post_is_question_summary`.\n\n**Space row** — `space_url`, `space_id`, `space_follower_count`, `space_all_time_followers` (conditional), `space_member_count`, `space_contributor_count`, `space_moderator_count`, `space_admin_count`, `space_description`, `space_icon_url`, `space_cover_url`, `space_item_count`, `space_feed_capped`, `space_ads_skipped`.\n\n**Space feed-item row** — `feed_url`, `feed_type`, `feed_title`, `feed_text` (opt-in), `feed_post_pid`/`feed_post_node_id` (post stories), `feed_author_name`/`_url`/`_image_url`/`_id`/`_credentials`/`_is_verified`/`_is_anonymous`, `feed_created_at`, `feed_age_days`/`_state`, `feed_upvote_count`, `feed_view_count`, `feed_share_count`, `feed_comment_count`, `feed_effective_access`, `feed_is_ai_answer`, `feed_question_url`/`_title`, `media_urls`/`image_urls`/`video_urls`/`outbound_links` (opt-in).\n\n**Relationship row (`entity_edge`)** — `relationship`, `edge_id`, `from_record_id`/`_content_type`/`_url`/`_id`, `to_record_id`/`_content_type`/`_url`/`_id`/`_name`/`_image_url`, `node_image_url`, `edge_state`, `unresolved_reason`, `edge_evidence_field`, `relationship_collection_key`, `collection_total_text`/`_value`.\n\n**Relationship-count row (`relationship_collection`)** — `relationship_collection_key`, `collection_total_text`, `collection_total_value`, `edge_evidence_field`.\n\n**Status row** — `access_state`, `http_status`, `error`, `source_url`, and for pages that failed to load `final_url`, `scrape_duration_ms`, `navigation_attempts`, `navigation_retries`. Run-level status rows (`url: run://quora-dataset-builder`) report a state store that could not be read (`state_store_unavailable`), state that was not saved because a source did not finish (`state_store_uncommitted`), or a run that produced no real rows (`no_records_emitted`).\n\n**Option-dependent fields** — with a `stateStoreId`, entity rows add `event_type` (`new`/`changed`/`unchanged`/`scope_mismatch`), `state_snapshot_hash`, `previous_snapshot_hash`, `state_scope_fingerprint`, `state_store_state`, `only_new_items`, `include_unchanged`. With `includeRawEvidence`, page-level rows add `raw_html_sha256`, `raw_html_bytes`, `raw_html_truncated`, `raw_html_returned_bytes`, `raw_html_redaction_state`, `raw_html_redactions`, `raw_evidence_state`, `raw_evidence_retention_days`, plus `raw_html` when `includeHtml` is also on and `rawEvidenceRetentionDays` is above zero. In `nested` format, question rows carry `answers` arrays (each answer with its `comments`) and `nested_*` count fields. With `maxItemsPerSource` set, rows add `max_items_per_source` and per-source cap fields.\n\n**Run-manifest row** — one per run, summarizing counts and the settings actually applied: `run_started_at`/`_finished_at`/`_duration_ms`, `records_emitted`, `source_pages_attempted`, `content_type_counts`, `access_state_counts`, `input_accounting`, `requested_result_types`, `requested_output_fields`, `dedupe_mode`, `duplicate_records_suppressed`, `proxy_path_used`, `proxy_resolution_state`, `search_discovery_source`, `search_discovery_hits`, `answer_gql_pages`, `answer_pagination_state`, `answer_pagination_unrelated_suppressed`, `comment_gql_pages`, `topic_feed_pages`, `space_feed_bundles`, `quora_plus_preview_count`, `comment_cap_hit_count`, `topic_feed_cap_hit_count`, `profile_history_pages`, `profile_history_state`, `relationship_identity_pages`, `relationship_identity_requests`, `relationship_identity_states`, `question_audit_state`, `question_audit_attempts`, `legacy_input_notes`, `hard_limits`, `gql_calls`, `query_hashes`, and the per-run values of your own input settings echoed back for reconciliation.\n\n## Trimming rows, depth, sessions and caps\n\n- **Field allowlist.** `outputFields` keeps only the fields you name, applied after extraction; an empty list returns the full row. Nested projection is supported with dotted paths such as `answers.answer_text` or `answers.comments.comment_text` in `nested` output. Child identity/URL fields stay in place, and `content_type`, identity, access/status, depth, timing and parser fields are always protected so a trimmed row can still be traced. `output_projection` on each row reads `full` or `selected`, and the run manifest records the requested fields. `includeFieldEvidence` toggles the `field_sources`/`fields_present` maps.\n- **Depth.** `scrapeDepth: \"detail\"` (default) runs the capped traversal; `overview` emits page-level summaries without answer, comment, profile-activity or Space-feed expansion. Every row reports `requested_depth`, `observed_depth` and `detail_expansion_state`. `bounded` means a configured cap was reached, not that Quora's full history was collected, and blocked pages report `observed_depth: \"status\"`.\n- **Caps.** `maxAnswersPerQuestion` bounds each question, `maxAnswers` is a global answer cap, `maxAnswerPages` bounds GraphQL pages explicitly, `maxItems` caps entity/status rows before graph/manifest rows, `maxItemsPerSource` caps each source, and `maxGraphEdges` caps relationship rows. When `maxItems`/`maxGraphEdges` is 0 the corresponding cap is off. `maxRelationshipItemsPerCollection` bounds each labeled relationship collection, `maxRelationshipPages` bounds each public identity-list query, and `maxProfileHistoryPages` bounds each profile answer/question list. `answer_pagination_limited` is emitted only when a configured page cap or a GraphQL rate limit stopped pagination; an exhausted source is not reported as a cap.\n- **Comments.** Set `includeComments: true`. When `maxCommentsPerAnswer` is 0, the documented fallback is 10 per answer. The actor calls `AllCommentsListQuery` with `after` cursors and a page size derived from your cap (up to 50), so a 24-comment answer is collected as 10 + 10 + 4 when the server pages at ten. `includeCommentReplies` (or `includeReplyGraph`) expands nested replies up to `maxCommentDepth`; `comment_page_limited` is set only when a cap is actually hit, and a `comments_capped` status row follows. If the paginated query fails, the actor falls back to the first-page loader rather than inventing rows. Comments use Quora's comment-area GraphQL, which `robots.txt` disallows for generic agents: keep this opt-in and review your own compliance posture.\n- **Topic feed.** Set `includeTopicFeed: true` to call the topic page's own public GraphQL feed. `maxTopicFeedPages` bounds pages. This path is also robots-sensitive; keep it opt-in.\n- **Question audit.** `includeQuestionAudit: true` reads the question's public `/log` page for `question_created_at`, `question_view_count`, `question_merge_count`, and the asker name/uid/profile/credential. It retries a transient 403 once, then keeps `question_audit_state: \"unavailable\"` and a `question_audit_unavailable` status row. `/log` is robots-disallowed for generic agents and is never part of the daily prefill.\n- **Profile history.** `includeProfileHistory: true` paginates `UserProfileAnswersMostRecent_RecentAnswers_Query` and `UserProfileQuestionsList_Questions_Query` and emits bounded `profile_activity` rows. `maxProfileHistoryPages` (default 0 = three pages per list) and `requestDelay` (used as a 1.5–2.5 s GraphQL pace when above zero) bound the work. A cap sets `profile_history_limited`; a 400/403 sets `profile_history_state: \"rate_limited\"` and a `profile_history_unavailable` status row instead of fabricated rows.\n- **Identity lists.** Identity rows are emitted only when `relationshipTypes` explicitly requests them, the matching family flag is on, and `includeSensitiveRelationshipData` is on for sensitive types. The public GraphQL operations cover profile followers/following people/questions/Spaces/Topics, question followers, answer upvoters, and Space admins/contributors/moderators/followers. `maxRelationshipItemsPerCollection` and `maxRelationshipPages` bound every list; Space role calls run from a `www.quora.com` page context. These lists are robots-sensitive and rate-sensitive; a failure keeps a `relationship_identity_unavailable` or `relationship_identities_not_observed` status row, and a page/item cap adds `relationship_identity_capped`.\n- **Sessions and proxies.