{ "openapi": "3.0.1", "info": { "title": "Lexonia Video Intel — Video Research & Creator Discovery", "description": "Find & rank the top creators on any topic across YouTube and China's Bilibili (B站) & Douyin (抖音) — then read what they say, in English. Get a ranked shortlist + contacts, ready to transcribe. For market research, influencer & opinion-leader discovery. Works in Claude & ChatGPT via Apify MCP.", "version": "0.0", "x-build-id": "udbO7WO9qWbg5GKoH" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lexonia~lexonia-video-intel/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lexonia-lexonia-video-intel", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lexonia~lexonia-video-intel/runs": { "post": { "operationId": "runs-sync-lexonia-lexonia-video-intel", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lexonia~lexonia-video-intel/run-sync": { "post": { "operationId": "run-sync-lexonia-lexonia-video-intel", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "topic", "platforms", "keywordSetA", "keywordSetB" ], "properties": { "estimateOnly": { "title": "Estimate only — preview cost, don't run", "type": "boolean", "description": "ON (default): the Actor calculates the expected cost range and time, saves ONE 'estimate' record, and exits in seconds — nothing is searched or charged. Review the cost, then set this OFF to fetch real results. NOTE FOR AI ASSISTANTS (Claude/ChatGPT via MCP): ALWAYS run this Actor with estimateOnly=true FIRST, show the user the returned estimatedCostUsd range, and only run again with estimateOnly=false after the user approves — so they never run over budget.", "default": true }, "focus": { "title": "Focus — what are you optimizing for?", "enum": [ "content", "audience" ], "type": "string", "description": "'Content' (default) ranks by topical relevance — best for research and 'what are they saying'. 'Audience' ranks creators as PARTNERSHIP targets — a big, ENGAGED, on-topic, reachable audience (reach + engagement lead; contacts prioritized) — best for sponsorships & creator agreements.", "default": "content" }, "topic": { "title": "Topic / niche", "type": "string", "description": "Plain-English description of the creators you want to find (e.g. 'US owner-operator trucking', 'home espresso reviewers', 'China EV unboxers'). Used to guide content-relevance scoring." }, "keywordSetA": { "title": "Keyword set A — SUBJECT (required)", "type": "array", "description": "Facet 1 of 3 — WHAT the content is about. Put each phrase as its OWN entry (click + Add). Entries in a set are SYNONYMS — a video needs just ONE of them (Set A = 'owner operator' OR 'OTR' OR 'over the road'). The rule across sets is AND: a result must match Set A AND Set B (AND Set C). ▶ Example: Set A = owner operator | OTR | over the road.", "items": { "type": "string" } }, "keywordSetB": { "title": "Keyword set B — ANGLE (required)", "type": "array", "description": "Facet 2 of 3 — the ANGLE / kind of content. Each phrase its own entry; entries are SYNONYMS (any ONE counts). A result must contain a Set A term AND a Set B term. ▶ Example: Set B = dispatch | load board | business → so 'owner operator' AND 'dispatch' must both appear.", "items": { "type": "string" } }, "keywordSetC": { "title": "Keyword set C — REFINE (optional)", "type": "array", "description": "Facet 3 of 3 — an OPTIONAL extra requirement. Each phrase its own entry; any ONE counts. If filled, a result must ALSO contain one of these (A AND B AND C). Leave empty for A AND B only. ▶ Example: Set C = beginner | profit → keeps only beginner/profit-focused owner-operator-dispatch videos.", "default": [], "items": { "type": "string" } }, "platforms": { "title": "Platforms to search", "type": "array", "description": "Which platforms to search: YouTube (Western) and China's Bilibili & Douyin. Discovered videos hand straight over to the Lexonia Video Scrape transcriber.", "items": { "type": "string", "enum": [ "youtube", "bilibili", "douyin" ], "enumTitles": [ "YouTube", "Bilibili (B站)", "Douyin (抖音)" ] }, "default": [ "youtube" ] }, "marketLanguage": { "title": "Search language (market)", "enum": [ "auto", "en", "zh", "es", "ja", "ko", "pt", "ru", "fr", "de", "ar", "hi", "id", "vi" ], "type": "string", "description": "The language to actually search in. Keywords are rendered into this language so the search hits the target market's local content — e.g. Chinese for Bilibili/Douyin. 'auto' picks the natural language of each selected platform's market.", "default": "auto" }, "channelUrls": { "title": "Search within specific channels (optional)", "type": "array", "description": "Optional. Paste channel/creator URLs (YouTube, Bilibili space, or Douyin user) to search WITHIN those channels instead of discovering across a platform — e.g. pull only the cold-calling videos on one creator's channel, or across a list of creators. Leave empty for normal topic discovery. The A AND B AND C match still applies.", "default": [], "items": { "type": "string" } }, "outputLevel": { "title": "Return channels or videos (Content focus)", "enum": [ "channels", "videos" ], "type": "string", "description": "CONTENT FOCUS. 'Channels' (default) = a ranked shortlist of CREATORS (ranked on key-phrase match + recency + consistency + reach). 