{ "openapi": "3.0.1", "info": { "title": "Archive.org Subtitle & Transcript Scraper — TXT, SRT & VTT", "description": "Download captions from any Archive.org film, TV, or audio item: clean transcript text, timestamped cues, normalized SRT & VTT, one row per language. Search 3M+ captioned items, monitor for new ones. No login or API key. $2 per 1,000 transcripts.", "version": "0.1", "x-build-id": "olUgmZDLEdrTgJ6MT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapersdelight~archive-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapersdelight-archive-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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~archive-transcript-scraper/runs": { "post": { "operationId": "runs-sync-scrapersdelight-archive-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~archive-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-scrapersdelight-archive-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": { "itemUrls": { "title": "Item URLs / identifiers", "type": "array", "description": "Archive.org items to transcribe — full https://archive.org/details/{identifier} URLs or bare identifiers (e.g. his_girl_friday).", "items": { "type": "string" } }, "searchQuery": { "title": "Search query (optional)", "type": "string", "description": "Archive.org advanced-search (Lucene) query to discover captioned items, e.g. `collection:prelinger`, `title:(news) AND year:[1950 TO 1960]`, or plain keywords. The actor automatically scopes it to movies/audio with .srt/.vtt captions and excludes access-restricted items, then sorts by downloads. Leave empty to use Item URLs only." }, "languages": { "title": "Caption languages", "type": "array", "description": "Keep only caption files in these language codes (from the filename suffix, e.g. en, es, ru; archive's autogenerated .asr captions count as en). Empty = all languages.", "items": { "type": "string" } }, "includeAutoGenerated": { "title": "Include autogenerated (.asr) captions", "type": "boolean", "description": "Archive.org auto-transcribes many films (English ASR, .asr.srt/.asr.vtt). Disable to keep only human-uploaded subtitle files.", "default": true }, "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 cues (array)", "Normalized SRT", "Normalized VTT" ] }, "default": [ "txt" ] }, "maxItems": { "title": "Max items per run", "minimum": 0, "type": "integer", "description": "Hard cap on archive.org items this run (0 = unlimited; search mode is window-capped at 10,000 by archive.org).", "default": 5 }, "maxCaptionFilesPerItem": { "title": "Max caption files per item", "minimum": 0, "type": "integer", "description": "Some items carry dozens of subtitle files (one per language). Cap how many are downloaded per item (0 = all).", "default": 5 }, "monitorMode": { "title": "Monitor mode (new-item watcher)", "type": "boolean", "description": "Recurring watcher: diff against the prior run's seen items (per search query) and output/alert ONLY new items. Pair with a searchQuery + an Apify Schedule.", "default": false }, "alertOnNewItem": { "title": "Alert on new items", "type": "boolean", "description": "In monitor mode, deliver an alert for each new item via the channels below.", "default": true }, "webhookUrl": { "title": "Webhook URL", "type": "string", "description": "POST endpoint for new-item 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-item digest (via apify/send-mail).", "items": { "type": "string" } }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Proxy settings. Archive.org is a public API — datacenter rotation is plenty.", "default": { "useApifyProxy": true } }, "requestConcurrency": { "title": "Request concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Max parallel item fetches. Keep modest — archive.org asks for polite crawling.", "default": 5 }, "diagnose": { "title": "Diagnostic mode (dev)", "type": "boolean", "description": "Dev only. Dumps the raw item metadata JSON + logs caption-file picks and a parsed sample, 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 } } } } } } } } } }