{
"openapi": "3.0.1",
"info": {
"title": "Crossref Scraper ยท DOI Metadata, Authors & Journals",
"description": "Scrape scholarly DOI metadata, works, journal articles, authors, citations, funding, and licenses from the Crossref REST API. Fast HTTP scraper with pay-per-event pricing.",
"version": "1.0",
"x-build-id": "uRsfxgrZHe5daEzYD"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/reapx~crossref-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-reapx-crossref-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/reapx~crossref-scraper/runs": {
"post": {
"operationId": "runs-sync-reapx-crossref-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/reapx~crossref-scraper/run-sync": {
"post": {
"operationId": "run-sync-reapx-crossref-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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_results"
],
"properties": {
"query": {
"title": "Search Query",
"type": "string",
"description": "Enter free-text keywords or phrase to search Crossref DOI metadata across titles, abstracts, and full texts (e.g. climate change or crispr).
Consequence: Broader search terms match more records, extending run time and consuming more budget. Empty value: Leave empty to search without keyword constraints when filtering by author, publisher, or date."
},
"query_author": {
"title": "Author Name",
"type": "string",
"description": "Filter work records by author given name or family name (e.g. Doudna or Vaswani).
Consequence: Restricts results strictly to works matching the specified author, reducing total records matched. Empty value: Leave empty to include works from all authors regardless of author name."
},
"query_title": {
"title": "Work Title Query",
"type": "string",
"description": "Search specifically within publication and work title fields (e.g. deep learning).
Consequence: Limits matching works to those containing the specified terms in their title, increasing query precision. Empty value: Leave empty to search across all metadata fields."
},
"query_container_title": {
"title": "Journal / Container Title",
"type": "string",
"description": "Filter works published in specific journals, proceedings, or book series (e.g. Nature or The CRISPR Journal).
Consequence: Restricts search results to specific publications, avoiding records from other journals. Empty value: Leave empty to query works across all journals and containers."
},
"query_publisher": {
"title": "Publisher Name Query",
"type": "string",
"description": "Search works issued by specific publishers (e.g. Elsevier, Wiley, or Springer).
Consequence: Filters results to publications from matching publishing houses. Empty value: Leave empty to include publications from all registered Crossref member publishers."
},
"filter_type": {
"title": "Publication Type Filter",
"enum": [
"journal-article",
"book-chapter",
"proceedings-article",
"dataset",
"posted-content",
"monograph",
"report",
"reference-entry"
],
"type": "string",
"description": "Filter by Crossref work category (e.g. journal-article, book-chapter, proceedings-article).
Consequence: Narrows output to a specific work type, ignoring all other publication formats. Empty value: Leave empty to retrieve works of any publication type."
},
"filter_from_pub_date": {
"title": "Published From Date",
"pattern": "^\\d{4}(-\\d{2}(-\\d{2})?)?$",
"type": "string",
"description": "Start date for publication filtering formatted as YYYY, YYYY-MM, or YYYY-MM-DD (e.g. 2020-01-01).
Consequence: Excludes works published prior to this date threshold. Empty value: Leave empty to include older historical publications back to the start of the index."
},
"filter_until_pub_date": {
"title": "Published Until Date",
"pattern": "^\\d{4}(-\\d{2}(-\\d{2})?)?$",
"type": "string",
"description": "End date for publication filtering formatted as YYYY, YYYY-MM, or YYYY-MM-DD (e.g. 2026-12-31).
Consequence: Excludes works published after this date threshold. Empty value: Leave empty to include recent publications up to the current date."
},
"filter_has_license": {
"title": "Has License Filter",
"type": "boolean",
"description": "Filter for works that include explicit licensing metadata or open reuse policies in Crossref.
Consequence: Excludes records lacking registered license statements. Empty value: Leave false or empty to include works with or without explicit license metadata."
},
"filter_has_abstract": {
"title": "Has Abstract Filter",
"type": "boolean",
"description": "Filter for works that contain indexed abstract text in Crossref metadata.
Consequence: Filters out records that do not contain an abstract, returning higher-detail items. Empty value: Leave false or empty to include records regardless of abstract availability."
},
"filter_has_funder": {
"title": "Has Funder Filter",
"type": "boolean",
"description": "Filter for works that carry research funding agency metadata or grant IDs.
Consequence: Narrows output to funded research publications. Empty value: Leave false or empty to include unfunded and funded publications alike."
},
"filter_funder_id": {
"title": "Funder ID / DOI",
"type": "string",
"description": "Filter works funded by a specific agency using its Crossref Funder Registry DOI (e.g. 10.13039/100000001 for NSF).
Consequence: Limits output to projects funded by that specific agency. Empty value: Leave empty to include works funded by any or no agency."
},
"filter_member": {
"title": "Publisher Member ID",
"type": "string",
"description": "Filter works by Crossref publisher member ID (e.g. 78 for Elsevier, 311 for Wiley, 179 for SAGE).
Consequence: Restricts results to the specified publisher member. Empty value: Leave empty to search across all registered publishers."
},
"sort": {
"title": "Sort Field",
"enum": [
"relevance",
"published",
"is-referenced-by-count",
"score",
"updated",
"created"
],
"type": "string",
"description": "Select field used to order returned work records (e.g. relevance, published, or is-referenced-by-count).
Consequence: Determines which matching items sort first during partial extraction runs. Empty value: Defaults to relevance score ordering.",
"default": "relevance"
},
"order": {
"title": "Sort Order",
"enum": [
"desc",
"asc"
],
"type": "string",
"description": "Order results in descending or ascending direction for the chosen sort field.
Consequence: desc puts highest relevance or newest works first; asc reverses order. Empty value: Defaults to desc.",
"default": "desc"
},
"mailto": {
"title": "Polite Pool Email",
"pattern": "^[^@]+@[^@]+\\.[^@]+$",
"type": "string",
"description": "Email address sent in Crossref API headers to route requests to Crossref's high-speed Polite Pool (e.g. reapxdev@proton.me).
Consequence: Provides higher rate limits and reliable response times. Empty value: Defaults to reapxdev@proton.me.
Leave this field empty to skip this filter.",
"default": "reapxdev@proton.me"
},
"max_results": {
"title": "Max Results Cap",
"minimum": 1,
"maximum": 10000,
"type": "integer",
"description": "Maximum number of work records to return and push to the default dataset (e.g. 50 or 1000).
Consequence: Higher values collect larger datasets but take longer and cost more per record event. Empty value: Defaults to 50 records.
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
}
}
}
}
}
}
}
}
}
}