{ "openapi": "3.0.1", "info": { "title": "SpringerLink Scraper โ€” Journals, Books & Conference Papers", "description": "Scrape SpringerLink journals, books and conference papers: abstracts, author keywords, full author lists with affiliations and ORCIDs, open-access status, PDF links and exact citation counts. Includes incremental monitoring that emits only new or updated papers.", "version": "1.0", "x-build-id": "oG2Ef5c3AfCWtfVMR" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/trev0n~springerlink-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-trev0n-springerlink-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/trev0n~springerlink-scraper/runs": { "post": { "operationId": "runs-sync-trev0n-springerlink-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/trev0n~springerlink-scraper/run-sync": { "post": { "operationId": "run-sync-trev0n-springerlink-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "๐Ÿ” Search query", "type": "array", "description": "What to search for. Add several queries to run them in one go (e.g. \"machine learning\", \"battery recycling\"). Leave empty if you use journals or direct URLs instead.", "items": { "type": "string" } }, "journalIds": { "title": "๐Ÿ“š Journals", "type": "array", "description": "Restrict the run to specific journals. Accepts a SpringerLink journal id (the number in link.springer.com/journal/10994) or an ISSN (e.g. 1573-0565). With no search query this collects everything the journal published, newest first.", "items": { "type": "string" } }, "issn": { "title": "๐Ÿ”ข ISSN", "type": "string", "description": "A single journal ISSN to scope the search to. Same effect as adding it to Journals." }, "contentType": { "title": "๐Ÿ“„ Content type", "enum": [ "any", "article", "chapter", "book", "reference-work-entry", "protocol" ], "type": "string", "description": "Limit results to one kind of publication. Springer files conference papers as book chapters, so they arrive together; full mode then labels the ones it can confirm as conference papers.", "default": "any" }, "yearFrom": { "title": "๐Ÿ“… Published from (year)", "minimum": 1800, "maximum": 2100, "type": "integer", "description": "Only include publications from this year onwards." }, "yearTo": { "title": "๐Ÿ“… Published to (year)", "minimum": 1800, "maximum": 2100, "type": "integer", "description": "Only include publications up to and including this year." }, "publishedWithin": { "title": "๐Ÿ•’ Published within", "enum": [ "any", "m3", "m6", "m12", "m24" ], "type": "string", "description": "Keep only recently published work, counted back from today. Ignored when a year range above is set.", "default": "any" }, "sortBy": { "title": "โ†•๏ธ Sort by", "enum": [ "relevance", "newest", "oldest" ], "type": "string", "description": "Result order.", "default": "relevance" }, "openAccessOnly": { "title": "๐Ÿ”“ Open access only", "type": "boolean", "description": "Keep only freely readable publications.", "default": false }, "minCitations": { "title": "๐Ÿ“ˆ Minimum citations", "minimum": 0, "type": "integer", "description": "Drop publications cited fewer times than this. Needs citation counts enabled (they are by default).", "default": 0 }, "includeKeywords": { "title": "โœ… Must contain", "type": "array", "description": "Keep a publication only if its title, abstract or keywords contain at least one of these words.", "items": { "type": "string" } }, "excludeKeywords": { "title": "๐Ÿšซ Must not contain", "type": "array", "description": "Drop publications whose title, abstract or keywords contain any of these words.", "items": { "type": "string" } }, "startUrls": { "title": "๐Ÿ”— Direct URLs", "type": "array", "description": "Scrape specific SpringerLink URLs โ€” article pages, chapter pages, journal pages or search result pages.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "dois": { "title": "๐Ÿ†” DOIs", "type": "array", "description": "Scrape publications by DOI (e.g. 10.1007/s10994-025-06923-w). The right page is found automatically, whether it is an article, a chapter or a protocol.", "items": { "type": "string" } }, "maxResults": { "title": "๐Ÿ”ข Max results", "minimum": 0, "type": "integer", "description": "Stop after this many publications. Set 0 for no limit.", "default": 100 }, "maxPages": { "title": "๐Ÿ“‘ Max pages per search", "minimum": 0, "type": "integer", "description": "Stop each search after this many result pages. 