{ "openapi": "3.0.1", "info": { "title": "GitLab Projects Scraper — Repositories, Star Velocity & Topi", "description": "Scrape public GitLab projects, repositories, star counts, forks, topic tags, and open issues via the official REST API. Tech scouting and enterprise open-source intelligence.", "version": "0.1", "x-build-id": "sJSQPLWsksLCkOBaw" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/spotless_studios~gitlab-projects-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-spotless_studios-gitlab-projects-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/spotless_studios~gitlab-projects-scraper/runs": { "post": { "operationId": "runs-sync-spotless_studios-gitlab-projects-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/spotless_studios~gitlab-projects-scraper/run-sync": { "post": { "operationId": "run-sync-spotless_studios-gitlab-projects-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "gitlabUrl": { "title": "GitLab instance URL", "type": "string", "description": "Target GitLab instance URL (default 'https://gitlab.com', or any public self-hosted instance like 'https://gitlab.gnome.org' or 'https://gitlab.freedesktop.org').", "default": "https://gitlab.com" }, "searchQuery": { "title": "Search query / keywords", "type": "string", "description": "Search project names and descriptions (e.g. 'kubernetes', 'cicd', 'security', 'embedded').", "default": "kubernetes" }, "searchQueries": { "title": "Multiple search queries", "type": "array", "description": "Optional list of multiple search queries to run sequentially in a single job.", "items": { "type": "string" } }, "topic": { "title": "Topic tag", "type": "string", "description": "Filter by GitLab project topic tag (e.g. 'docker', 'rust', 'linux', 'machine-learning')." }, "topics": { "title": "Multiple topic tags", "type": "array", "description": "Filter across multiple GitLab topic tags.", "items": { "type": "string" } }, "minStars": { "title": "Minimum stars", "minimum": 0, "type": "integer", "description": "Minimum star count." }, "maxStars": { "title": "Maximum stars", "minimum": 0, "type": "integer", "description": "Maximum star count." }, "minForks": { "title": "Minimum forks", "minimum": 0, "type": "integer", "description": "Minimum fork count." }, "orderBy": { "title": "Order by", "enum": [ "star_count", "last_activity_at", "created_at", "updated_at", "name", "similarity" ], "type": "string", "description": "Field to order projects by.", "default": "star_count" }, "sort": { "title": "Sort direction", "enum": [ "desc", "asc" ], "type": "string", "description": "Descending or ascending.", "default": "desc" }, "createdAfter": { "title": "Created after", "type": "string", "description": "Only keep projects created after this date (YYYY-MM-DD, ISO, or relative like '90 days')." }, "lastActivityAfter": { "title": "Last activity after", "type": "string", "description": "Only keep projects active after this date (YYYY-MM-DD, ISO, or relative like '30 days')." }, "includeArchived": { "title": "Include archived projects", "type": "boolean", "description": "Include read-only archived projects.", "default": false }, "projectPaths": { "title": "Direct project paths, IDs or URLs", "type": "array", "description": "Scrape specific GitLab projects directly by 'group/project' path, numeric ID, or URL (e.g. 'gitlab-org/gitlab', 'https://gitlab.com/inkscape/inkscape').", "items": { "type": "string" } }, "includeLanguages": { "title": "Include programming language breakdown", "type": "boolean", "description": "Fetch each project's language breakdown to populate primaryLanguage and languages (% share per language).", "default": false }, "gitlabToken": { "title": "Optional GitLab Personal Access Token", "type": "string", "description": "Optional GitLab PAT for higher rate limits or private/internal project access." }, "includeKeywords": { "title": "Include keywords", "type": "array", "description": "Keep only projects matching these keywords or /regex/ in name, description, topics, or namespace.", "items": { "type": "string" } }, "excludeKeywords": { "title": "Exclude keywords", "type": "array", "description": "Skip projects matching any of these keywords or /regex/.", "items": { "type": "string" } }, "keywordMatch": { "title": "Include keyword logic", "enum": [ "any", "all" ], "type": "string", "description": "Require any or all includeKeywords to match.", "default": "any" }, "onlyNewItems": { "title": "Only new projects (monitoring mode)", "type": "boolean", "description": "Remember seen project IDs across runs and emit only newly discovered repositories.", "default": false }, "stateKey": { "title": "Monitor state name", "type": "string", "description": "Separate state key per saved search or schedule.", "default": "default" }, "maxResults": { "title": "Max results", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of projects to save.", "default": 100 }, "outputPreset": { "title": "Data preset", "enum": [ "full", "lean", "contacts" ], "type": "string", "description": "Choose full record, lean summary, or contacts & links only.", "default": "full" }, "outputFields": { "title": "Output fields", "type": "array", "description": "Keep only these specific fields in each saved record.", "items": { "type": "string" } }, "excludeFields": { "title": "Exclude fields", "type": "array", "description": "Remove specific fields from each saved record.", "items": { "type": "string" } }, "includeEmptyFields": { "title": "Keep empty / null fields", "type": "boolean", "description": "When disabled, strips null and empty values from each saved record.", "default": true }, "requiredFields": { "title": "Required non-empty fields", "type": "array", "description": "Only save records where every listed field has a non-empty value.", "items": { "type": "string" } }, "maxPages": { "title": "Max search pages", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum search pages per query (100 projects per page).", "default": 15 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 15, "type": "integer", "description": "Parallel requests when fetching direct project paths.", "default": 5 }, "maxRequestRetries": { "title": "Max retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "Retries per failed HTTP request.", "default": 3 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout per HTTP request.", "default": 30 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional proxy settings.", "default": { "useApifyProxy": false } }, "proxyEscalation": { "title": "Auto-escalate proxies when blocked", "type": "boolean", "description": "Automatically step up from direct to Apify datacenter/residential proxies if blocked.", "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 }, "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 } } } } } } } } } }