{ "openapi": "3.0.1", "info": { "title": "NCI GDC Cancer Genomics Scraper", "description": "Scrape projects, cases, files, and annotations from the NCI Genomic Data Commons (GDC) public API. Filter by primary site or program (TCGA / CPTAC / TARGET) and get rich summary fields like case_count, file_count, file_size, disease_type and demographics. No API key required.", "version": "0.0", "x-build-id": "bomT6yMWAsG8tAcdu" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/parseforge~nci-gdc-cancer-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-parseforge-nci-gdc-cancer-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/parseforge~nci-gdc-cancer-scraper/runs": { "post": { "operationId": "runs-sync-parseforge-nci-gdc-cancer-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/parseforge~nci-gdc-cancer-scraper/run-sync": { "post": { "operationId": "run-sync-parseforge-nci-gdc-cancer-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "entity": { "title": "Entity", "enum": [ "projects", "cases", "files", "annotations" ], "type": "string", "description": "Which GDC public endpoint to scrape.", "default": "projects" }, "maxItems": { "title": "Max Items", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Free users: Limited to 10 items (preview). Paid users: Optional, max 1,000,000" }, "primarySite": { "title": "Primary Site", "enum": [ "", "Adrenal gland", "Anus and anal canal", "Base of tongue", "Bladder", "Bones, joints and articular cartilage of limbs", "Bones, joints and articular cartilage of other and unspecified sites", "Brain", "Breast", "Bronchus and lung", "Cervix uteri", "Colon", "Connective, subcutaneous and other soft tissues", "Corpus uteri", "Esophagus", "Eye and adnexa", "Gallbladder", "Heart, mediastinum, and pleura", "Hematopoietic and reticuloendothelial systems", "Kidney", "Larynx", "Lip", "Liver and intrahepatic bile ducts", "Lymph nodes", "Meninges", "Nasal cavity and middle ear", "Nasopharynx", "Oropharynx", "Other and ill-defined sites", "Other and unspecified parts of mouth", "Other and unspecified parts of tongue", "Ovary", "Pancreas", "Penis", "Peripheral nerves and autonomic nervous system", "Prostate gland", "Rectum", "Rectosigmoid junction", "Renal pelvis", "Retroperitoneum and peritoneum", "Skin", "Small intestine", "Spinal cord, cranial nerves, and other parts of central nervous system", "Stomach", "Testis", "Thymus", "Thyroid gland", "Tonsil", "Trachea", "Ureter", "Uterus, NOS", "Vagina", "Vulva" ], "type": "string", "description": "Filter records by primary tumour / tissue site. Leave empty for all sites.", "default": "" }, "program": { "title": "Program", "enum": [ "", "ALCHEMIST", "APOLLO", "BEATAML1.0", "CCDI", "CCG", "CDDP_EAGLE", "CGCI", "CMI", "CPTAC", "CTSP", "EXCEPTIONAL_RESPONDERS", "FM", "HCMI", "MATCH", "MMRF", "MP2PRT", "NCICCR", "OHSU", "ORGANOID", "RC", "REBC", "TARGET", "TCGA", "TRIO", "VAREPOP", "WCDT" ], "type": "string", "description": "Filter by NCI cancer program. Leave empty for all programs.", "default": "" } } }, "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 } } } } } } } } } }