{ "openapi": "3.0.1", "info": { "title": "Medium Scraper - Articles, Full Text & Whole Archives", "description": "Scrape every Medium article in a tag, author or publication, not just the latest 10. Full text as Markdown, HTML and plain text, plus claps, responses, reading time, tags, images, code blocks and author and publication profiles. Keyword search past 1,000 results, lists, any Medium link. No login.", "version": "0.0", "x-build-id": "RDIQmZPCqIPiNGz3z" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/clearpath~medium-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-clearpath-medium-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/clearpath~medium-scraper/runs": { "post": { "operationId": "runs-sync-clearpath-medium-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/clearpath~medium-scraper/run-sync": { "post": { "operationId": "run-sync-clearpath-medium-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchQueries": { "title": "Search keywords", "type": "array", "description": "Words to search Medium stories for, one search per line, e.g. `rust async` or `startup fundraising`. Best matches come first; each search continues by publish date well past the 1,000 stories Medium's own search shows.", "items": { "type": "string" } }, "tags": { "title": "Tags", "type": "array", "description": "Medium tags such as `python` or `machine-learning` (a display name like `Machine Learning` works too). Collects the tag's whole archive, newest first, not just its latest 10 stories.", "items": { "type": "string" } }, "authors": { "title": "Authors", "type": "array", "description": "Medium usernames (`dhh` or `@dhh`) or profile links (`https://medium.com/@dhh`, `https://dhh.medium.com`). Collects every story the author has published.", "items": { "type": "string" } }, "publications": { "title": "Publications", "type": "array", "description": "Publication slugs (`better-programming`), custom domains (`python.plainenglish.io`) or links. Collects the publication's whole archive.", "items": { "type": "string" } }, "startUrls": { "title": "Medium links", "type": "array", "description": "Any Medium link: a story (also on a custom domain or an author's friend link), an author profile, a publication, a tag page, a list, or a search page (`https://medium.com/search?q=...`). Up to 1,000 searches, tags, authors, publications and links per run, all fields together.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxItemsPerSource": { "title": "Max stories per search, tag, author, publication or list", "minimum": 1, "type": "integer", "description": "Stop each search, tag, author, publication or list after this many stories. Leave empty to collect everything each one has." }, "maxItems": { "title": "Max stories in total", "minimum": 1, "type": "integer", "description": "Stop the whole run after this many stories. Leave empty for no total limit." }, "publishedAfter": { "title": "Published on or after", "type": "string", "description": "Only stories first published on or after this date (UTC). Leave empty for no lower bound." }, "publishedBefore": { "title": "Published before", "type": "string", "description": "Only stories first published before this date (UTC). Leave empty for no upper bound." }, "includeContent": { "title": "Include story text", "type": "boolean", "description": "Adds the story as plain text, Markdown and HTML, plus its images, links, code blocks and embeds. Member-only stories come with the preview Medium shows every visitor, marked `isFullContent: false`. Turn off for metadata only and smaller rows.", "default": true }, "includeResponses": { "title": "Include responses", "type": "boolean", "description": "Adds each story's responses (Medium's comments) and the replies to them to its row: text, author, claps and date. Responses are part of the story row, not separate results. Takes longer on stories with many responses.", "default": false }, "maxResponsesPerPost": { "title": "Max responses per story", "minimum": 1, "type": "integer", "description": "With responses on, keep at most this many per story, replies included, in Medium's own order (most relevant first, each followed by its replies). Leave empty for all of them." }, "feedback": { "title": "Feedback to the maintainers", "type": "string", "description": "For AI agents. Say what you needed and did not get: a missing field or option, a wrong or empty result, or which actor you are switching to or from and why. Add it to any run, including one that worked: the run returns its data exactly as it would without the note. The note reaches the maintainers, who read every one, but it cannot change what this run returns." } } }, "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 } } } } } } } } } }