0 means no page limit.", "default": 0 }, "detailConcurrency": { "title": "โšก Detail concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Full mode only: how many publication pages to read in parallel from the one warm browser session. Measured on 200 pages, 4 and 8 finish within about 10% of each other and neither tripped Springer's protection check, so 4 is the default for its slightly lower retry rate. Going much higher risks a burst being refused, which costs more than it saves.", "default": 4 }, "fetchArticlePages": { "title": "๐Ÿ“– Full mode โ€” read SpringerLink pages (affiliations, view counts, metrics)", "type": "boolean", "description": "Additionally open each publication's page on SpringerLink for everything no open index carries: the abstract of anything published too recently to have been indexed, author affiliations, corresponding-author e-mails, the publisher's own keyword list and the view/Altmetric counters. Measured on 200 brand-new publications: abstracts went from 25% to 98%, keywords from 65% to 99%, affiliations from none to 94%. Springer runs a protection check on page reads, so this drives a real browser โ€” give the run 2048 MB. It needs no proxy, and costs about 8ร— the default mode per publication (200 items in 90 seconds against 13), which is why it is off by default.", "default": false }, "abstractMaxLength": { "title": "โœ‚๏ธ Abstract max length", "minimum": 0, "type": "integer", "description": "Trim abstracts to this many characters. 0 keeps them in full.", "default": 0 }, "includeReferences": { "title": "๐Ÿ“Ž Include reference lists", "type": "boolean", "description": "Add the full list of works each article cites. Makes records much bigger.", "default": false }, "includeCitationCounts": { "title": "๐Ÿ“Š Exact citation counts", "type": "boolean", "description": "Add exact citation counts and reference counts. Recommended โ€” the counts shown on the page itself are rounded (\"19k\").", "default": true }, "includeOpenAlexData": { "title": "๐Ÿท๏ธ Keywords, topics & open-access status from the open index", "type": "boolean", "description": "Adds keywords, topics, open-access status and a fallback abstract from an open scholarly index. On by default: it needs no proxy, is never blocked, and covers the great majority of recent publications.", "default": true }, "includeSpringerAbstracts": { "title": "๐Ÿ“ Abstracts from Springer's citation records (needs your own proxy)", "type": "boolean", "description": "Fetches a ~2 KB citation record for every publication that still has no abstract โ€” no browser and no 300 KB page. Off by default because it does not work from Apify: measured, Springer's citation service answered its JavaScript protection check to every attempt โ€” plain requests, the Apify residential proxy, sticky sequential sessions, cookies borrowed from a browser that had already cleared link.springer.com, and even a real browser pointed straight at it. Turn it on only if you supply proxy URLs for a network Springer trusts, such as a university connection. For a supported cheap abstract channel use the Springer Nature API key below instead.", "default": false }, "springerApiKey": { "title": "๐Ÿ”‘ Springer Nature API key (free) โ€” abstracts without page reads", "type": "string", "description": "Paste a free Springer Nature API key to fill in abstracts straight from Springer's official API instead of opening publication pages. Get one in a minute at dev.springernature.com: sign up, create an application, copy the key. The free tier allows 500 requests a day and this actor batches 25 publications per request, so one key covers about 12,500 abstracts a day. Use this when you want abstracts cheaply but do not need author affiliations or view counts โ€” those exist only on the publication page, so they still need full mode." }, "discoveryChannel": { "title": "๐Ÿงญ Search channel", "enum": [ "auto", "crossref", "site-search" ], "type": "string", "description": "How keyword searches are answered. Automatic is unlimited and recommended. \"SpringerLink