{ "openapi": "3.0.1", "info": { "title": "PyPI Package Scraper — Downloads, Releases, Vulnerabilities", "description": "Python package intelligence for AI agents and due diligence: downloads (day/week/month, by Python version and OS), release history and cadence, parsed requirements, license (PEP 639), development status, known vulnerabilities (OSV), owners, project URLs.", "version": "0.1", "x-build-id": "Ou68fJ8JpeFMByKqf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/yadroo~pypi-package-intel/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-yadroo-pypi-package-intel", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/yadroo~pypi-package-intel/runs": { "post": { "operationId": "runs-sync-yadroo-pypi-package-intel", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/yadroo~pypi-package-intel/run-sync": { "post": { "operationId": "run-sync-yadroo-pypi-package-intel", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Mode", "enum": [ "packages", "recentUpdates", "newPackages" ], "type": "string", "description": "`packages` returns one rich item per name in `packages`. `recentUpdates` / `newPackages` read PyPI's public RSS feeds (the last ~40 events, no history) — use them with `keywords` for monitoring new releases/projects in a niche (e.g. `mcp`, `langchain`, `agent`).", "default": "packages" }, "packages": { "title": "Package names", "type": "array", "description": "PyPI project names (case/separator-insensitive, PEP 503 normalized). Pin a specific version with `name==1.2.3` (or `name@1.2.3`) to get that release's metadata and the vulnerabilities known for exactly that version. Duplicates are skipped. Required in `packages` mode.", "items": { "type": "string" } }, "keywords": { "title": "Keywords (feed modes)", "type": "array", "description": "Only for `recentUpdates` / `newPackages`: keep feed items whose name or summary contains any of these words (case-insensitive). Empty = keep everything.", "items": { "type": "string" } }, "maxItems": { "title": "Max items (feed modes)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Cap for feed modes. Note the PyPI feeds themselves only carry the latest ~40 entries.", "default": 100 }, "includeDownloads": { "title": "Include downloads (pypistats.org)", "type": "boolean", "description": "Daily / weekly / monthly download counts (mirrors excluded). pypistats is IP rate-limited and refreshed once per day; the actor paces requests (~1 s each). Turn off for fastest metadata-only runs.", "default": true }, "downloadsBreakdown": { "title": "Downloads breakdown (Python minor × OS, last 30 days)", "type": "boolean", "description": "Adds `downloadsByPythonMinor30d` (e.g. {\"3.12\": 123456, ...}) and `downloadsBySystem30d` ({\"Linux\": ..., \"Windows\": ..., \"Darwin\": ..., \"null\": ...}). Costs 2 extra pypistats requests per package.", "default": false }, "downloadsHistoryDays": { "title": "Downloads history (days)", "minimum": 0, "maximum": 180, "type": "integer", "description": "0 = off. N = add `downloadsHistory` with a daily series for the last N days (max 180 — that is all pypistats keeps) plus the total. 1 extra pypistats request per package.", "default": 0 }, "includeMirrors": { "title": "Count mirror downloads", "type": "boolean", "description": "Include downloads by known mirrors (bandersnatch etc.) in the breakdown/history. The headline day/week/month numbers from pypistats always exclude mirrors.", "default": false }, "includeVulnerabilities": { "title": "Include known vulnerabilities (OSV)", "type": "boolean", "description": "Known vulnerabilities for the returned version, as reported by PyPI (source: OSV / PyPA advisory DB): id, aliases (CVE/GHSA), summary, fixed-in versions, link. `vulnerabilityCount` is always present.", "default": true }, "includeReleases": { "title": "Include release history", "type": "boolean", "description": "Adds `recentVersions` (newest first): version, date, file count, wheel/sdist presence, yanked flag, requires_python. Cadence metrics (`releasesLast90d`, `daysSinceLastRelease`, ...) are always computed.", "default": true }, "versionsLimit": { "title": "Recent versions to include", "minimum": 0, "maximum": 200, "type": "integer", "description": "How many entries to keep in `recentVersions`.", "default": 10 }, "includeClassifiers": { "title": "Include raw Trove classifiers", "type": "boolean", "description": "Full `classifiers` array. `developmentStatus`, `pythonVersions` and `licenseClassifiers` are extracted from them regardless.", "default": true }, "descriptionChars": { "title": "Long description characters", "minimum": 0, "maximum": 20000, "type": "integer", "description": "0 = omit. N = include the first N characters of the project's long description (README) as `description`, with `descriptionContentType` (text/markdown, text/x-rst...).", "default": 0 }, "fields": { "title": "Only these output fields", "type": "array", "description": "Optional whitelist of top-level output fields (e.g. [\"version\", \"license\", \"downloadsMonth\", \"vulnerabilityCount\"]). `id`, `name` and `error` are always kept. Empty = full item.", "items": { "type": "string" } } } }, "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 } } } } } } } } } }