** No account, login, cookie, or session secret is used. The transport ladder is direct (`curl_cffi`, fresh session per attempt) → optional user proxy override → Apify AUTO datacenter → RESIDENTIAL only as a hardcoded last resort after the free rungs fail. A missing `proxyConfiguration` never stops the run, and there is no paid default. `proxy_path_used` reports the rung that worked.\n- **Exact field names.** Every output field this actor can emit is listed under [Output per record](#output-per-record) above. Fields whose source is absent on a given page are omitted, not set to null or a sentinel.\n\n## Complete schema input inventory\n\nEvery input is optional. The daily prefill uses one public question URL with a small answer cap, comments and feeds off, and no paid proxy.\n\n| Field | Type | Default | Description |\n|---|---|---|---|\n| `mode` | string | `auto` | `auto` / `byQuestionUrls` / `byAnswerUrls` / `byProfileUrls` / `byTopicUrls` / `bySpaceUrls` / `byPostUrls` / `search`; typed modes validate seed routes |\n| `scrapeDepth` | string | `detail` | `overview` (page-level summary only) or `detail` (full capped traversal) |\n| `startUrls` | array | `[]` | Question, answer, profile, Topic, Space, or Post URLs; mixed lists are auto-detected and invalid hosts become status rows |\n| `searchQueries` | array | `[]` | Best-effort discovery terms; Quora's native search is login/Cloudflare-gated and is never claimed |\n| `questionUrls` | array | `[]` | Typed question seeds |\n| `answerUrls` | array | `[]` | Typed answer-permalink seeds |\n| `topicUrls` | array | `[]` | Typed Topic seeds |\n| `spaceUrls` | array | `[]` | Typed Space seeds; automatically enables Space output |\n| `profileUrls` | array | `[]` | Typed profile seeds |\n| `postUrls` | array | `[]` | Typed standalone Post seeds |\n| `resultTypes` | array | `[\"question\",\"answer\",\"comment\",\"profile\",\"profile_activity\",\"topic\",\"topic_post\",\"space\",\"space_feed_item\",\"entity_edge\",\"status\",\"run_manifest\"]` | Which `content_type` values to include |\n| `outputFormat` | string | `normalized` | `normalized` / `nested` / `flat` / `edges` |\n| `dedupeMode` | string | `canonical` | `canonical` (merge duplicate entities by canonical URL/ID) or `none` |\n| `onlyNewItems` | boolean | `false` | With `stateStoreId`, suppress rows unchanged since the last run |\n| `includeUnchanged` | boolean | `true` | Keep unchanged rows when `onlyNewItems` is on |\n| `stateStoreId` | string | - | Apify key-value store name for incremental re-scraping; required when `onlyNewItems` is on |\n| `outputFields` | array | `[]` | Optional field allowlist for smaller rows; identity/status fields are always kept |\n| `includeFieldEvidence` | boolean | `true` | Include `field_sources`/`fields_present` on each row |\n| `includeUnresolvedEdges` | boolean | `true` | Keep relationship rows whose target could not be matched |\n| `relationshipTypes` | array | `[]` | Allowlist of labeled relationship collections to expand (follower, following, want-answers, upvoter, Space role); identity-revealing types also need `includeSensitiveRelationshipData` and the matching family opt-in |\n| `includeProfileEdges` | boolean | `false` | Per-family opt-in for profile follower/following/question/space/topic relationships |\n| `includeQuestionFollowerEdges` | boolean | `false` | Per-family opt-in for question follower/want-answer identities (sensitive) |\n| `includeAnswerUpvoterEdges` | boolean | `false` | Per-family opt-in for answer upvoter identities (requires `includeSensitiveRelationshipData`) |\n| `includeSensitiveRelationshipData` | boolean | `false` | Privacy gate required for identity-revealing relationship collections |\n| `includeTargetMetadata` | boolean | `false` | Keep the visible name/image of each relationship target |\n| `includeRelationshipCounts` | boolean | `false` | Emit privacy-preserving member-count rows; also add `relationship_collection` to `resultTypes` |\n| `includeSpaceRoleEdges` | boolean | `false` | Keep Space contributor/moderator/admin edges |\n| `includeSpaceContentEdges` | boolean | `true` | Keep Space to post/question membership edges and feed-item membership |\n| `maxRelationshipItemsPerCollection` | integer | `500` | Cap per labeled relationship collection |\n| `maxQuestions` | integer | `25` | How many discovered question links get queued on top of your own seed URLs |\n| `maxAnswersPerQuestion` | integer | `10` | Maximum answer rows kept per question after SSR and GraphQL pagination |\n| `maxAnswers` | integer | `0` | Global answer cap across the whole run (`0` = no cap) |\n| `includeQuestion` | boolean | `true` | Keep question entities in the output |\n| `includeAuthor` | boolean | `true` | Keep author/profile entities and author fields in the output |\n| `includeAuthorSnapshot` | boolean | `false` | Fetch a bounded profile snapshot for each visible answer author |\n| `includeTopics` | boolean | `true` | Keep topic entities and topic links |\n| `includeSpaces` | boolean | `false` | Keep Space and Space feed-item rows; switched on automatically when a Space URL is used in `startUrls` or `spaceUrls` |\n| `includeComments` | boolean | `false` | Opt-in comment rows with `AllCommentsListQuery` cursor pagination; robots-sensitive |\n| `includeEngagementBreakdown` | boolean | `true` | Include per-reaction breakdowns alongside aggregate counts |\n| `includeRelatedContent` | boolean | `false` | Collect explicitly attached answer related-content links when Quora's public payload exposes them; otherwise they are omitted |\n| `maxRelatedContent` | integer | `20` | Bound related-content links per answer when enabled; zero emits no related-content items |\n| `topCommentsOnly` | boolean | `false` | Keep only comments explicitly labeled Top/Most helpful |\n| `commentSortOrder` | string | `observed` | `observed` / `upvotes_desc` / `reactions_desc` / `replies_desc` / `newest` |\n| `includeReplyGraph` | boolean | `false` | Compatibility alias that enables comments and nested replies |\n| `includeMedia` | boolean | `false` | Include image/video URL fields where available |\n| `includeFeedText` | boolean | `false` | Include visible text on Space feed cards |\n| `includeOutboundLinks` | boolean | `false` | Include non-Quora links found in rich text |\n| `includeEntityGraph` | boolean | `false` | Emit relationship rows even when `entity_edge` is not in `resultTypes` |\n| `maxCommentsPerAnswer` | integer | `0` | Comments kept per answer; when comments are on and this is 0, the fallback is 10; the cap is the pagination limit, not a page size |\n| `maxCommentDepth` | integer | `20` | Maximum nested reply depth when replies are enabled; 0 disables replies |\n| `maxItems` | integer | `0` | Cap on entity/status rows before graph and manifest rows (`0` = no cap) |\n| `maxGraphEdges` | integer | `5000` | Cap on relationship rows (`0` = no edges) |\n| `maxScrollAttempts` | integer | `5` | Scroll attempts per page in detail mode |\n| `maxLoadMoreAttempts` | integer | `0` | \"Load more\" button clicks per page |\n| `includeRawEvidence` | boolean | `false` | Attach a document hash and size/redaction metadata for auditing |\n| `includeHtml` | boolean | `false` | Retain bounded raw HTML on page-level rows and derived answer HTML |\n| `maxHtmlBytes` | integer | `100000` | Upper bound for retained or derived HTML |\n| `requestDelay` | number | `1` | Delay in seconds between page batches |\n| `maxConcurrency` | integer | `1` | Independent seeds processed in parallel (values above 3 are treated as 3) |\n| `maxNavigationRetries` | integer | `2` | Retries after a failed page load (max 3) |\n| `language` | string | `auto` | Browser language hint (`en`, `es`, `fr`, ...); not a translation guarantee |\n| `proxyConfiguration` | object | - | Optional proxy override. The free ladder runs first; there is no paid default |\n| `redactSensitiveQueryParams` | boolean | `true` | Redact credential-like query values and fragment credentials from emitted URLs/HTML |\n| `rawEvidenceRetentionDays` | integer | `30` | Retention label for raw HTML evidence; 0 keeps metadata only |\n| `maxRawEvidenceBytes` | integer | `100000` | Size