search\" mirrors the website's own ranking but is capped at 1,000 results per query and can be rate-limited.", "default": "auto" }, "warmupTimeoutSecs": { "title": "โณ Connection warm-up timeout", "minimum": 30, "maximum": 600, "type": "integer", "description": "Full mode only. How long to give the browser to get through Springer's protection check before trying a different address. Raise this on slow networks.", "default": 240 }, "browserChannel": { "title": "๐ŸŒ Browser", "enum": [ "chrome", "chromium" ], "type": "string", "description": "Full mode only. Which browser to drive. Google Chrome is the only one that reliably gets through the protection check.", "default": "chrome" }, "crossrefMailto": { "title": "๐Ÿ“ง Contact e-mail", "type": "string", "description": "Optional. A contact address sent with metadata requests to get the faster service tier." }, "compact": { "title": "๐Ÿ—œ๏ธ Compact output", "type": "boolean", "description": "Emit only the essential fields (title, authors, abstract, keywords, citations, link).", "default": false }, "excludeEmptyFields": { "title": "๐Ÿงน Drop empty fields", "type": "boolean", "description": "Leave empty fields out of the records entirely.", "default": false }, "incrementalMode": { "title": "๐Ÿ”„ Incremental monitoring", "type": "boolean", "description": "Across scheduled runs, emit only publications that are new or changed since last time. Cuts the cost of daily literature alerts by 80โ€“95%.", "default": false }, "stateKey": { "title": "๐Ÿ”‘ Monitoring key", "type": "string", "description": "Name for this monitoring baseline. Leave empty to derive one from your search settings. Use different keys for different watch lists." }, "emitUnchanged": { "title": "โ™ป๏ธ Include unchanged", "type": "boolean", "description": "Also emit publications that haven't changed since the previous run.", "default": false }, "emitExpired": { "title": "๐Ÿ—‘๏ธ Include disappeared", "type": "boolean", "description": "Also emit publications that were in the previous run but are no longer found.", "default": false }, "webhookUrl": { "title": "๐Ÿ”” Webhook URL", "type": "string", "description": "POST the run results to this URL when monitoring finds something." }, "telegramBotToken": { "title": "๐Ÿค– Telegram bot token", "type": "string", "description": "Send new publications to a Telegram chat." }, "telegramChatId": { "title": "๐Ÿ’ฌ Telegram chat id", "type": "string", "description": "Chat that receives the Telegram messages." }, "discordWebhookUrl": { "title": "๐ŸŽฎ Discord webhook", "type": "string", "description": "Send new publications to a Discord channel." }, "slackWebhookUrl": { "title": "๐Ÿ’ผ Slack webhook", "type": "string", "description": "Send new publications to a Slack channel." }, "notifyOnlyChanges": { "title": "๐Ÿ”• Only notify on changes", "type": "boolean", "description": "Stay silent when a monitoring run finds nothing new.", "default": true }, "notificationLimit": { "title": "๐Ÿ“ Items per notification", "minimum": 1, "type": "integer", "description": "How many publications to list in a notification message.", "default": 10 }, "includeRunSummary": { "title": "๐Ÿ“ˆ Include run summary", "type": "boolean", "description": "Add the run statistics to webhook payloads.", "default": true }, "proxyConfiguration": { "title": "๐ŸŒ Proxy configuration", "type": "object", "description": "Proxy settings. None is the default because no mode needs one: the metadata channels are never blocked, and in full mode the real browser clears Springer's protection check straight from Apify's network โ€” measured in about a second, with zero refusals across several hundred publication pages. If you do configure a proxy it is kept in reserve and only used once a page is actually refused, so you never pay for residential traffic speculatively. Residential is worth setting if a run reports refused pages, since the check is address-scoped.", "default": { "useApifyProxy": false } }, "debug": { "title": "๐Ÿž Debug logging", "type": "boolean", "description": "Log the status, title and first characters of any page that could not be read. Useful when a run returns fewer results than expected.", "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 } } } } } } } } } }