{ "openapi": "3.0.1", "info": { "title": "GBIF Species & Occurrence API Scraper", "description": "Extract biodiversity data from the Global Biodiversity Information Facility (GBIF). Dual-mode: species mode retrieves taxonomy, vernacular names, synonyms, and distributions; occurrence mode streams georeferenced observation records for species distribution modelling and conservation analysis.", "version": "0.1", "x-build-id": "OmuGdttXQk3vBTnmo" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jungle_synthesizer~gbif-species-occurrence-api-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jungle_synthesizer-gbif-species-occurrence-api-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jungle_synthesizer~gbif-species-occurrence-api-scraper/runs": { "post": { "operationId": "runs-sync-jungle_synthesizer-gbif-species-occurrence-api-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jungle_synthesizer~gbif-species-occurrence-api-scraper/run-sync": { "post": { "operationId": "run-sync-jungle_synthesizer-gbif-species-occurrence-api-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "sp_intended_usage": { "title": "What is the intended usage of this data?", "minLength": 1, "type": "string", "description": "Please describe how you plan to use the data extracted by this crawler." }, "sp_improvement_suggestions": { "title": "How can we improve this crawler for you?", "minLength": 1, "type": "string", "description": "Provide any feedback or suggestions for improvements." }, "sp_contact": { "title": "Contact Email", "minLength": 1, "type": "string", "description": "Provide your email address so we can get in touch with you." }, "mode": { "title": "Scrape Mode", "enum": [ "species", "occurrence" ], "type": "string", "description": "Which dataset to scrape: 'species' retrieves taxonomy + enrichment (vernacular names, synonyms, distributions, descriptions); 'occurrence' streams georeferenced observation records.", "default": "species" }, "query": { "title": "Search Query", "type": "string", "description": "Free-text search query (e.g. 'Acer', 'Quercus robur', 'Plantae'). Leave blank to stream all records matching other filters." }, "higherTaxonKey": { "title": "Higher Taxon Key", "type": "integer", "description": "GBIF backbone key for a higher taxon. Use to fetch all species within a kingdom, phylum, class, order, or family. Example: 6 = Plantae, 1 = Animalia." }, "rank": { "title": "Taxonomic Rank Filter (species mode)", "enum": [ "", "SPECIES", "GENUS", "FAMILY", "ORDER", "CLASS", "PHYLUM", "KINGDOM", "SUBSPECIES", "VARIETY" ], "type": "string", "description": "Restrict species-mode results to this rank. Leave blank for all ranks." }, "taxonomicStatus": { "title": "Taxonomic Status Filter (species mode)", "enum": [ "", "ACCEPTED", "SYNONYM", "DOUBTFUL" ], "type": "string", "description": "Restrict species-mode results to ACCEPTED names only, SYNONYM only, or all." }, "datasetKey": { "title": "Dataset Key (species/occurrence)", "type": "string", "description": "Restrict to a specific GBIF dataset UUID. Example: 'd7dddbf4-2cf0-4f39-9b2a-bb099caae36c' for the GBIF backbone taxonomy." }, "countryCode": { "title": "Country Code (occurrence mode)", "type": "string", "description": "ISO 3166-1 alpha-2 country code to filter occurrence records (e.g. 'US', 'GB', 'AU'). Only used in occurrence mode." }, "yearFrom": { "title": "Year From (occurrence mode)", "type": "integer", "description": "Filter occurrences recorded on or after this year. Also used for year-chunking to bypass the 100k offset cap." }, "yearTo": { "title": "Year To (occurrence mode)", "type": "integer", "description": "Filter occurrences recorded on or before this year." }, "hasCoordinate": { "title": "Has Coordinate Only (occurrence mode)", "type": "boolean", "description": "When true, return only occurrence records with a decimal latitude and longitude. Recommended for SDM/GIS workflows.", "default": false }, "enrich": { "title": "Enrich Species Records", "type": "boolean", "description": "When true (default), each accepted species record is enriched with vernacular names, synonyms, geographic distributions, and descriptions via 4 additional API calls. Set to false for faster bulk taxonomy extraction.", "default": true }, "maxItems": { "title": "Max Items", "type": "integer", "description": "Maximum number of records to return (0 = unlimited). For occurrence mode without year filters, GBIF caps offset at 100,000; use yearFrom/yearTo chunking or set a maxItems limit.", "default": 15 } } }, "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 } } } } } } } } } }