bound for raw HTML evidence |\n| `maxItemsPerSource` | integer | `0` | Cap on records from each individual source URL/query (`0` = no cap) |\n| `searchDiscovery` | string | `relatedOnly` | `relatedOnly` (related questions only) / `bestEffortIndex` (third-party index) / `off` |\n| `maxRelatedQuestions` | integer | `20` | Related questions enqueued per question seed |\n| `searchResultsPerQuery` | integer | `10` | Maximum best-effort index results per query |\n| `maxAnswerPages` | integer | `0` | Explicit answer GraphQL page cap; 0 derives from `maxAnswersPerQuestion` |\n| `maxTopicFeedPages` | integer | `3` | Topic-feed GraphQL page cap when `includeTopicFeed` is on (minimum one page) |\n| `maxSpaceFeedBundles` | integer | `4` | Space feed bundles read from the SSR multifeed |\n| `includeCommentReplies` | boolean | `false` | Expand nested `repliesConnection` comment replies |\n| `includeQuoraPlusPreview` | boolean | `true` | Emit Quora+ preview answers with preview flags; when false, omit them |\n| `includeProfileStats` | boolean | `true` | Emit profile follower/following/answer/question/post/view/joined/credential fields |\n| `includeTopicStats` | boolean | `true` | Emit Topic follower count and most-viewed authors |\n| `includeSpaceStats` | boolean | `true` | Emit Space counters, description, icon and cover |\n| `includePostStats` | boolean | `true` | Emit Post counters, effective access and question-summary flag |\n| `includeAnswerStats` | boolean | `true` | Emit answer counters, dates, AI flag and effective access |\n| `includeTopicFeed` | boolean | `false` | Browser GraphQL Topic feed; opt-in and robots-sensitive |\n| `includeQuestionAudit` | boolean | `false` | Read the public question `/log` for created time, view count, merge count, and asker identity; robots-sensitive opt-in |\n| `includeProfileHistory` | boolean | `false` | Paginate the public profile answer/question tabs into bounded `profile_activity` rows; robots- and rate-sensitive opt-in |\n| `maxProfileHistoryPages` | integer | `0` | Cap per profile history list; 0 derives three pages (about 30 items per list) |\n| `maxRelationshipPages` | integer | `3` | Cap per public identity-list query after the relationship allowlist and privacy gates |\n\n## Example inputs\n\n### Example: full detail for a question\n\n```json\n{\n \"questionUrls\": [{ \"url\": \"https://www.quora.com/What-is-the-best-way-to-learn-Python\" }],\n \"maxAnswersPerQuestion\": 20,\n \"includeComments\": true,\n \"maxCommentsPerAnswer\": 10\n}\n```\n\n### Example: best-effort search discovery, compact nested output\n\n```json\n{\n \"searchQueries\": [\"machine learning career advice\"],\n \"searchDiscovery\": \"relatedOnly\",\n \"maxQuestions\": 10,\n \"outputFormat\": \"nested\",\n \"maxAnswersPerQuestion\": 5\n}\n```\n\n### Example: a Space's content and follower count\n\n```json\n{\n \"spaceUrls\": [{ \"url\": \"https://www.quora.com/q/example-space\" }],\n \"resultTypes\": [\"space\", \"space_feed_item\", \"relationship_collection\", \"run_manifest\"],\n \"includeRelationshipCounts\": true,\n \"relationshipTypes\": [\"space_has_contributor\"]\n}\n```\n\n### Example: incremental re-scrape of the same question\n\n```json\n{\n \"questionUrls\": [{ \"url\": \"https://www.quora.com/What-is-the-best-way-to-learn-Python\" }],\n \"onlyNewItems\": true,\n \"includeUnchanged\": false,\n \"stateStoreId\": \"python-question-watch\"\n}\n```\n\n## Use cases\n\n- **Content research** — pull full question-answer-comment threads on a topic for analysis\n- **Community monitoring** — re-scrape the same questions on a schedule and keep only rows flagged `new`/`changed`\n- **Knowledge graph building** — use `outputFormat: \"edges\"` to load the question/answer/topic relationship graph into a graph database\n- **Influencer and expert tracking** — follow a profile's visible answers and its public follower/following/content statistics\n- **Space analysis** — collect a Quora Space's feed, metrics and contributor counts\n\n## FAQ\n\n**Do I need a Quora account?**\nNo. Direct public question, answer, profile, Topic, Space, and Post pages are read without login. The actor never asks for, stores, or emits cookies or session secrets.\n\n**Why did I get a `status` row instead of question/answer data?**\nQuora showed a login wall, Cloudflare challenge, a removed page, or an unsupported redirect for that URL. The actor reports this honestly as a `status` row instead of guessing at data that was not there. A run with zero real rows also gets a `no_records_emitted` status row and a non-success status message.\n\n**Why do I sometimes get fewer answers than `maxAnswersPerQuestion`?**\nThe actor reads the server-rendered answers, filters out answers whose question is provably unrelated, then paginates the public GraphQL cursor up to your cap. If the question genuinely has fewer answers, the cursor stops; you get the answers that were observable and no `answer_pagination_limited` row, because the source was exhausted rather than capped. `answer_pagination_limited` appears only when `maxAnswerPages`/your cap stopped a non-exhausted source or Quora rate-limited a pagination request, and the page's known `answerCount` is not already satisfied; a non-rate GraphQL failure uses `answer_pagination_unavailable`. Neither case fabricates an answer.\n\n**How do I get question created time, view count, or the asker?**\nSet `includeQuestionAudit: true`. The actor reads the public `//log` page (robots-sensitive, opt-in) and fills `question_created_at`, `question_view_count`, `question_merge_count`, and the `question_author_*` fields. Without it, those fields are omitted rather than guessed. A blocked `/log` leaves `question_audit_state: \"unavailable\"` and a status row.\n\n**How do I get more than the three visible profile history items?**\nSet `includeProfileHistory: true`. The actor paginates the public answer/question tab connections into `profile_activity` rows, bounded by `maxProfileHistoryPages` and paced by `requestDelay`. This GraphQL path is robots- and rate-sensitive; a 400/403 leaves a `profile_history_unavailable` status row and no fabricated rows.\n\n**What is the difference between the four `outputFormat` values?**\n`normalized` keeps every entity as its own row (the default). `nested` groups each question's answers (and each answer's comments) underneath it; rows without a matching parent stay at the top level with an orphan reason. `flat` is like `normalized`, except answer rows also get question context and comment rows get `answer_url`. `edges` returns the relationship rows between entities plus any status rows.\n\n**Can I get a Quora account's followers, question followers, answer upvoters, or Space roles?**\nYes, as explicit opt-ins. Request the relationship type in `relationshipTypes`, turn on the matching family flag (`includeProfileEdges`, `includeQuestionFollowerEdges`, `includeAnswerUpvoterEdges`, or `includeSpaceRoleEdges`), and set `includeSensitiveRelationshipData: true` for follower/upvoter/want-answer types. The actor then calls the public identity-list GraphQL operations, paginates up to `maxRelationshipPages`, and emits only identities whose profile/question/Space/Topic URLs it observed. It may also use visible DOM links as a fallback. These paths are robots- and rate-sensitive; failures produce `relationship_identity_unavailable` or `relationship_identities_not_observed` status rows. It never invents identities.\n\n**What does the incremental re-scrape (`onlyNewItems`) actually compare?**\nIt hashes each entity's semantic content and compares it to the previous run stored under `stateStoreId`, tagging each row `new`, `changed`, `unchanged`, or `scope_mismatch` (the previous run used different settings). Rows are only dropped when `onlyNewItems` is on and `includeUnchanged` is off. Status and manifest rows are never dropped by this setting. If any requested source did not finish, the new state is not saved and a `state_store_uncommitted` status row tells you so.\n\n**Why are some text/media fields missing even with `includeMedia`/`includeHtml` on?**\nThose fields are only populated when Quora's public payload actually contains that content for the entity in question. The toggles request the data; they do not guarantee every entity has it.\n\n**Is search native Quora search?**\nNo. Quora's native `/search?q=` is login/Cloudflare-gated for logged-out clients and is disallowed by `robots.txt`. `searchQueries` uses related-question discovery by default and an optional third-party best-effort index; if no public results are discoverable it emits a `search_unavailable` status row.\n\n**What are the hard limitations?**\nNative Quora search is not available cookielessly: `/search?q=` redirects and the public search GraphQL returns no connection. Quora+ `smart_distribution` answers may be preview/truncated; they are flagged `answer_is_quora_plus` and their observed completeness is reported, and no gated remainder is fabricated. Space all-time views/upvotes/comments are private (tested across ten diverse Spaces), Topic description and question count are absent, and question description is absent. Space `allTimeFollowers` is emitted as `space_all_time_followers` only when the payload carries it (not every Space does).\n\nQuestion created/view/asker, full profile history, comment/reply pagination, and identity lists are technically available through public pages/GraphQL but are **robots-sensitive and/or rate-sensitive opt-ins**; they are off by default and not part of the daily prefill. Be aware that `robots.txt` for generic agents disallows `/` broadly, including `/*_POST`, `/*/log`, `/*/followers`, `/*/following`, and `/*/comments`; product/legal review decides whether to enable those opt-ins. Quora URLs are valid in a browser, but plain HTTP clients can receive a Cloudflare 403 on HEAD/GET; the actor fetches them with TLS impersonation.\n\n**Is this affiliated with Quora?**\nNo. This is an independent, third-party actor that reads public Quora pages; it is not affiliated with or endorsed by Quora, Inc. You are responsible for how you use the data.\n", "dockerfile": "./Dockerfile", "storages": { "dataset": { "actorSpecification": 1, "title": "Quora Dataset Builder Output", "views": { "overview": { "title": "Normalized records", "transformation": { "fields": [ "content_type", "event_type", "state_snapshot_hash", "previous_snapshot_hash", "state_scope_fingerprint", "state_store_state", "state_store_error", "only_new_items", "include_unchanged", "parser_strategy", "parser_version", "field_sources", "fields_present", "final_url", "http_status", "error", "scrape_duration_ms", "navigation_attempts", "navigation_retries", "proxy_resolution_state", "session_input_state", "browser_locale", "navigation_retry_delays_seconds", "records_emitted", "input_accounting", "session_cookie_count", "session_cookie_expiry_state", "run_duration_ms", "proxy_used", "request_delay_seconds", "scrape_timestamp", "requested_result_types", "run_started_at", "run_finished_at", "source_pages_attempted", "content_type_counts", "access_state_counts", "relationship_collection_diagnostic", "manifest_version", "requested_output_fields", "max_concurrency", "navigation_attempts_total", "navigation_retries_total", "raw_evidence_retention_days", "max_raw_evidence_bytes", "redact_sensitive_query_params", "raw_html_redactions", "url_redactions", "date_interpretations", "canonical_url", "redirect_chain", "answer_count", "scroll_attempts", "scroll_state", "load_more_attempts", "load_more_clicks", "load_more_state", "raw_html_redaction_state", "url_redaction_state", "output_format", "output_projection", "answers", "comments", "nested_answer_count", "nested_answer_count_observed", "nested_comment_count", "nested_comment_count_observed", "nested_child_state", "nested_orphan_reason", "requested_depth", "observed_depth", "detail_expansion_state", "title", "question_title", "url", "post_url", "post_pid", "post_node_id", "post_title", "post_author_name", "post_author_url", "post_author_image_url", "post_author_id", "post_author_credentials", "post_author_is_verified", "post_author_is_anonymous", "post_body", "post_media_urls", "post_image_urls", "post_video_urls", "post_outbound_links", "question_media_urls", "question_author_name", "question_author_url", "question_author_image_url", "question_author_id", "question_author_is_verified", "question_author_is_anonymous", "question_author_credentials", "question_image_urls", "question_video_urls", "question_outbound_links", "post_created_at", "post_updated_at", "post_updated_age_days", "post_updated_age_state", "post_age_days", "post_age_state", "relationship", "record_id", "access_state", "from_record_id", "to_record_id", "from_id", "to_id", "to_name", "to_image_url", "node_image_url", "relationship_collection_key", "collection_total_text", "collection_total_value", "edge_evidence_field", "unresolved_reason", "source_query", "source_kind", "source_queries", "matched_input", "matched_input_kind", "source_observations", "source_observation_count", "question_url", "question_answer_count", "question_answer_count_value", "question_answer_count_scraped", "question_id", "question_created_at", "question_age_days", "question_age_state", "question_updated_at", "question_view_count", "question_audit_state", "question_merge_count", "last_answered_at", "last_answered_at_evidence", "answer_id", "answer_node_id", "answer_url", "answer_text", "answer_html", "answer_media_urls", "answer_image_urls", "answer_video_urls", "answer_outbound_links", "answer_translation_state", "answer_translation_label", "answer_original_url", "answer_is_anonymous", "answer_author_is_verified", "answer_author_credentials", "answer_author_image_url", "answer_updated_at", "answer_created_at", "answer_age_days", "answer_age_state", "answer_visibility", "answer_text_completeness", "answer_is_collapsed", "answer_is_quora_plus", "answer_is_top_labeled", "answer_rank_source", "answer_upvote_count", "answer_upvote_count_value", "answer_comment_count", "answer_comment_count_value", "answer_view_count", "answer_view_count_value", "answer_share_count", "answer_share_count_value", "reaction_breakdown", "is_ai_answer", "ai_label_text", "ai_label_source", "related_content", "related_content_count", "related_content_observed_count", "related_content_limit_reached", "answer_jsonld_type", "answer_rank", "answer_limit_reached", "edge_id", "from_url", "to_url", "comment_id", "comment_url", "comment_text", "comment_author_name", "comment_author_url", "comment_author_image_url", "comment_author_id", "comment_author_credentials", "comment_author_is_verified", "comment_is_anonymous", "comment_timestamp", "comment_created_at", "comment_age_days", "comment_age_state", "comment_visibility", "comment_upvote_count", "comment_depth", "comment_depth_limit_reached", "comment_items_observed_count", "comment_items_emitted_count", "comment_limit_reached", "comment_media_urls", "comment_image_urls", "comment_video_urls", "comment_outbound_links", "comment_collection_label", "comment_is_top_labeled", "comment_filter_top_only", "comment_filter_observed", "comment_filter_emitted", "comment_filter_unknown", "comment_rank", "comment_rank_source", "comment_sort_order", "comment_sort_observed", "comment_sort_fallback_count", "comment_reaction_count", "comment_reaction_count_value", "comment_reply_count", "comment_reply_path", "parent_comment_id", "parent_answer_url", "parent_comment_url", "comment_is_reply", "comment_reaction_breakdown", "comment_upvote_count_value", "comment_reply_count_value", "profile_url", "profile_name", "profile_bio", "profile_image_url", "profile_jsonld_type", "profile_author_id", "profile_is_verified", "profile_is_restricted", "profile_snapshot_requested", "topic_url", "space_url", "feed_url", "feed_type", "feed_post_pid", "feed_post_node_id", "feed_title", "feed_text", "feed_author_name", "feed_author_url", "feed_author_image_url", "feed_author_id", "feed_author_credentials", "feed_author_is_verified", "feed_author_is_anonymous", "feed_created_at", "feed_age_days", "feed_age_state", "media_urls", "image_urls", "video_urls", "outbound_links", "activity_url", "activity_type", "activity_source", "activity_question_url", "activity_question_title", "activity_question_id", "activity_answer_id", "author_name", "author_url", "author_image_url", "author_id", "author_credentials", "topics", "topic_links", "created_at", "timestamp", "include_unresolved_edges", "include_field_evidence", "include_engagement_breakdown", "include_entity_graph", "profile_snapshot_state", "global_answer_cap_reached", "answers_observed_before_global_cap", "answers_suppressed_by_global_cap", "dedupe_mode", "duplicate_records_suppressed", "raw_html_bytes", "raw_html_returned_bytes", "raw_html_truncated", "raw_evidence_state", "raw_html", "raw_html_sha256", "max_items_per_source", "source_cap", "source_items_observed", "source_items_emitted", "source_cap_reached", "source_url", "from_content_type", "to_content_type", "edge_state", "requested_language", "max_answers_per_question", "max_answers_total", "recordType", "scrapedAt", "sourceUrl", "question_follower_count", "question_follower_count_value", "related_questions", "answer_author_follower_count", "answer_access_option", "answer_effective_access", "answer_original_question_url", "answer_original_question_title", "profile_follower_count", "profile_following_count", "profile_answer_count", "profile_question_count", "profile_post_count", "profile_total_content_views", "profile_month_content_views", "profile_joined_at", "profile_credential", "profile_work_credentials", "profile_school_credentials", "profile_location_credentials", "profile_expertise_topics", "profile_account_status", "profile_is_anonymous", "profile_is_deceased", "profile_history_limited", "profile_history_state", "topic_id", "topic_name", "topic_follower_count", "topic_most_viewed_authors", "topic_photo_url", "topic_default_photo_url", "topic_has_leaderboard", "topic_feed_state", "space_id", "space_name", "space_follower_count", "space_all_time_followers", "space_member_count", "space_contributor_count", "space_moderator_count", "space_admin_count", "space_description", "space_icon_url", "space_cover_url", "space_item_count", "space_feed_capped", "space_ads_skipped", "feed_upvote_count", "feed_view_count", "feed_share_count", "feed_comment_count", "feed_effective_access", "feed_is_ai_answer", "feed_question_url", "feed_question_title", "post_upvote_count", "post_view_count", "post_share_count", "post_comment_count", "post_effective_access", "post_is_question_summary", "post_author_follower_count", "post_question_url", "post_question_title", "comment_source", "comment_page_limited", "comment_container_id", "proxy_path_used", "search_discovery_source", "search_discovery_hits", "answer_gql_pages", "comment_gql_pages", "topic_feed_pages", "space_feed_bundles", "quora_plus_preview_count", "comment_cap_hit_count", "topic_feed_cap_hit_count", "profile_history_pages", "relationship_identity_pages", "relationship_identity_requests", "question_audit_attempts", "answer_pagination_state", "answer_pagination_unrelated_suppressed", "relationship_identity_states", "gql_calls", "query_hashes", "legacy_input_notes", "hard_limits", "proxy_errors" ] }, "display": { "component": "table", "properties": { "content_type": { "label": "Type", "format": "text" }, "event_type": { "label": "Incremental event", "format": "text" }, "state_snapshot_hash": { "label": "Current state hash", "format": "text" }, "previous_snapshot_hash": { "label": "Previous state hash", "format": "text" }, "state_scope_fingerprint": { "label": "State scope fingerprint", "format": "text" }, "state_store_state": { "label": "State store", "format": "text" }, "state_store_error": { "label": "State store error", "format": "text" }, "only_new_items": { "label": "Only new items", "format": "boolean" }, "include_unchanged": { "label": "Include unchanged", "format": "boolean" }, "parser_strategy": { "label": "Parser strategy", "format": "text" }, "parser_version": { "label": "Parser version", "format": "text" }, "field_sources": { "label": "Field sources", "format": "json" }, "fields_present": { "label": "Fields present", "format": "json" }, "final_url": { "label": "Final URL", "format": "link" }, "http_status": { "label": "HTTP status", "format": "number" }, "error": { "label": "Error", "format": "text" }, "scrape_duration_ms": { "label": "Duration (ms)", "format": "number" }, "navigation_attempts": { "label": "Navigation attempts", "format": "number" }, "navigation_retries": { "label": "Navigation retries", "format": "number" }, "proxy_resolution_state": { "label": "Proxy state", "format": "text" }, "session_input_state": { "label": "Session input", "format": "text" }, "browser_locale": { "label": "Browser locale", "format": "text" }, "navigation_retry_delays_seconds": { "label": "Retry delays", "format": "json" }, "records_emitted": { "label": "Records emitted", "format": "number" }, "input_accounting": { "label": "Input accounting", "format": "json" }, "session_cookie_count": { "label": "Session cookie count", "format": "number" }, "session_cookie_expiry_state": { "label": "Cookie expiry", "format": "text" }, "run_duration_ms": { "label": "Run duration (ms)", "format": "number" }, "proxy_used": { "label": "Proxy used", "format": "boolean" }, "request_delay_seconds": { "label": "Request delay (s)", "format": "number" }, "scrape_timestamp": { "label": "Scrape timestamp", "format": "text" }, "requested_result_types": { "label": "Requested result types", "format": "json" }, "run_started_at": { "label": "Run started", "format": "text" }, "run_finished_at": { "label": "Run finished", "format": "text" }, "source_pages_attempted": { "label": "Source pages attempted", "format": "number" }, "content_type_counts": { "label": "Content type counts", "format": "json" }, "access_state_counts": { "label": "Access state counts", "format": "json" }, "relationship_collection_diagnostic": { "label": "Relationship collection diagnostic", "format": "json" }, "manifest_version": { "label": "Manifest version", "format": "text" }, "requested_output_fields": { "label": "Requested output fields", "format": "json" }, "max_concurrency": { "label": "Max concurrency", "format": "number" }, "navigation_attempts_total": { "label": "Navigation attempts total", "format": "number" }, "navigation_retries_total": { "label": "Navigation retries total", "format": "number" }, "raw_evidence_retention_days": { "label": "Raw retention days", "format": "number" }, "max_raw_evidence_bytes": { "label": "Max raw bytes", "format": "number" }, "redact_sensitive_query_params": { "label": "Sensitive query redaction", "format": "boolean" }, "raw_html_redactions": { "label": "HTML redactions", "format": "json" }, "url_redactions": { "label": "URL redactions", "format": "json" }, "date_interpretations": { "label": "Date interpretations", "format": "json" }, "canonical_url": { "label": "Canonical URL", "format": "link" }, "redirect_chain": { "label": "Redirect chain", "format": "json" }, "answer_count": { "label": "Answer count", "format": "number" }, "scroll_attempts": { "label": "Scroll attempts", "format": "number" }, "scroll_state": { "label": "Scroll state", "format": "text" }, "load_more_attempts": { "label": "Load-more attempts", "format": "number" }, "load_more_clicks": { "label": "Load-more clicks", "format": "number" }, "load_more_state": { "label": "Load-more state", "format": "text" }, "raw_html_redaction_state": { "label": "HTML redaction", "format": "text" }, "url_redaction_state": { "label": "URL redaction", "format": "text" }, "output_format": { "label": "Output format", "format": "text" }, "answers": { "label": "Nested answers", "format": "json" }, "comments": { "label": "Nested comments", "format": "json" }, "nested_answer_count": { "label": "Nested answers emitted", "format": "number" }, "nested_answer_count_observed": { "label": "Nested answers observed", "format": "number" }, "nested_comment_count": { "label": "Nested comments emitted", "format": "number" }, "nested_comment_count_observed": { "label": "Nested comments observed", "format": "number" }, "nested_child_state": { "label": "Nested child state", "format": "text" }, "nested_orphan_reason": { "label": "Nested orphan reason", "format": "text" }, "requested_depth": { "label": "Requested depth", "format": "text" }, "observed_depth": { "label": "Observed depth", "format": "text" }, "detail_expansion_state": { "label": "Detail expansion", "format": "text" }, "title": { "label": "Title", "format": "text" }, "url": { "label": "URL", "format": "link" }, "post_url": { "label": "Post URL", "format": "link" }, "post_title": { "label": "Post title", "format": "text" }, "post_author_name": { "label": "Post author", "format": "text" }, "post_author_url": { "label": "Post author URL", "format": "link" }, "post_author_image_url": { "label": "Post author image", "format": "link" }, "post_author_is_verified": { "label": "Post author verified", "format": "boolean" }, "post_author_is_anonymous": { "label": "Post author anonymous", "format": "boolean" }, "post_media_urls": { "label": "Post media URLs", "format": "json" }, "post_image_urls": { "label": "Post image URLs", "format": "json" }, "post_video_urls": { "label": "Post video URLs", "format": "json" }, "post_outbound_links": { "label": "Post outbound links", "format": "json" }, "question_media_urls": { "label": "Question media URLs", "format": "json" }, "question_author_name": { "label": "Question author", "format": "text" }, "question_author_url": { "label": "Question author URL", "format": "link" }, "question_author_image_url": { "label": "Question author image", "format": "link" }, "question_author_id": { "label": "Question author ID", "format": "text" }, "question_author_is_verified": { "label": "Question author verified", "format": "boolean" }, "question_author_is_anonymous": { "label": "Question author anonymous", "format": "boolean" }, "question_author_credentials": { "label": "Question author credentials", "format": "text" }, "question_image_urls": { "label": "Question image URLs", "format": "json" }, "question_video_urls": { "label": "Question video URLs", "format": "json" }, "question_outbound_links": { "label": "Question outbound links", "format": "json" }, "post_author_id": { "label": "Post author ID", "format": "text" }, "post_author_credentials": { "label": "Post author credentials", "format": "text" }, "post_body": { "label": "Post body", "format": "text" }, "post_created_at": { "label": "Post created at", "format": "text" }, "post_updated_at": { "label": "Post updated at", "format": "text" }, "post_updated_age_days": { "label": "Post updated age (days)", "format": "number" }, "post_updated_age_state": { "label": "Post updated age evidence", "format": "text" }, "post_age_days": { "label": "Post age (days)", "format": "number" }, "post_age_state": { "label": "Post age evidence", "format": "text" }, "relationship": { "label": "Relationship", "format": "text" }, "edge_id": { "label": "Edge ID", "format": "text" }, "from_url": { "label": "From URL", "format": "link" }, "to_url": { "label": "To URL", "format": "link" }, "record_id": { "label": "Record ID", "format": "text" }, "access_state": { "label": "Access", "format": "text" }, "from_record_id": { "label": "From record", "format": "text" }, "to_record_id": { "label": "To record", "format": "text" }, "from_id": { "label": "From ID", "format": "text" }, "to_id": { "label": "To ID", "format": "text" }, "to_name": { "label": "To name", "format": "text" }, "to_image_url": { "label": "To image", "format": "link" }, "node_image_url": { "label": "Node image", "format": "link" }, "relationship_collection_key": { "label": "Relationship collection", "format": "text" }, "collection_total_text": { "label": "Collection total", "format": "text" }, "collection_total_value": { "label": "Collection total (value)", "format": "number" }, "edge_evidence_field": { "label": "Edge evidence", "format": "text" }, "unresolved_reason": { "label": "Unresolved reason", "format": "text" }, "source_query": { "label": "Source query", "format": "text" }, "source_queries": { "label": "Source queries", "format": "json" }, "matched_input": { "label": "Matched input", "format": "text" }, "matched_input_kind": { "label": "Matched input kind", "format": "text" }, "source_observations": { "label": "Source observations", "format": "json" }, "source_observation_count": { "label": "Source observation count", "format": "number" }, "question_url": { "label": "Question URL", "format": "link" }, "question_answer_count": { "label": "Answers (raw)", "format": "text" }, "question_answer_count_value": { "label": "Answers", "format": "number" }, "question_answer_count_scraped": { "label": "Answers scraped", "format": "number" }, "question_id": { "label": "Question ID", "format": "text" }, "question_created_at": { "label": "Question created", "format": "text" }, "question_view_count": { "label": "Question views", "format": "number" }, "question_audit_state": { "label": "Question audit state", "format": "text" }, "question_merge_count": { "label": "Question merges into", "format": "number" }, "question_age_days": { "label": "Question age (days)", "format": "number" }, "question_age_state": { "label": "Question age evidence", "format": "text" }, "question_updated_at": { "label": "Question updated", "format": "text" }, "last_answered_at": { "label": "Last answered (observed)", "format": "date" }, "last_answered_at_evidence": { "label": "Last answered evidence", "format": "json" }, "answer_id": { "label": "Answer ID", "format": "text" }, "answer_node_id": { "label": "Answer node ID", "format": "text" }, "answer_url": { "label": "Answer URL", "format": "link" }, "answer_text": { "label": "Answer", "format": "text" }, "answer_html": { "label": "Answer HTML", "format": "text" }, "answer_media_urls": { "label": "Answer media URLs", "format": "json" }, "answer_image_urls": { "label": "Answer image URLs", "format": "json" }, "answer_video_urls": { "label": "Answer video URLs", "format": "json" }, "answer_outbound_links": { "label": "Answer outbound links", "format": "json" }, "answer_translation_state": { "label": "Answer translation state", "format": "text" }, "answer_translation_label": { "label": "Answer translation label", "format": "text" }, "answer_original_url": { "label": "Answer original URL", "format": "link" }, "answer_is_anonymous": { "label": "Answer is anonymous", "format": "boolean" }, "answer_author_is_verified": { "label": "Answer author verified", "format": "boolean" }, "answer_updated_at": { "label": "Answer updated at", "format": "text" }, "answer_created_at": { "label": "Answer created at", "format": "text" }, "answer_age_days": { "label": "Answer age (days)", "format": "number" }, "answer_age_state": { "label": "Answer age evidence", "format": "text" }, "answer_visibility": { "label": "Answer visibility", "format": "text" }, "answer_text_completeness": { "label": "Answer text completeness", "format": "text" }, "answer_is_collapsed": { "label": "Answer is collapsed", "format": "boolean" }, "answer_is_quora_plus": { "label": "Answer is Quora+", "format": "boolean" }, "answer_is_top_labeled": { "label": "Answer has top label", "format": "boolean" }, "answer_rank_source": { "label": "Answer rank source", "format": "text" }, "answer_upvote_count": { "label": "Answer upvotes", "format": "text" }, "answer_upvote_count_value": { "label": "Answer upvotes (number)", "format": "number" }, "answer_comment_count": { "label": "Answer comments", "format": "text" }, "answer_comment_count_value": { "label": "Answer comments (number)", "format": "number" }, "answer_view_count": { "label": "Answer views", "format": "text" }, "answer_view_count_value": { "label": "Answer views (number)", "format": "number" }, "answer_share_count": { "label": "Answer shares", "format": "text" }, "answer_share_count_value": { "label": "Answer shares (number)", "format": "number" }, "reaction_breakdown": { "label": "Answer reaction breakdown", "format": "json" }, "is_ai_answer": { "label": "Is AI answer", "format": "boolean" }, "ai_label_text": { "label": "AI label text", "format": "text" }, "ai_label_source": { "label": "AI label source", "format": "text" }, "related_content": { "label": "Related content", "format": "json" }, "related_content_count": { "label": "Related content count", "format": "number" }, "related_content_observed_count": { "label": "Related content observed", "format": "number" }, "related_content_limit_reached": { "label": "Related content cap", "format": "boolean" }, "answer_jsonld_type": { "label": "Answer JSON-LD type", "format": "text" }, "answer_rank": { "label": "Answer rank", "format": "number" }, "answer_limit_reached": { "label": "Answer cap", "format": "boolean" }, "comment_id": { "label": "Comment ID", "format": "text" }, "comment_url": { "label": "Comment URL", "format": "link" }, "comment_text": { "label": "Comment", "format": "text" }, "comment_author_name": { "label": "Comment author", "format": "text" }, "comment_author_image_url": { "label": "Comment author image", "format": "link" }, "comment_author_id": { "label": "Comment author ID", "format": "text" }, "comment_author_credentials": { "label": "Comment author credentials", "format": "text" }, "comment_author_is_verified": { "label": "Comment author verified", "format": "boolean" }, "comment_is_anonymous": { "label": "Anonymous author", "format": "boolean" }, "comment_timestamp": { "label": "Comment timestamp", "format": "text" }, "comment_created_at": { "label": "Comment created", "format": "text" }, "comment_age_days": { "label": "Comment age (days)", "format": "number" }, "comment_age_state": { "label": "Comment age evidence", "format": "text" }, "comment_visibility": { "label": "Comment visibility", "format": "text" }, "comment_upvote_count": { "label": "Comment upvotes", "format": "text" }, "comment_depth": { "label": "Comment depth", "format": "number" }, "comment_depth_limit_reached": { "label": "Comment depth cap reached", "format": "boolean" }, "comment_items_observed_count": { "label": "Comments observed", "format": "number" }, "comment_items_emitted_count": { "label": "Comments emitted", "format": "number" }, "comment_limit_reached": { "label": "Comment cap", "format": "boolean" }, "comment_media_urls": { "label": "Comment media", "format": "json" }, "comment_image_urls": { "label": "Comment image URLs", "format": "json" }, "comment_video_urls": { "label": "Comment video URLs", "format": "json" }, "comment_outbound_links": { "label": "Comment outbound links", "format": "json" }, "comment_collection_label": { "label": "Comment collection", "format": "text" }, "comment_is_top_labeled": { "label": "Top-labeled comment", "format": "boolean" }, "comment_filter_top_only": { "label": "Top comments only", "format": "boolean" }, "comment_filter_observed": { "label": "Comment filter observed", "format": "number" }, "comment_filter_emitted": { "label": "Comment filter emitted", "format": "number" }, "comment_filter_unknown": { "label": "Comment filter unknown", "format": "number" }, "comment_rank": { "label": "Comment rank", "format": "number" }, "comment_rank_source": { "label": "Comment rank source", "format": "text" }, "comment_sort_order": { "label": "Comment sort", "format": "text" }, "comment_sort_observed": { "label": "Comments observed", "format": "number" }, "comment_sort_fallback_count": { "label": "Comment sort fallback", "format": "number" }, "comment_reaction_count": { "label": "Comment reactions", "format": "text" }, "comment_reaction_count_value": { "label": "Comment reactions (typed)", "format": "number" }, "comment_reply_count": { "label": "Comment replies", "format": "text" }, "comment_reply_path": { "label": "Reply path", "format": "json" }, "parent_comment_id": { "label": "Parent comment ID", "format": "text" }, "parent_comment_url": { "label": "Parent comment URL", "format": "link" }, "comment_is_reply": { "label": "Comment is reply", "format": "boolean" }, "comment_reaction_breakdown": { "label": "Comment reactions", "format": "json" }, "comment_upvote_count_value": { "label": "Comment upvotes", "format": "number" }, "comment_reply_count_value": { "label": "Comment replies", "format": "number" }, "profile_url": { "label": "Profile URL", "format": "link" }, "profile_name": { "label": "Profile name", "format": "text" }, "profile_bio": { "label": "Profile bio", "format": "text" }, "profile_image_url": { "label": "Profile image", "format": "link" }, "profile_jsonld_type": { "label": "Profile JSON-LD type", "format": "text" }, "profile_author_id": { "label": "Profile author ID", "format": "text" }, "profile_is_verified": { "label": "Profile verified", "format": "boolean" }, "profile_is_restricted": { "label": "Profile restricted", "format": "boolean" }, "profile_snapshot_requested": { "label": "Profile snapshot requested", "format": "boolean" }, "topic_url": { "label": "Topic URL", "format": "link" }, "space_url": { "label": "Space URL", "format": "link" }, "feed_url": { "label": "Feed URL", "format": "link" }, "feed_type": { "label": "Feed type", "format": "text" }, "feed_title": { "label": "Feed title", "format": "text" }, "feed_text": { "label": "Feed text", "format": "text" }, "feed_author_name": { "label": "Feed author", "format": "text" }, "feed_author_url": { "label": "Feed author URL", "format": "link" }, "feed_author_image_url": { "label": "Feed author image", "format": "link" }, "feed_author_id": { "label": "Feed author ID", "format": "text" }, "feed_author_credentials": { "label": "Feed author credentials", "format": "text" }, "feed_author_is_verified": { "label": "Feed author verified", "format": "boolean" }, "feed_author_is_anonymous": { "label": "Feed author anonymous", "format": "boolean" }, "feed_created_at": { "label": "Feed created at", "format": "text" }, "feed_age_days": { "label": "Feed age (days)", "format": "number" }, "feed_age_state": { "label": "Feed age evidence", "format": "text" }, "media_urls": { "label": "Feed media URLs", "format": "array" }, "image_urls": { "label": "Feed image URLs", "format": "array" }, "video_urls": { "label": "Feed video URLs", "format": "array" }, "outbound_links": { "label": "Feed outbound links", "format": "array" }, "activity_url": { "label": "Activity URL", "format": "link" }, "activity_source": { "label": "Activity source", "format": "text" }, "activity_question_url": { "label": "Activity question URL", "format": "link" }, "activity_question_title": { "label": "Activity question title", "format": "text" }, "activity_question_id": { "label": "Activity question ID", "format": "text" }, "activity_answer_id": { "label": "Activity answer ID", "format": "text" }, "author_name": { "label": "Author name", "format": "text" }, "author_url": { "label": "Author URL", "format": "link" }, "author_image_url": { "label": "Author image", "format": "link" }, "author_id": { "label": "Author ID", "format": "text" }, "author_credentials": { "label": "Author credentials", "format": "text" }, "topics": { "label": "Topics", "format": "json" }, "topic_links": { "label": "Topic links", "format": "json" }, "created_at": { "label": "Created", "format": "date" }, "timestamp": { "label": "Timestamp", "format": "text" }, "include_unresolved_edges": { "label": "Unresolved edges included", "format": "boolean" }, "include_field_evidence": { "label": "Field evidence included", "format": "boolean" }, "include_engagement_breakdown": { "label": "Engagement breakdown included", "format": "boolean" }, "include_entity_graph": { "label": "Entity graph included", "format": "boolean" }, "profile_snapshot_state": { "label": "Profile snapshot", "format": "text" }, "global_answer_cap_reached": { "label": "Global answer cap", "format": "boolean" }, "answers_observed_before_global_cap": { "label": "Answers observed", "format": "number" }, "answers_suppressed_by_global_cap": { "label": "Answers suppressed", "format": "number" }, "dedupe_mode": { "label": "Dedupe mode", "format": "text" }, "duplicate_records_suppressed": { "label": "Duplicates suppressed", "format": "number" }, "raw_html_bytes": { "label": "Raw HTML bytes", "format": "number" }, "raw_html_returned_bytes": { "label": "Returned HTML bytes", "format": "number" }, "raw_html_truncated": { "label": "Raw HTML truncated", "format": "boolean" }, "raw_evidence_state": { "label": "Raw evidence", "format": "text" }, "raw_html_sha256": { "label": "HTML SHA-256", "format": "text" }, "raw_html": { "label": "HTML snapshot", "format": "text" }, "output_projection": { "label": "Projection", "format": "text" }, "max_items_per_source": { "label": "Configured