{ "openapi": "3.0.1", "info": { "title": "Npm PyPI Package Scraper", "description": "npm & PyPI Package Scraper is a Python tool designed to extract package metadata, download statistics, version histories, and dependencies from npm and PyPI, exporting structured software data into clean CSV or JSON formats for ecosystem analysis and research.", "version": "0.0", "x-build-id": "l9kQ5IOotZZAxtZhe" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/zerobreak~npm-PyPI-Package-Scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-zerobreak-npm-PyPI-Package-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/zerobreak~npm-PyPI-Package-Scraper/runs": { "post": { "operationId": "runs-sync-zerobreak-npm-PyPI-Package-Scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/zerobreak~npm-PyPI-Package-Scraper/run-sync": { "post": { "operationId": "run-sync-zerobreak-npm-PyPI-Package-Scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "mode" ], "properties": { "mode": { "title": "What to scrape", "enum": [ "npm_search", "npm_packages", "pypi_packages" ], "type": "string", "description": "npm_search queries the npm registry. npm_packages and pypi_packages look up names you already have. PyPI has no keyword search.", "default": "npm_search" }, "searchQueries": { "title": "npm search keywords", "type": "array", "description": "Keywords for npm search. One query per line. Qualifiers such as keywords:, author:, and maintainer: are passed through as npm documents them.", "items": { "type": "string" } }, "packages": { "title": "Package names", "type": "array", "description": "Package names for npm_packages or pypi_packages. npm accepts scoped names such as @babel/core. PyPI examples: requests, pandas. npmjs.com/package and pypi.org/project URLs are accepted.", "items": { "type": "string" } }, "includeDownloads": { "title": "Include download stats", "type": "boolean", "description": "npm: last-week and last-month from the downloads API (search rows already include those counts). PyPI: last day, week, and month from pypistats, which allows 60 requests per minute.", "default": true }, "includeDownloadHistory": { "title": "Include daily download history", "type": "boolean", "description": "Add a daily downloads series. npm uses the last-month range endpoint. PyPI uses pypistats overall without mirrors, about 180 days, and counts toward the 60 requests per minute limit.", "default": false }, "enrichSearchResults": { "title": "Enrich npm search results with full metadata", "type": "boolean", "description": "After npm search, load /latest and the packument so the row includes created time, version count, dependencies, and repository fields that search omits.", "default": false }, "minWeeklyDownloads": { "title": "Min weekly downloads (npm search filter)", "minimum": 0, "type": "integer", "description": "Drop packages below this weekly download count. Uses npm search counts, or a downloads lookup when you pass package names. Zero keeps every package.", "default": 0 }, "updatedAfter": { "title": "Updated after", "type": "string", "description": "Keep packages whose latest publish date is on or after this day. npm uses the registry updated or version time. PyPI uses the latest release upload time." }, "includeReadme": { "title": "Include README / description text", "type": "boolean", "description": "Store the README. npm reads it from the packument, which can be large. PyPI stores the project description from the JSON API.", "default": false }, "maxItems": { "title": "Max results (total)", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Stop after this many dataset rows, including error rows. Free version cap: 5,000 per run.", "default": 200 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many package lookups run at once. Higher is faster and more likely to hit registry or pypistats limits.", "default": 5 }, "timeoutSecs": { "title": "Run timeout (seconds)", "minimum": 1, "maximum": 3600, "type": "integer", "description": "Stop the run after this many seconds and keep rows already saved. Default 300. Maximum 3600.", "default": 300 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 1, "maximum": 300, "type": "integer", "description": "Per-request timeout for registry and stats calls. Default 30. Packument reads use 60 seconds because those documents are large.", "default": 30 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional proxy for registry and stats requests. Leave useApifyProxy off unless a registry blocks the platform IP. Datacenter proxies are faster. Residential proxies are harder to detect.", "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 } } } } } } } } } }