{
"openapi": "3.0.1",
"info": {
"title": "Zenodo Scraper ยท Research Records, DOIs, Authors & Files",
"description": "Scrape open research records, DOIs, publications, datasets, software, authors, and file metadata from Zenodo. Fast HTTP scraper charging per returned record with tiered pricing.",
"version": "1.0",
"x-build-id": "qbC4RNynRuc9372nm"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/reapx~zenodo-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-reapx-zenodo-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/reapx~zenodo-scraper/runs": {
"post": {
"operationId": "runs-sync-reapx-zenodo-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/reapx~zenodo-scraper/run-sync": {
"post": {
"operationId": "run-sync-reapx-zenodo-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": [
"max_records"
],
"properties": {
"query": {
"title": "Search Query",
"type": "string",
"description": "Full-text search query across titles, abstracts, subjects, and authors (e.g. climate change, machine learning). Leave empty to query all Zenodo records. The broader the query, the more total records matched."
},
"community": {
"title": "Community Identifier",
"type": "string",
"description": "Filter records belonging to a specific Zenodo community slug (e.g. biosyslit, eu, ecfunded). Leave this field empty to search across all communities nationwide and worldwide."
},
"resource_type": {
"title": "Resource Type",
"enum": [
"",
"publication-article",
"publication-preprint",
"publication-book",
"publication-conferencepaper",
"publication-report",
"dataset",
"software",
"image-figure",
"image-photo",
"presentation",
"poster",
"video",
"lesson",
"model"
],
"type": "string",
"description": "Filter by resource type identifier. Select a specific publication type, dataset, software, or image category. Leave empty to retrieve records of all resource types without restrictions.
Options: publication-article, publication-preprint, publication-book, publication-conferencepaper, publication-report."
},
"access_right": {
"title": "Access Status",
"enum": [
"",
"open",
"restricted",
"embargoed",
"metadata-only"
],
"type": "string",
"description": "Filter by record access status. Choose open for open-access publications, or filter restricted/embargoed records. Leave empty to return records of any access level."
},
"license": {
"title": "License ID",
"type": "string",
"description": "Filter records by license identifier (e.g. cc-by-4.0, mit, cc0-1.0, apache-2.0). Leave empty to return research records regardless of license."
},
"creator": {
"title": "Creator / Author Name",
"type": "string",
"description": "Return only records with this person or organisation among the creators (e.g. Hansen, European Commission). Matched against Zenodo's own metadata.creators.person_or_org.name field.
Empty value: leave empty to include records by any author.
Consequence: the match is on the name string Zenodo holds, so a common surname still returns many people; combine it with a community or a year to narrow it."
},
"file_type": {
"title": "File Type",
"pattern": "^[A-Za-z0-9]{0,10}$",
"type": "string",
"description": "Return only records that carry at least one file of this type (e.g. pdf, csv, zip, xlsx). Sent as Zenodo's own file_type facet, not as free text.
Empty value: leave empty to include records whatever they carry, including metadata-only records with no files at all.
Consequence: filtering to pdf is the quickest way to drop metadata-only and embargoed records from a corpus you intend to read."
},
"year": {
"title": "Publication Year / Range",
"pattern": "^(\\[\\d{4}\\s+TO\\s+\\d{4}\\]|\\d{4})?$",
"type": "string",
"description": "Filter by publication year (e.g. 2024) or Lucene year range (e.g. [2020 TO 2024]). Leave empty to include records published in any year."
},
"date_from": {
"title": "Published From",
"pattern": "^(\\d{4}-\\d{2}-\\d{2})?$",
"type": "string",
"description": "Only records published on or after this date (e.g. 2024-01-01). Compiled into a Zenodo publication_date range together with Published To.
Empty value: leave empty for no lower bound.
Consequence: a tight window is the cheapest way to make a repeat run return only what is new since the last one."
},
"date_to": {
"title": "Published To",
"pattern": "^(\\d{4}-\\d{2}-\\d{2})?$",
"type": "string",
"description": "Only records published on or before this date (e.g. 2024-12-31).
Empty value: leave empty for no upper bound, which is what you want for a monitoring run.
Consequence: pairs with Published From; either bound works on its own, and both are applied by Zenodo rather than after the fact."
},
"sort": {
"title": "Sort Order",
"enum": [
"newest",
"bestmatch",
"mostrecent",
"mostviewed"
],
"type": "string",
"description": "Order Zenodo returns matches in: newest for the latest uploads, bestmatch for relevance to your query, mostrecent for the most recently updated, mostviewed for the most read.
Empty value: falls back to newest.
Consequence: ordering decides which records you get when Max Records is smaller than the match count, which it usually is; it does not change what a row costs."
},
"all_versions": {
"title": "Include All Versions",
"type": "boolean",
"description": "Return every version of a record, not just the latest one. Zenodo mints a DOI per version and a concept DOI for the record as a whole, and both are on every row.
Turned off (the default): one row per record, the current version.
Consequence: this genuinely multiplies rows and therefore cost - the same query measured 218,626 matches with it off and 260,002 with it on - so raise Max Records deliberately, not by accident."
},
"max_records": {
"title": "Max Records",
"type": "integer",
"description": "Maximum number of Zenodo research records to return and write to the dataset (1 to 10,000). The higher the number, the longer the run takes and the more it costs.
The higher the number, the longer the run takes and the more you are charged, because you pay per row returned.",
"default": 50
}
}
},
"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
}
}
}
}
}
}
}
}
}
}