{ "openapi": "3.0.1", "info": { "title": "Medium Scraper — Articles, Authors, Tags & Search", "description": "Scrape Medium articles by tag, keyword, author, publication or link: claps, responses, reading time, tags and author. Full text, comments and profiles as options. Walk any tag by date. No login. Export JSON, CSV, Excel.", "version": "0.0", "x-build-id": "BiKWO8UXfky4NXSrj" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/nice_dev~medium-articles-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-nice_dev-medium-articles-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/nice_dev~medium-articles-scraper/runs": { "post": { "operationId": "runs-sync-nice_dev-medium-articles-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/nice_dev~medium-articles-scraper/run-sync": { "post": { "operationId": "run-sync-nice_dev-medium-articles-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Medium links", "maxItems": 100, "type": "array", "description": "Any Medium link, mixed freely: tag page (`https://medium.com/tag/python`, …/tag/python/archive/2024/03), search (medium.com/search?q=…), author (medium.com/@user or user.medium.com; …/@user/followers and …/@user/following list the people instead of the stories), publication (medium.com/towards-artificial-intelligence or its own domain such as levelup.gitconnected.com), article (any article URL, also on custom domains). Each link is read as its own source. Max 100 URLs.", "default": [], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "query": { "title": "Search keyword", "maxLength": 200, "type": "string", "description": "One keyword searched on Medium, e.g. `web scraping` (stories, or authors / publications / tags with 'Search for'). Medium returns up to about 1,000 results per keyword. Use 'Search keywords' below for several." }, "searchQueries": { "title": "Search keywords", "maxItems": 100, "type": "array", "description": "Several keywords searched one after the other (added to 'Search keyword'). Up to 100 keywords of 200 characters.", "default": [], "items": { "type": "string" } }, "searchType": { "title": "Search for", "enum": [ "articles", "people", "publications", "tags" ], "type": "string", "description": "What the keywords search for: stories (articles), people (author rows), publications (publication rows) or tags (tag rows with their story and follower counts).", "default": "articles" }, "tags": { "title": "Tags", "maxItems": 100, "type": "array", "description": "Medium tag slugs or tag links, e.g. `python`, `data-science`. `C++`, `C#`, `.NET` and `F#` are read as the tags `cpp`, `csharp`, `dotnet` and `fsharp`. Up to 100 tags. Read with the order set in 'Tag feed'.", "default": [], "items": { "type": "string" } }, "tagSort": { "title": "Tag feed", "enum": [ "latest", "mostRead", "hot", "topWeek", "topMonth", "topYear", "topAllTime" ], "type": "string", "description": "Which stories of each tag. 'Latest' walks the tag's whole archive, newest first (with 'Published after / before' it jumps straight to those months). 'Most read' = the 20 most-read stories of each month, month by month back from 'Published before' (or today) to 'Published after'. 'Hot', 'Top this week / month / year / all time' = Medium's own rankings, about 100 stories each.", "default": "latest" }, "authors": { "title": "Authors", "maxItems": 100, "type": "array", "description": "Usernames (`karpathy` or `@karpathy`) or profile links (medium.com/@user, user.medium.com). All their stories, newest first. Up to 100 authors.", "default": [], "items": { "type": "string" } }, "publications": { "title": "Publications", "maxItems": 100, "type": "array", "description": "Publication slugs (`netflix-techblog`), own domains (`levelup.gitconnected.com`) or links. Their whole archive, newest first. Up to 100 publications.", "default": [], "items": { "type": "string" } }, "followersOf": { "title": "Followers of", "maxItems": 100, "type": "array", "description": "Usernames or profile links: one author row per follower (name, username, bio, followers, following, X handle, membership). Newest followers first.", "default": [], "items": { "type": "string" } }, "followingOf": { "title": "Followed by", "maxItems": 100, "type": "array", "description": "Usernames or profile links: one author row per person they follow.", "default": [], "items": { "type": "string" } }, "articleUrls": { "title": "Article links", "maxItems": 1000, "type": "array", "description": "Direct article links (medium.com, writer subdomains, publication domains, or medium.com/p/), e.g. `https://medium.com/p/a64152b37c35`. One row per article. Up to 1 000 links.", "default": [], "items": { "type": "string" } }, "maxItems": { "title": "Max results (total)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Maximum results for the whole run: articles, plus the author, publication and tag rows of a search or a followers list (0 = no limit). Responses and the profile rows added by the options are not counted.", "default": 100 }, "maxItemsPerQuery": { "title": "Max results per source", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Maximum results from each source: tag, keyword, author, publication, followers list or link (0 = no per-source limit, only the total).", "default": 0 }, "maxFollowersPerUser": { "title": "Max followers per user", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Rows per user in 'Followers of' / 'Followed by' (0 = all).", "default": 1000 }, "includeContent": { "title": "Include article text (paid option)", "type": "boolean", "description": "Adds each article's full text as markdown and plain text (headings, lists, quotes, code, images and links kept), its outbound links, images, headings and paragraph / image / code-block counts. Member-only stories give Medium's public preview only (flagged by 'contentIsPreview'). Billed per article with text.", "default": false }, "includeHtml": { "title": "Include article HTML", "type": "boolean", "description": "Also adds the text as simple HTML (needs 'Include article text').", "default": false }, "compareWithAuthor": { "title": "Compare with the author's usual claps (paid option)", "type": "boolean", "description": "Adds the author's median claps over their latest 25 stories and how this article compares (×). One extra request per author; billed per article compared (not charged when no comparison is possible: median not found, or equal to 0). 