{ "openapi": "3.0.1", "info": { "title": "GitHub Scraper - Repos, Developers & Contact Leads", "description": "Scrape GitHub via the official API: search repositories & developers, get full repo metadata, README, languages, topics, stars & activity, plus developer/org profiles and contributor & stargazer leads with emails. Developer lead-gen + monitoring. No browser.", "version": "0.1", "x-build-id": "i69p6UOdRUnUDd8ib" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapesage~github-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapesage-github-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapesage~github-scraper/runs": { "post": { "operationId": "runs-sync-scrapesage-github-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapesage~github-scraper/run-sync": { "post": { "operationId": "run-sync-scrapesage-github-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Mode", "enum": [ "searchRepositories", "searchUsers", "repositoryDetails", "userProfiles", "organizationProfiles", "repositoryContributors" ], "type": "string", "description": "What to scrape. searchRepositories = find repos by keyword/filters. searchUsers = find developers by location/language/followers. repositoryDetails = full records for specific repos. userProfiles = developer leads by username. organizationProfiles = org leads. repositoryContributors = contributor/stargazer leads from a repo. Start URLs override the mode.", "default": "searchRepositories" }, "searchQueries": { "title": "Search queries", "type": "array", "description": "Keywords / phrases for searchRepositories or searchUsers mode. Each query runs separately and combines with the filters below. Examples: \"llm agent framework\", \"vector database\", \"react native\".", "items": { "type": "string" } }, "repositories": { "title": "Repositories", "type": "array", "description": "Repository names (\"owner/repo\") or URLs. Primary input for repositoryDetails and repositoryContributors modes. Examples: \"facebook/react\", \"https://github.com/vercel/next.js\".", "items": { "type": "string" } }, "usernames": { "title": "Usernames (developers)", "type": "array", "description": "GitHub usernames for userProfiles mode. Examples: \"torvalds\", \"gaearon\", \"sindresorhus\".", "items": { "type": "string" } }, "organizations": { "title": "Organizations", "type": "array", "description": "GitHub organization logins for organizationProfiles mode. Examples: \"vercel\", \"openai\", \"microsoft\".", "items": { "type": "string" } }, "startUrls": { "title": "Start URLs", "type": "array", "description": "GitHub URLs to scrape directly (auto-routed). Repo URLs (github.com/owner/repo), user URLs (github.com/torvalds) and org URLs (github.com/orgs/vercel) are all supported.", "items": { "type": "string" } }, "language": { "title": "Programming language", "type": "string", "description": "Repository language filter (searchRepositories). Examples: \"JavaScript\", \"Python\", \"Rust\", \"Go\"." }, "minStars": { "title": "Minimum stars", "minimum": 0, "type": "integer", "description": "Only repositories with at least this many stars." }, "maxStars": { "title": "Maximum stars", "minimum": 0, "type": "integer", "description": "Only repositories with at most this many stars (combine with minStars to window large topics past the 1,000-result cap)." }, "topics": { "title": "Topics", "type": "array", "description": "Require these GitHub topics, e.g. \"machine-learning\", \"hacktoberfest\", \"cli\".", "items": { "type": "string" } }, "repoLicense": { "title": "License", "type": "string", "description": "Require a license (SPDX-ish key), e.g. \"mit\", \"apache-2.0\", \"gpl-3.0\"." }, "repoCreatedAfter": { "title": "Created after (YYYY-MM-DD)", "type": "string", "description": "Only repositories created on/after this date." }, "repoPushedAfter": { "title": "Pushed after (YYYY-MM-DD)", "type": "string", "description": "Only repositories with a commit pushed on/after this date — great for finding actively maintained projects." }, "includeForks": { "title": "Include forks", "type": "boolean", "description": "Include forked repositories in repository search results.", "default": false }, "onlyActive": { "title": "Only active (not archived)", "type": "boolean", "description": "Exclude archived repositories.", "default": false }, "userLocation": { "title": "Developer location", "type": "string", "description": "Location filter for searchUsers, e.g. \"San Francisco\", \"Berlin\", \"London\". Matches the free-text GitHub location field." }, "userLanguage": { "title": "Developer language", "type": "string", "description": "Primary language filter for searchUsers (their most-used repo language), e.g. \"Python\", \"TypeScript\"." }, "minFollowers": { "title": "Minimum followers", "minimum": 0, "type": "integer", "description": "Only developers/orgs with at least this many followers." }, "minRepos": { "title": "Minimum public repos", "minimum": 0, "type": "integer", "description": "Only developers/orgs with at least this many public repositories." }, "userType": { "title": "Account type", "enum": [ "user", "org", "any" ], "type": "string", "description": "Restrict searchUsers to individual developers or organizations.", "default": "user" }, "extraQualifiers": { "title": "Extra search qualifiers", "type": "string", "description": "Advanced: raw GitHub search qualifiers appended to the query verbatim, e.g. \"sponsorable:true\" or \"created:>2023-01-01\". See GitHub search syntax