{ "openapi": "3.0.1", "info": { "title": "Thesis Literature Review Scraper", "description": "Turn any research question into a clean reading list of peer-reviewed academic papers from OpenAlex, Semantic Scholar, and Crossref in one run. Includes citation-manager and spreadsheet exports, plus LLM-ready Markdown you can paste into ChatGPT or Claude for instant literature synthesis.", "version": "0.1", "x-build-id": "BhYpur6Yhdz2Wh0DD" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/leafy-dev-jr~thesis-literature-review-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-leafy-dev-jr-thesis-literature-review-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/leafy-dev-jr~thesis-literature-review-scraper/runs": { "post": { "operationId": "runs-sync-leafy-dev-jr-thesis-literature-review-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/leafy-dev-jr~thesis-literature-review-scraper/run-sync": { "post": { "operationId": "run-sync-leafy-dev-jr-thesis-literature-review-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "query" ], "properties": { "query": { "title": "Research question or keywords", "minLength": 3, "maxLength": 500, "type": "string", "description": "Your research question or topic keywords (e.g., 'impact of social media on adolescent mental health')." }, "yearFrom": { "title": "Earliest publication year", "minimum": 1900, "maximum": 2100, "type": "integer", "description": "Only include papers published in or after this year.", "default": 2015 }, "yearTo": { "title": "Latest publication year", "minimum": 1900, "maximum": 2100, "type": "integer", "description": "Only include papers published in or before this year.", "default": 2026 }, "maxResults": { "title": "Max papers to return", "minimum": 10, "maximum": 1000, "type": "integer", "description": "Total de-duplicated papers across all sources (10–1000). Larger runs take longer and cost more — start with 100 to validate the query.", "default": 100 }, "sources": { "title": "Sources to query", "uniqueItems": true, "type": "array", "description": "Which free scholarly APIs to aggregate. Results are deduplicated by DOI (with fuzzy-title fallback) and field-merged across sources. ⚠️ Adding Semantic Scholar can make runs noticeably longer — its anonymous rate-limit pool is strict (1 req/sec + frequent 429s). Enable it only if you need its abstracts/influentialCitationCount, or supply a free Semantic Scholar API key below to bypass the shared pool.", "items": { "type": "string", "enum": [ "openalex", "semanticscholar", "crossref" ], "enumTitles": [ "OpenAlex (250M+ works)", "Semantic Scholar (~200M papers — slower, rate-limited)", "Crossref (160M+ records)" ] }, "default": [ "openalex", "crossref" ] }, "minCitations": { "title": "Minimum citation count (0 = no filter)", "minimum": 0, "type": "integer", "description": "Drop papers with fewer citations than this. Set to 0 to keep all.", "default": 0 }, "openAccessOnly": { "title": "Only papers with open access", "type": "boolean", "description": "When true, only include papers with a free open-access PDF link.", "default": false }, "sortBy": { "title": "Sort results by", "enum": [ "relevance", "citations", "date" ], "type": "string", "description": "Ranking order for the final deduped list.", "default": "relevance" }, "outputFormat": { "title": "Additional output formats", "type": "array", "description": "JSON dataset is always produced. These are additional exports written to the run's Key-Value Store.", "items": { "type": "string", "enum": [ "bibtex", "ris", "markdown", "csv" ] }, "default": [ "bibtex", "markdown" ] }, "contactEmail": { "title": "Your email (optional — enables polite-pool API access)", "type": "string", "description": "Optional. When provided, we include it in OpenAlex and Crossref requests so you get priority routing and higher rate limits. Leave blank to run anonymously. Never stored, never shared." }, "semanticScholarApiKey": { "title": "Semantic Scholar API key (optional)", "type": "string", "description": "Optional. Semantic Scholar's anonymous pool is heavily rate-limited. If you have a free API key from https://www.semanticscholar.org/product/api#api-key-form, paste it here to bypass the shared pool. Leave blank to run without it." } } }, "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 } } } } } } } } } }