{ "openapi": "3.0.1", "info": { "title": "LinkedIn Newsletter & Article Scraper", "description": "Read LinkedIn long-form articles in full: body text, author, publish and edit dates, reactions and comments, with reading time and engagement-per-thousand-followers computed. Discover an author's articles from their profile. No login required.", "version": "0.0", "x-build-id": "AApNSok14flnPqXP6" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/fanndev~linkedin-newsletter-article-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-fanndev-linkedin-newsletter-article-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/fanndev~linkedin-newsletter-article-scraper/runs": { "post": { "operationId": "runs-sync-fanndev-linkedin-newsletter-article-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/fanndev~linkedin-newsletter-article-scraper/run-sync": { "post": { "operationId": "run-sync-fanndev-linkedin-newsletter-article-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "articleUrls": { "title": "Article URLs", "type": "array", "description": "LinkedIn long-form articles to read - linkedin.com/pulse/... links. Individual newsletter issues are /pulse/ links too, so paste those here.", "items": { "type": "string" } }, "authorProfiles": { "title": "Author profiles", "type": "array", "description": "Discover articles instead of listing them: give a member profile (a /in/ URL or a bare handle) and the actor reads the articles linked from their public profile page.", "items": { "type": "string" } }, "newsletterUrls": { "title": "Newsletter series URLs", "type": "array", "description": "Accepted so a run does not fail on them, but LinkedIn answers HTTP 500 to logged-out visitors on every /newsletters/ series page - subscriber counts have no public surface at all. Anything passed here produces a NOTICE row explaining that. Pass the individual issue /pulse/ links in Article URLs instead; those are fully readable.", "items": { "type": "string" } }, "startUrls": { "title": "Article URLs (request list)", "type": "array", "description": "The same article links in the request-list format, for callers that already keep one.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "includeFullText": { "title": "Include the full article text", "type": "boolean", "description": "Keep the complete body on each row. Turn off for a much smaller dataset when you only want titles, dates and engagement.", "default": true }, "includeComments": { "title": "Include a sample of comments", "type": "boolean", "description": "Attach the commenters LinkedIn renders on the public page - roughly the first 8 - with their names, profile links and comment text. No extra requests: they arrive in the same page load.", "default": false }, "minReactions": { "title": "Ignore articles below this many reactions", "minimum": 0, "type": "integer", "description": "Skip low performers, which is useful when discovering from an author profile and you only want what actually landed.", "default": 0 }, "maxArticlesPerAuthor": { "title": "Maximum articles per author", "minimum": 1, "maximum": 200, "type": "integer", "description": "Cap on articles discovered from each author profile.", "default": 20 }, "maxArticles": { "title": "Maximum articles in total", "minimum": 1, "maximum": 500, "type": "integer", "description": "Overall ceiling after de-duplication. Each article costs one request.", "default": 50 }, "emitSummary": { "title": "Emit a run summary row", "type": "boolean", "description": "Append a SUMMARY row with median reactions, median length and the most-used hashtags across everything read - a quick read on what topics and formats are working.", "default": true }, "minDelaySeconds": { "title": "Minimum delay between requests", "minimum": 0, "maximum": 60, "type": "integer", "description": "LinkedIn answers request bursts with HTTP 999 and a near-empty page. A randomised gap is what keeps a run under that gate.", "default": 3 }, "maxDelaySeconds": { "title": "Maximum delay between requests", "minimum": 0, "maximum": 120, "type": "integer", "description": "The ceiling of the randomised gap. Raise both bounds if the log shows rate-gate warnings.", "default": 8 }, "exportFormats": { "title": "Extra export files", "type": "array", "description": "Besides the dataset, write ready-made files into this run's key-value store.", "items": { "type": "string", "enum": [ "json", "ndjson", "csv", "excel" ], "enumTitles": [ "JSON", "NDJSON", "CSV", "Excel (XLSX)" ] }, "default": [] }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Article pages carry no WAF and Apify's datacenter range reaches them; a proxy mainly helps on long runs where LinkedIn's per-IP rate gate becomes the bottleneck.", "default": { "useApifyProxy": 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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }