{ "openapi": "3.0.1", "info": { "title": "Coursera Transcript Scraper — Lecture Subtitles", "description": "Extract Coursera lecture transcripts from the course's own subtitle tracks — no login, no ASR. By course slug, returns each open lecture's transcript as text, timestamped segments, and SRT/VTT, in any of 30+ available languages. Gated lectures are flagged, not faked.", "version": "0.1", "x-build-id": "FlNlo58CeJWIvjWjj" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapersdelight~coursera-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapersdelight-coursera-transcript-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapersdelight~coursera-transcript-scraper/runs": { "post": { "operationId": "runs-sync-scrapersdelight-coursera-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapersdelight~coursera-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-scrapersdelight-coursera-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "courseSlugs": { "title": "Course slugs / URLs", "type": "array", "description": "Coursera courses to transcribe — slugs (e.g. machine-learning) or full https://www.coursera.org/learn/{slug} URLs.", "items": { "type": "string" } }, "language": { "title": "Subtitle language", "type": "string", "description": "Preferred subtitle language code (e.g. en, es, fr, zh-CN). Falls back to the first available language for the lecture. Many courses offer 30+ languages.", "default": "en" }, "transcriptFormats": { "title": "Transcript formats", "type": "array", "description": "Which transcript representations to include. Plain text is always included.", "items": { "type": "string", "enum": [ "txt", "segments", "srt", "vtt" ], "enumTitles": [ "Plain text", "Timestamped segments (array)", "SRT subtitles", "VTT subtitles" ] }, "default": [ "txt" ] }, "maxLecturesPerCourse": { "title": "Max lectures per course", "minimum": 0, "type": "integer", "description": "Hard cap on lectures per course (0 = all).", "default": 0 }, "includeLocked": { "title": "Include locked lectures", "type": "boolean", "description": "Also emit a row for enrollment-gated lectures (with needs_auth=true and no transcript) so you can see the full course outline.", "default": false }, "monitorMode": { "title": "Monitor mode (new-lecture watcher)", "type": "boolean", "description": "Recurring watcher: diff against the prior run's seen lectures (per course set) and output/alert ONLY new lectures. Pair with an Apify Schedule.", "default": false }, "alertOnNewLecture": { "title": "Alert on new lectures", "type": "boolean", "description": "In monitor mode, deliver an alert for each new lecture via the channels below.", "default": true }, "webhookUrl": { "title": "Webhook URL", "type": "string", "description": "POST endpoint for new-lecture alert payloads." }, "slackWebhookUrl": { "title": "Slack webhook URL", "type": "string", "description": "Slack incoming-webhook URL for formatted cards." }, "emailRecipients": { "title": "Email recipients", "type": "array", "description": "Emails for the new-lecture digest (via apify/send-mail).", "items": { "type": "string" } }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Proxy settings. Datacenter rotation is plenty.", "default": { "useApifyProxy": true } }, "requestConcurrency": { "title": "Request concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Max parallel lecture fetches.", "default": 5 }, "diagnose": { "title": "Diagnostic mode (dev)", "type": "boolean", "description": "Dev only. Logs the resolved course + first lecture's subtitle languages + parsed cues, then exits.", "default": false } } }, "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 } } } } } } } } } }