'Videos' = the individual matching CLIPS (ranked on key-phrase match + recency + views — same key phrases, minus the per-creator consistency). In AUDIENCE focus this is ignored — you always get creators.", "default": "channels" }, "maxChannels": { "title": "Max channels returned (Top-N shortlist)", "type": "integer", "description": "The curated shortlist — the top-N ranked creators the engine refines the whole search down to (e.g. top 50 out of thousands scanned). Lower = tighter & cheaper; higher = broader. Set 0 to return all.", "default": 50 }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Files to save. The dataset always holds the full person-centric records. CSV & Markdown carry the full dossier (reach, engagement, contacts incl. WeChat, cross-platform presence).", "items": { "type": "string", "enum": [ "json", "csv", "markdown" ], "enumTitles": [ "JSON", "CSV (spreadsheet)", "Markdown" ] }, "default": [ "json", "csv" ] }, "minFollowers": { "title": "Minimum followers / subscribers", "type": "integer", "description": "Drop channels below this subscriber count. Channels with unknown counts (e.g. some China creators) are kept.", "default": 5000 }, "minViews": { "title": "Minimum views (best video)", "type": "integer", "description": "Drop channels whose best on-topic video has fewer than this many views. Leave 0 for no view filter.", "default": 0 }, "excludeKeywords": { "title": "Exclude keywords", "type": "array", "description": "Hard-drop creators whose content matches these (e.g. 'box truck', 'hotshot').", "default": [], "items": { "type": "string" } }, "includePopularityInRanking": { "title": "Factor popularity into the ranking (Content focus)", "type": "boolean", "description": "Content focus only. OFF (default): ranking is purely topical, so a small focused channel can outrank a big generic one. ON: also weight audience size. (In Audience focus, reach is already a lead factor, so this is not needed.)", "default": false }, "requireContact": { "title": "Audience mode: drop creators with no contact", "type": "boolean", "description": "Audience focus only. ON (default): a creator we can't reach (no email, WeChat/QQ/Weibo, website, or social) is nixed — you can't sign a partner you can't contact. Turn OFF to keep uncontactable creators (flagged) — useful for China where contacts are hard and you'll hunt them manually.", "default": true }, "enrichContacts": { "title": "Deep contact enrichment (crawl websites for email/phone)", "type": "boolean", "description": "Optional. Crawl the discovered websites of top channels for emails/phones. Adds time and can pull sponsor/reference contacts, so it's off by default in Content focus (Audience focus runs it automatically).", "default": false }, "enrichGoogleBusiness": { "title": "Google Business Profile lookup (local-business owners)", "type": "boolean", "description": "Optional. For owners that are LOCAL BUSINESSES, look them up on Google Maps to attach phone, address, website, and email. Best for local-business verticals (med spa, salon, dojo…); name→listing matching is fuzzy for pure influencers. No China (Bilibili/Douyin) coverage.", "default": false }, "topNContentDigest": { "title": "Deep read — what your top creators say (Content focus)", "minimum": 0, "maximum": 100, "type": "integer", "description": "CONTENT FOCUS ONLY (ignored in Audience focus — there you want who they REACH, not what they say). For the top N creators, transcribe + summarize their latest video in English so you see what they're actually saying. Transcription cost per video (YouTube ~cents; a 1-hour China video ~a few $). 0 = off.", "default": 0 }, "digestSummaryLanguages": { "title": "Digest summary languages", "type": "array", "description": "If deep read is on, summarize each creator's videos in these languages.", "default": [ "English" ], "items": { "type": "string" } }, "digestTranslateLanguages": { "title": "Digest translate languages", "type": "array", "description": "If deep read is on, also produce a full translation of each creator's recent video in these languages (useful for Bilibili/Douyin creators).", "default": [], "items": { "type": "string" } }, "localizeKeywords": { "title": "Translate keywords to the market language", "type": "boolean", "description": "ON (default): your English/source keywords are translated into the search language above, while non-translatable technical and brand terms are kept as-is (Docker, API, LLM, GitHub, DeepSeek…). OFF: keywords are used exactly as typed (use this if you've already entered them in the target language, or they're pure technical terms).", "default": true }, "preserveTerms": { "title": "Keep these terms untranslated", "type": "array", "description": "Optional. Technical/brand terms to leave in their original form during keyword translation (common ones like API, LLM, Docker are auto-preserved). Add product names or acronyms specific to your topic.", "default": [], "items": { "type": "string" } }, "maxResultsPerKeyword": { "title": "Max results per keyword", "minimum": 10, "maximum": 500, "type": "integer", "description": "How many raw results to pull per keyword/phrase before filtering. Higher = wider net + more coverage, but more scraping cost. Lower = leaner & cheaper.", "default": 50 }, "maxSubActorSpendUsd": { "title": "Max sub-actor spend per run (cost guard)", "type": "number", "description": "Optional safety cap in USD (decimals allowed, e.g. 0.5). If the estimated scraping cost for a run exceeds this, the run stops adding platforms. Leave blank for no cap." } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }