{ "openapi": "3.0.1", "info": { "title": "ScienceDirect Search Scraper | 2$/1k Cheap", "description": "Extract academic articles from ScienceDirect.com — title, DOI, authors, journal, abstract, keywords, dates, open-access status and PDF links. Search by keyword, author, journal, year and article type, or paste a search URL. Ideal for literature reviews and bibliometrics.", "version": "1.0", "x-build-id": "MR9eZY5KF1oTA1g4k" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/trev0n~sciencedirect-search-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-trev0n-sciencedirect-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/trev0n~sciencedirect-search-scraper/runs": { "post": { "operationId": "runs-sync-trev0n-sciencedirect-search-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/trev0n~sciencedirect-search-scraper/run-sync": { "post": { "operationId": "run-sync-trev0n-sciencedirect-search-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": { "searchQuery": { "title": "Search keywords", "type": "string", "description": "Keywords to search across title, abstract and author-specified keywords (the main ScienceDirect search box). Example: \"machine learning\" or \"CRISPR gene editing\". Leave empty if you use Start URLs." }, "title": { "title": "Title contains", "type": "string", "description": "Restrict to articles whose title contains these words." }, "authors": { "title": "Author(s)", "type": "string", "description": "Filter by author name, e.g. \"Y. LeCun\"." }, "publicationTitle": { "title": "Journal or book title", "type": "string", "description": "Restrict to a specific journal, book or publication title, e.g. \"The Lancet\"." }, "volume": { "title": "Volume(s)", "type": "string", "description": "Filter by journal volume(s), e.g. \"75\" or \"75,76\"." }, "issue": { "title": "Issue", "type": "string", "description": "Filter by issue number." }, "page": { "title": "Page", "type": "string", "description": "Filter by article page number." }, "years": { "title": "Year(s)", "type": "string", "description": "Filter by publication year(s). A single year (\"2025\"), a comma list (\"2023,2024,2025\") or an inclusive range (\"2020-2025\")." }, "articleTypes": { "title": "Article types", "uniqueItems": true, "type": "array", "description": "Limit to one or more article types. Leave empty for all types.", "items": { "type": "string", "enum": [ "FLA", "REV", "ABS", "BC", "CH", "CRP", "PRP", "SCO", "DAT", "VID", "EDI", "COR", "DIS", "ERR", "NWS", "PGL", "BRV", "SSU", "MIS", "RPL", "ENC" ], "enumTitles": [ "Research articles", "Review articles", "Abstracts", "Book chapters", "Chapters", "Case reports", "Conference abstracts", "Short communications", "Data articles", "Video articles", "Editorials", "Correspondence", "Discussion", "Errata", "News", "Practice guidelines", "Book reviews", "Short surveys", "Mini reviews / Other", "Replication studies", "Encyclopedia" ] } }, "openAccessOnly": { "title": "Open access & open archive only", "type": "boolean", "description": "Return only articles that are open access or in an open archive (freely readable).", "default": false }, "sortBy": { "title": "Sort results by", "enum": [ "relevance", "date" ], "type": "string", "description": "Sort search results by relevance (default) or newest first.", "default": "relevance" }, "startUrls": { "title": "Start URLs (search URLs)", "type": "array", "description": "Optional. Paste full ScienceDirect search URLs (e.g. https://www.sciencedirect.com/search?qs=RPG&years=2025). Overrides the keyword filters above.", "default": [], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxItems": { "title": "Max results", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum number of articles to collect across all searches.", "default": 100 }, "maxPagesPerSearch": { "title": "Max pages per search", "minimum": 1, "maximum": 200, "type": "integer", "description": "Safety cap on how many result pages to page through per search.", "default": 40 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many search sessions to run in parallel. Keep low (1-2) to stay under the radar.", "default": 1 }, "maxRequestRetries": { "title": "Max retries per page", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many times to retry a page that does not clear the bot challenge.", "default": 4 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "ScienceDirect (Elsevier/Akamai) blocks datacenter IPs. Residential proxies are strongly recommended.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "headless": { "title": "Run headless", "type": "boolean", "description": "Run the browser headless. ScienceDirect blocks headless Chromium (CPE00001), so leave this OFF — headed clears the bot wall.", "default": false } } }, "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 } } } } } } } } } }