{ "openapi": "3.0.1", "info": { "title": "Twitter (X) Comments Scraper", "description": "Scrape replies (comments) of Twitter/X posts from their URLs — many posts in one run. Returns text, author, favorites, retweets, replies and the source tweet each reply belongs to. Compatible with api-ninja/x-twitter-replies-retweets-scraper.", "version": "1.0", "x-build-id": "kV3CxlvtFxq6kgOsX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/outspoken_strategy~twitter-comments-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-outspoken_strategy-twitter-comments-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/outspoken_strategy~twitter-comments-scraper/runs": { "post": { "operationId": "runs-sync-outspoken_strategy-twitter-comments-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/outspoken_strategy~twitter-comments-scraper/run-sync": { "post": { "operationId": "run-sync-outspoken_strategy-twitter-comments-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "Post URLs", "type": "array", "description": "URLs of the X/Twitter posts whose replies (comments) you want to scrape, e.g. https://x.com/user/status/1234567890123456789 — one or MANY posts per run. Both x.com and twitter.com URLs work.", "items": { "type": "string" } }, "startUrls": { "title": "Post URLs (request list)", "type": "array", "description": "Alternative way to provide the post URLs as a request list of { \"url\": ... } objects. Merged with \"urls\" and de-duplicated by tweet id.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "category": { "title": "Category", "enum": [ "replies" ], "type": "string", "description": "What to scrape for each post. Currently \"replies\" (the comments under the post).", "default": "replies" }, "resultsPerCategory": { "title": "Max replies per post", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of replies to fetch PER post URL. The source post itself is also emitted (flagged is_source_tweet) and does not count towards this limit.", "default": 100 }, "parseAllResults": { "title": "Parse all results", "type": "boolean", "description": "Accepted for backwards compatibility with older pipelines. This actor always emits fully parsed items, so the flag has no effect.", "default": false }, "scrapeAll": { "title": "Scrape all (auto-paginate)", "type": "boolean", "description": "Keep scrolling the conversation (and expanding \"Show more replies\") until the per-post limit is reached or the thread runs dry. When unchecked only the replies on the initial page load are returned.", "default": true }, "includeSourceTweet": { "title": "Include the source post", "type": "boolean", "description": "Also emit one dataset item for the post itself (flagged is_source_tweet: true). Uncheck to get replies only.", "default": true }, "cookies": { "title": "Twitter/X session cookies", "type": "array", "description": "Cookies of a logged-in X session, exported with a browser extension such as Cookie-Editor or EditThisCookie (JSON array of {name, value, domain, ...}). REQUIRED in practice: X hides replies from anonymous visitors. The \"auth_token\" and \"ct0\" cookies carry the session. Alternatively set the TW_COOKIES secret environment variable on the actor (same JSON, or a 'name=value; name2=value2' string) to avoid passing cookies in every run. Use a throwaway account, never your personal one." }, "twUsername": { "title": "X username (automated login)", "type": "string", "description": "Username/email/phone of a throwaway X account. If set together with twPassword (or via the TW_USERNAME/TW_PASSWORD secret env vars), the actor logs in itself and caches the session, so you don't need to paste cookies. The account must have 2FA disabled. Prefer setting these as secret environment variables on the actor rather than per run." }, "twPassword": { "title": "X password (automated login)", "type": "string", "description": "Password for the account in twUsername. Stored encrypted. Prefer the TW_PASSWORD secret environment variable instead of putting it in run input." }, "twEmail": { "title": "X email (login identity check)", "type": "string", "description": "Email of the account, used only when X asks to confirm the identity during automated login (\"Enter your phone number or email\"). Also settable via the TW_EMAIL env var." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy to route traffic through. Residential proxies with a country set are strongly recommended for X — the random global residential pool often hands out dead exit IPs, so the actor defaults RESIDENTIAL to US exits when no country is chosen.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ], "apifyProxyCountry": "US" } }, "headless": { "title": "Run browser headless", "type": "boolean", "description": "Uncheck to run a headed browser (useful only for local debugging).", "default": true } } }, "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 } } } } } } } } } }