docs." }, "sortBy": { "title": "Sort by", "enum": [ "best-match", "stars", "forks", "updated", "help-wanted-issues", "followers", "repositories", "joined" ], "type": "string", "description": "Result ordering. Repos: stars / forks / updated / help-wanted-issues. Users: followers / repositories / joined. \"best-match\" is GitHub's relevance ranking.", "default": "best-match" }, "sortOrder": { "title": "Sort order", "enum": [ "desc", "asc" ], "type": "string", "description": "Direction for the sort field above (ignored for best-match).", "default": "desc" }, "maxResults": { "title": "Max records (total)", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Total cap on records emitted across all queries/inputs in this run.", "default": 50 }, "maxResultsPerQuery": { "title": "Max records per query", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Optional cap per individual query (0 = no per-query cap). GitHub search serves up to 1,000 results per query — window with minStars/maxStars or dates to go deeper.", "default": 0 }, "peopleSource": { "title": "People to extract (contributors mode)", "enum": [ "contributors", "stargazers", "both" ], "type": "string", "description": "For repositoryContributors mode: pull a repo's contributors, its stargazers, or both — each as a developer-lead record.", "default": "contributors" }, "extractCommitEmails": { "title": "Extract developer emails from commits", "type": "boolean", "description": "For developer/contributor records, read the user's public commit activity (and a repo's recent commits) to recover their public commit email — the core lead wedge. GitHub no-reply addresses are filtered out. One extra request per developer.", "default": true }, "enrichContactEmails": { "title": "Enrich from personal website", "type": "boolean", "description": "Crawl each developer's/org's website (their GitHub 'blog' field) home + /contact + /about for extra emails, phone and social links. Opt-in (charged as contact enrichment).", "default": false }, "includeUserRepos": { "title": "Include developer's top repos", "type": "boolean", "description": "For developer/org records, attach their top repositories (by stars) and derived top languages. One extra request per developer.", "default": false }, "maxReposPerUser": { "title": "Max repos per developer", "minimum": 0, "maximum": 100, "type": "integer", "description": "Cap on a developer's top repos attached when 'Include developer's top repos' is on.", "default": 10 }, "includeReadme": { "title": "Include README", "type": "boolean", "description": "For repository records, fetch and attach the README text (truncated to ~8,000 chars) + word count. One extra request per repo.", "default": false }, "includeLanguages": { "title": "Include language breakdown", "type": "boolean", "description": "For repository records, attach the full language breakdown with byte counts and percentages. One extra request per repo.", "default": false }, "includeLatestRelease": { "title": "Include latest release", "type": "boolean", "description": "For repository records, attach the latest release (tag, name, date). One extra request per repo.", "default": false }, "includeContributorsCount": { "title": "Include contributors count", "type": "boolean", "description": "For repository records, compute the total contributor count. One extra request per repo.", "default": false }, "includeOwnerProfile": { "title": "Include repo owner profile", "type": "boolean", "description": "For repository records, attach the owner's profile lead fields (name, company, blog, location, email, followers). One extra request per repo.", "default": false }, "withEmailOnly": { "title": "Only records with an email", "type": "boolean", "description": "Emit only developer/org records for which at least one email was found.", "default": false }, "hireableOnly": { "title": "Only hireable developers", "type": "boolean", "description": "Emit only developers whose profile is flagged 'available for hire'. Great for technical recruiting.", "default": false }, "monitorMode": { "title": "Monitor mode (only new records)", "type": "boolean", "description": "Remember repos/developers/orgs seen in previous runs (in a named key-value store) and emit only NEW ones. Pair with Apify Schedules to watch a topic, company, or repo for new projects, contributors or stargazers. Does not conflict with scheduling.", "default": false }, "monitorStoreName": { "title": "Monitor store name", "type": "string", "description": "Named key-value store that holds the 'already seen' keys for monitor mode. Use a distinct name per saved task so their histories stay separate.", "default": "github-monitor" }, "githubToken": { "title": "GitHub token (optional, strongly recommended)", "type": "string", "description": "A GitHub personal access token (classic or fine-grained, read-only is enough). Without it GitHub allows only ~60 requests/hour per IP; with it you get 5,000/hour and 30 searches/minute — much faster, larger runs. Create one at github.com/settings/tokens." }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 16, "type": "integer", "description": "Maximum API requests in parallel.", "default": 6 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. The GitHub API has no anti-bot; a proxy is used to spread the per-IP rate limit across IPs when running without a token. The default Apify proxy is fine.", "default": { "useApifyProxy": 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 } } } } } } } } } }