source cap", "format": "number" }, "source_cap": { "label": "Source cap", "format": "number" }, "source_items_observed": { "label": "Source observed", "format": "number" }, "source_items_emitted": { "label": "Source emitted", "format": "number" }, "source_cap_reached": { "label": "Source cap reached", "format": "boolean" }, "source_url": { "label": "Source url", "format": "link" }, "from_content_type": { "label": "From content type", "format": "text" }, "to_content_type": { "label": "To content type", "format": "text" }, "edge_state": { "label": "Edge state", "format": "text" }, "requested_language": { "label": "Requested language", "format": "text" }, "max_answers_per_question": { "label": "Max answers per question", "format": "number" }, "max_answers_total": { "label": "Max answers total", "format": "number" }, "recordType": { "label": "Record type alias", "format": "text" }, "scrapedAt": { "label": "Scraped at alias", "format": "text" }, "sourceUrl": { "label": "Source URL alias", "format": "text" }, "question_follower_count": { "label": "Question followers", "format": "text" }, "question_follower_count_value": { "label": "Question followers (number)", "format": "text" }, "related_questions": { "label": "Related questions", "format": "json" }, "answer_author_follower_count": { "label": "Answer author followers", "format": "text" }, "answer_access_option": { "label": "Answer effective access", "format": "text" }, "answer_effective_access": { "label": "Answer effective access (alias)", "format": "text" }, "answer_original_question_url": { "label": "Original question URL", "format": "text" }, "answer_original_question_title": { "label": "Original question title", "format": "text" }, "profile_follower_count": { "label": "Profile followers", "format": "text" }, "profile_following_count": { "label": "Profile following", "format": "text" }, "profile_answer_count": { "label": "Profile answers", "format": "text" }, "profile_question_count": { "label": "Profile questions", "format": "text" }, "profile_post_count": { "label": "Profile posts", "format": "text" }, "profile_total_content_views": { "label": "Profile total views", "format": "text" }, "profile_month_content_views": { "label": "Profile monthly views", "format": "text" }, "profile_joined_at": { "label": "Profile joined", "format": "text" }, "profile_credential": { "label": "Profile credential", "format": "text" }, "profile_work_credentials": { "label": "Work credentials", "format": "json" }, "profile_school_credentials": { "label": "School credentials", "format": "json" }, "profile_location_credentials": { "label": "Location credentials", "format": "json" }, "profile_expertise_topics": { "label": "Expertise topics", "format": "json" }, "profile_account_status": { "label": "Profile account status", "format": "text" }, "profile_is_anonymous": { "label": "Profile anonymous", "format": "text" }, "profile_is_deceased": { "label": "Profile deceased", "format": "text" }, "profile_history_limited": { "label": "Profile history limited", "format": "text" }, "profile_history_state": { "label": "Profile history state", "format": "text" }, "topic_id": { "label": "Topic ID", "format": "text" }, "topic_name": { "label": "Topic name", "format": "text" }, "topic_follower_count": { "label": "Topic followers", "format": "text" }, "topic_most_viewed_authors": { "label": "Topic most-viewed authors", "format": "json" }, "topic_photo_url": { "label": "Topic photo", "format": "text" }, "topic_default_photo_url": { "label": "Topic default photo", "format": "text" }, "topic_has_leaderboard": { "label": "Topic leaderboard", "format": "text" }, "topic_feed_state": { "label": "Topic feed state", "format": "text" }, "space_id": { "label": "Space ID", "format": "text" }, "space_name": { "label": "Space name", "format": "text" }, "space_follower_count": { "label": "Space followers", "format": "text" }, "space_all_time_followers": { "label": "Space all-time followers", "format": "text" }, "space_member_count": { "label": "Space members", "format": "text" }, "space_contributor_count": { "label": "Space contributors", "format": "text" }, "space_moderator_count": { "label": "Space moderators", "format": "text" }, "space_admin_count": { "label": "Space admins", "format": "text" }, "space_description": { "label": "Space description", "format": "text" }, "space_icon_url": { "label": "Space icon", "format": "text" }, "space_cover_url": { "label": "Space cover", "format": "text" }, "space_item_count": { "label": "Space items", "format": "text" }, "space_feed_capped": { "label": "Space feed capped", "format": "text" }, "space_ads_skipped": { "label": "Space ads skipped", "format": "text" }, "feed_upvote_count": { "label": "Feed upvotes", "format": "text" }, "feed_view_count": { "label": "Feed views", "format": "text" }, "feed_share_count": { "label": "Feed shares", "format": "text" }, "feed_comment_count": { "label": "Feed comments", "format": "text" }, "feed_effective_access": { "label": "Feed effective access", "format": "text" }, "feed_is_ai_answer": { "label": "Feed AI answer", "format": "text" }, "feed_question_url": { "label": "Feed question URL", "format": "text" }, "feed_question_title": { "label": "Feed question title", "format": "text" }, "post_upvote_count": { "label": "Post upvotes", "format": "text" }, "post_view_count": { "label": "Post views", "format": "text" }, "post_share_count": { "label": "Post shares", "format": "text" }, "post_comment_count": { "label": "Post comments", "format": "text" }, "post_effective_access": { "label": "Post effective access", "format": "text" }, "post_is_question_summary": { "label": "Post is question summary", "format": "text" }, "post_author_follower_count": { "label": "Post author followers", "format": "text" }, "post_question_url": { "label": "Post question URL", "format": "text" }, "post_question_title": { "label": "Post question title", "format": "text" }, "comment_source": { "label": "Comment source", "format": "text" }, "comment_page_limited": { "label": "Comment page limited", "format": "text" }, "comment_container_id": { "label": "Comment container ID", "format": "text" }, "proxy_path_used": { "label": "Proxy path", "format": "text" }, "search_discovery_source": { "label": "Search discovery source", "format": "text" }, "search_discovery_hits": { "label": "Search discovery hits", "format": "text" }, "answer_gql_pages": { "label": "Answer GraphQL pages", "format": "text" }, "comment_gql_pages": { "label": "Comment GraphQL pages", "format": "text" }, "topic_feed_pages": { "label": "Topic feed pages", "format": "text" }, "space_feed_bundles": { "label": "Space feed bundles", "format": "text" }, "quora_plus_preview_count": { "label": "Quora+ previews", "format": "text" }, "comment_cap_hit_count": { "label": "Comment cap hits", "format": "text" }, "topic_feed_cap_hit_count": { "label": "Topic feed cap hits", "format": "text" }, "profile_history_pages": { "label": "Profile history pages", "format": "number" }, "relationship_identity_pages": { "label": "Identity list pages", "format": "number" }, "relationship_identity_requests": { "label": "Identity list requests", "format": "number" }, "question_audit_attempts": { "label": "Question audit attempts", "format": "number" }, "answer_pagination_state": { "label": "Answer pagination state", "format": "text" }, "answer_pagination_unrelated_suppressed": { "label": "Unrelated paginated answers suppressed", "format": "number" }, "relationship_identity_states": { "label": "Relationship identity states", "format": "json" }, "gql_calls": { "label": "GraphQL calls", "format": "json" }, "query_hashes": { "label": "Query hashes", "format": "json" }, "legacy_input_notes": { "label": "Legacy input notes", "format": "text" }, "hard_limits": { "label": "Hard limits", "format": "json" }, "proxy_errors": { "label": "Proxy errors", "format": "json" } } } } } } } }, "buildNumber": "1.0.2", "imageDigest": "38a27bd31f46fadd50a72e60389228288f293b1183066abe334ed82372092b48", "actVersion": { "sourceType": "SOURCE_FILES", "buildTag": "latest", "versionNumber": "1.0" }, "usage": { "ACTOR_COMPUTE_UNITS": 0.04058777777777778 } } }