{ "openapi": "3.0.1", "info": { "title": "arXiv Papers Scraper — Search Research Papers by Topic & Author", "description": "Search arXiv for research papers by keywords, author, category and date; returns title, authors, abstract, categories, published/updated dates, PDF and abstract URLs, DOI. Sort by relevance or date. Built for research agents. No API key.", "version": "0.1", "x-build-id": "hacBQmSAMU0en3Ion" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/yadroo~arxiv-papers/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-yadroo-arxiv-papers", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/yadroo~arxiv-papers/runs": { "post": { "operationId": "runs-sync-yadroo-arxiv-papers", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/yadroo~arxiv-papers/run-sync": { "post": { "operationId": "run-sync-yadroo-arxiv-papers", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Mode", "enum": [ "search", "latest" ], "type": "string", "description": "`search` queries the whole arXiv archive through the export API (keywords, authors, dates, ids, sorting) — that API is rate-limited and sometimes throttles for minutes. `latest` returns the papers in the current daily announcement for `categories` from arXiv's RSS feed (fast, not rate-limited); `query`, `authors`, `excludeCategories` and `announceTypes` are applied locally. On weekends/holidays the most recent announcement is returned.", "default": "search" }, "announceTypes": { "title": "Announce types (latest mode)", "type": "array", "description": "Only in mode `latest`: keep only these announcement types. `new` = first-time submissions, `cross` = new papers cross-listed from another category, `replace` / `replace-cross` = new versions of older papers. Empty = all.", "items": { "type": "string", "enum": [ "new", "cross", "replace", "replace-cross" ], "enumTitles": [ "New submissions", "Cross-lists", "Replacements (new versions)", "Replacement cross-lists" ] } }, "query": { "title": "Search query", "type": "string", "description": "Keywords to search (all words must match unless matchMode says otherwise; whole-word match, no stemming). You can also paste raw arXiv query syntax — field prefixes ti: (title), abs: (abstract), au: (author), co: (comment), jr: (journal ref), cat: (category), rn: (report number), all:, with AND / OR / ANDNOT and parentheses, e.g. `au:Vaswani AND ti:attention`. Raw syntax is passed through unchanged. Leave empty to browse by authors/categories/dates or fetch idList. In mode `latest` plain keywords are matched locally (whole words, case-insensitive)." }, "searchIn": { "title": "Search in field", "enum": [ "all", "title", "abstract", "author", "comment", "journalRef", "reportNumber" ], "type": "string", "description": "Which arXiv field the plain-keyword query is matched against. Ignored when the query already uses field prefixes.", "default": "all" }, "matchMode": { "title": "Keyword match mode", "enum": [ "all", "any", "phrase" ], "type": "string", "description": "How multiple plain keywords are combined. `phrase` wraps the query in quotes for an exact phrase match.", "default": "all" }, "authors": { "title": "Authors", "type": "array", "description": "Author names, all must appear (au: prefix). Best recall with surname only (`Vaswani`) or `Surname_Initial` (`Vaswani_A`); full names are quoted automatically.", "items": { "type": "string" } }, "category": { "title": "Category (single)", "type": "string", "description": "One arXiv category code, e.g. cs.AI, q-fin.TR, or an archive like `cs` (= all cs.*). Kept for backward compatibility — prefer `categories`." }, "categories": { "title": "Categories (any of)", "type": "array", "description": "Required for mode `latest`. arXiv category codes, paper matches if it is in ANY of them (cross-listings count). Case-insensitive; archive names (`cs`, `q-fin`) expand to all their subcategories. Full list of ~155 codes in the README Reference section. Unknown codes are passed through with a warning.", "items": { "type": "string" } }, "excludeCategories": { "title": "Exclude categories", "type": "array", "description": "Drop papers filed in any of these categories (ANDNOT cat:…).", "items": { "type": "string" } }, "submittedFrom": { "title": "Submitted from", "pattern": "^\\d{4}(-\\d{2}(-\\d{2})?)?([T ]\\d{2}:?\\d{2}(:\\d{2})?Z?)?$", "type": "string", "description": "Earliest original submission date (v1), inclusive. YYYY-MM-DD (also YYYY-MM, YYYY or ISO datetime). Use with sortBy=submittedDate to monitor new papers." }, "submittedTo": { "title": "Submitted to", "pattern": "^\\d{4}(-\\d{2}(-\\d{2})?)?([T ]\\d{2}:?\\d{2}(:\\d{2})?Z?)?$", "type": "string", "description": "Latest original submission date, inclusive (end of that day, GMT)." }, "idList": { "title": "arXiv IDs", "type": "array", "description": "Fetch specific papers by id: `2301.00001`, `2301.00001v2`, `arXiv:…`, `https://arxiv.org/abs/…` or old-style `hep-th/9901001`. Can be combined with a query (then only ids matching the query are returned).", "items": { "type": "string" } }, "sortBy": { "title": "Sort by", "enum": [ "relevance", "submittedDate", "lastUpdatedDate" ], "type": "string", "description": "arXiv server-side sort.", "default": "relevance" }, "sortOrder": { "title": "Sort order", "enum": [ "descending", "ascending" ], "type": "string", "description": "Sort direction.", "default": "descending" }, "limit": { "title": "Max papers", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Stop after this many papers. A busy category announces 200–600 papers a day, so raise this for a full `latest` digest. In search mode pages of 100 are fetched with a polite 3 s pause (arXiv rule), so 1000 papers take ~40 s. Alias: maxItems.", "default": 25 }, "startOffset": { "title": "Start offset", "minimum": 0, "maximum": 30000, "type": "integer", "description": "Skip the first N results (manual paging across runs).", "default": 0 }, "includeAbstract": { "title": "Include abstract", "type": "boolean", "description": "Set false for a compact metadata-only dataset.", "default": true }, "maxAbstractChars": { "title": "Max abstract characters", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Truncate abstracts to this length (0 = full abstract).", "default": 0 }, "fields": { "title": "Output fields", "type": "array", "description": "Keep only these output fields (see Output table in README), e.g. [\"id\",\"title\",\"published\",\"pdfUrl\"]. Empty = all fields.", "items": { "type": "string" } } } }, "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 } } } } } } } } } }