'Claps per 1,000 author followers' is always given.", "default": false }, "includeResponses": { "title": "Include responses (comments)", "type": "boolean", "description": "Adds the responses of each article as extra rows (type 'response': text, claps, author, date), up to 'Max responses per article'. Billed per response row.", "default": false }, "maxResponsesPerArticle": { "title": "Max responses per article", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Response rows per article when 'Include responses' is on (0 = all).", "default": 25 }, "includeAuthorProfiles": { "title": "Add author profile rows (paid option)", "type": "boolean", "description": "Adds a profile row (type 'author') for each author of the articles found, and turns the author rows of a search or a followers list into full profiles: followers, following, bio, links, membership, last story date, stories in the last 30 / 90 days, median claps and responses, best story, top tags. One extra request per author; billed per profile row.", "default": false }, "includePublicationProfiles": { "title": "Add publication profile rows (paid option)", "type": "boolean", "description": "Adds a profile row (type 'publication') for each publication of the articles found, and turns the publication rows of a search into full profiles: followers, description, domain, editors' links, stories in the last 30 / 90 days, median claps and responses, best story, top tags. One extra request per publication; billed per profile row.", "default": false }, "includeBioContacts": { "title": "Add bio contacts (paid option)", "type": "boolean", "description": "Author and publication rows: e-mail addresses and phone numbers written in the bio or description ('emails', 'phones'). Billed only for rows where at least one contact is found.", "default": false }, "postedAfter": { "title": "Published after", "maxLength": 40, "type": "string", "description": "Keeps articles first published on or after this date (the article's 'publishedAt'): `2026-09-01` (the whole day is included, UTC) or a period before now like `7 days`, `2 weeks`, `1 month`. Tags in 'Latest' / 'Most read' jump straight to these months." }, "postedBefore": { "title": "Published before", "maxLength": 40, "type": "string", "description": "Keeps articles first published before this date (the article's 'publishedAt'): `2026-09-01` (the whole day is included, UTC: articles of 1 September are kept, those of 2 September are not) or a period before now like `7 days`, `2 weeks`, `1 month`. Tags in 'Latest' / 'Most read' jump straight to these months." }, "excludeKeywords": { "title": "Exclude keywords", "maxItems": 50, "type": "array", "description": "Drops the rows whose title, subtitle or tags contain one of these words (case-insensitive), e.g. `crypto`: articles, and also author, publication and tag rows (judged on their name, and a publication on its tags). Responses are never dropped by it. Up to 50 words of 100 characters.", "default": [], "items": { "type": "string" } }, "minClaps": { "title": "Min claps", "minimum": 0, "maximum": 10000000, "type": "integer", "description": "Keeps articles with at least this many claps (0 = all). Dropped articles are not billed.", "default": 0 }, "minFollowers": { "title": "Min followers (authors / publications)", "minimum": 0, "maximum": 100000000, "type": "integer", "description": "Keeps author, publication and tag rows with at least this many followers (0 = all). Dropped rows are not billed.", "default": 0 }, "memberOnly": { "title": "Member-only stories", "enum": [ "all", "free", "memberOnly" ], "type": "string", "description": "All stories, only free stories, or only member-only (paywalled) stories.", "default": "all" }, "language": { "title": "Language", "pattern": "^[A-Za-z]{2}(-[A-Za-z]{2,4})?$", "maxLength": 7, "type": "string", "description": "Keeps articles in this language only, as detected by Medium. A two-letter code (`en`, `es`, `fr`, `de`, `pt`, `ja`, `zh`…) also keeps its variants (`zh` keeps `zh-hant`); a code with a script (`zh-hant`) keeps exactly that one. Empty = all." }, "onlyNew": { "title": "New articles only", "type": "boolean", "description": "Skips articles already returned by a previous run with the same 'State key' — schedule the run to get only new stories of a tag, author, publication or keyword.", "default": false }, "stateKey": { "title": "State key", "pattern": "^[a-zA-Z0-9_-]{1,64}$", "maxLength": 64, "type": "string", "description": "Name of the memory of articles already seen, one per monitoring task, e.g. `python-daily` (letters, digits, dashes and underscores, up to 64 characters).", "default": "default" }, "resetState": { "title": "Reset state", "type": "boolean", "description": "Forgets the articles already seen under this 'State key' before the run.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "The Apify proxy is included in the price: keep the default. You can also give your own proxy URLs.", "default": { "useApifyProxy": true } }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Requests in parallel.", "default": 8 }, "maxRequestsPerMinute": { "title": "Max requests per minute", "minimum": 1, "maximum": 3000, "type": "integer", "description": "Upper limit of requests per minute for the whole run.", "default": 600 }, "minRequestIntervalMs": { "title": "Min interval between requests (ms)", "minimum": 0, "maximum": 60000, "type": "integer", "description": "Pause between two requests, in milliseconds (0 = none).", "default": 0 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "Tries again a request that failed or that the site turned away, each time on a new proxy session (0-10).", "default": 5 }, "debugLog": { "title": "Debug log", "type": "boolean", "description": "More detailed log.", "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 }, "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 } } } } } } } } } }