{ "name": "GitHub Topics Repositories API", "description": "Public GitHub repositories listed under a topic, with name, owner, description, stars, forks and language.", "api_id": "generated_047a8ebb25911ccf62f4a212", "slug": "github-topics-repositories-api", "source": { "name": "GitHub", "domain": "github.com", "url": "https://github.com/" }, "category": "public_data", "countries": [], "languages": [ "en" ], "record_types": [], "tags": [], "limitations": [ "Stars, forks and language come from each repository page, so they appear only on enriched records.", "Stars and forks are returned as text, such as \"12\", not as numbers." ], "updated": "2026-10-26", "note": "Sample records are saved samples, not a live run. CleanedWeb is not affiliated with the source.", "endpoints": [ { "endpoint_id": "generated_047a8ebb25911ccf62f4a212_search", "name": "Extract records", "description": "Return records within the accepted scope.", "definition_version": "ccb220b4bbd6870eb03e3509eb1f13351075b8dc273d35584b5d2aca6f935789", "method": "POST", "path": "/v1/catalog/public/apis/generated_047a8ebb25911ccf62f4a212/endpoints/generated_047a8ebb25911ccf62f4a212_search/run", "url": "https://broker.cleanedweb.com/v1/catalog/public/apis/generated_047a8ebb25911ccf62f4a212/endpoints/generated_047a8ebb25911ccf62f4a212_search/run", "authentication": { "type": "bearer", "scheme": "Authorization: Bearer ", "scope": "run", "note": "Reading this file and the live catalog needs no credential. A run needs a CleanedWeb account and uses the credits of its workspace.", "docs": "https://cleanedweb.com/docs/run-catalog-api/" }, "required_headers": [ { "name": "Authorization", "value": "Bearer YOUR_API_KEY", "description": "An API key with the run scope." }, { "name": "Idempotency-Key", "value": "UNIQUE_REQUEST_ID", "description": "Required. Save it before you send; reuse it only to retry the same request and to read the result. 1-200 characters: letters, numbers, . _ : -" }, { "name": "Content-Type", "value": "application/json", "description": "The body is JSON." } ], "request_body": { "input": "An object that follows input_schema.", "max_items": "Optional. Stop after this many records.", "timeout_seconds": "Optional, 60-86400, default 10800.", "wait_seconds": "Optional, 0-86400, default 90. How long the request waits before answering 202." }, "input_schema": { "type": "object", "properties": { "enrich_records": { "type": "boolean", "default": true, "description": "true: read each returned record's product/detail page and merge its fields into the record. false: return list/search-level fields only, with no detail page reads. Every returned record's detail page is read within the run's time budget; records the time budget leaves unread are returned without detail fields, and summary.record_enrichment reports how many records were enriched and why any were not (run_time_budget). Detail fields are optional." }, "continuation": { "type": "string", "minLength": 32, "maxLength": 128, "description": "Resume an unfinished collection with the continuation returned by the previous call." }, "read_on": { "type": "boolean", "default": false, "description": "With a continuation from a call that reached its max_pages or max_records, read on past that total; the limits given with this call then count from here. Limits are otherwise totals across continuation calls." }, "topics": { "type": "string", "minLength": 1, "maxLength": 200, "examples": [ "web-scraping", "python-web-scraper", "web-scraping-python", "python", "crawler", "scraping", "python-web-crawler", "webscraping", "python-projects", "github-python", "web-scraping-api", "scraper-python", "json-database-python", "python-crawler", "data-science", "web-crawler", "scrapy", "python-3", "web-crawling", "python3", "scraper", "pandas", "requests-module", "data-mining", "web-scraper", "beautifulsoup", "scraping-websites", "datamining", "scraping-api", "scraping-tool", "scraping-data", "email-scraper", "google-trends-api", "scraper-api", "google-search-scraper", "google-sheets-web-scraping", "web-scraping-google-sheets", "amazon-scraper-python", "anti-bot-page", "anti-bot", "python-spider", "web-spider", "python-scraper", "tls-client", "cloudflare-bypass", "scraping-python", "python-web-scraping", "crawling-python", "anti-bot-detection", "cf-clearance", "cloudflare-scraper", "python-tls-client", "bioinformatics", "database", "analysis", "health", "plants", "cannabis", "biological-data-analysis", "biological-data", "terpenes", "cannabis-strains", "aromatherapy", "terpene-profile", "fastapi", "imagemagick", "computer-vision", "lda", "cvpr2019", "amazon", "tkinter", "flipkart", "ecommerce-sites-amazon", "corresponding-prices", "crawling", "python-package", "youtube", "social-media", "csv", "youtube-downloader", "lxml", "youtube-crawler", "comment-parser", "youtube-scraper", "data-mining-python", "requests-library-python", "python-script", "regular-expression", "data-visualization", "data-analysis", "matplotlib", "web-mining", "urllib", "python-developer", "os-module", "cli-tool", "zoominfo-client", "leadgen", "leadgeneration", "web-harvesting", "learning", "spider", "hacktoberfest", "hacktoberfest-accepted", "frequency-lists", "word-frequency", "data", "machine-learning", "mongodb", "nosql", "pymongo", "artificial-intelligence", "scrapping", "olx", "nosql-mongodb", "downloader", "recursive", "file-download", "pdf-extractor", "price-scraper", "price-scraping", "scraping-web", "alibaba-scraper", "dynamic-website", "nstl", "dynamic-web-crawler", "pdf", "parser", "pdf-converter", "html-to-pdf", "html-to-pdf-converter" ], "x-verified-values": [ "web-scraping", "python-web-scraper", "web-scraping-python", "python", "crawler", "scraping", "python-web-crawler", "webscraping", "python-projects", "github-python", "web-scraping-api", "scraper-python", "json-database-python", "python-crawler", "data-science", "web-crawler", "scrapy", "python-3", "web-crawling", "python3", "scraper", "pandas", "requests-module", "data-mining", "web-scraper", "beautifulsoup", "scraping-websites", "datamining", "scraping-api", "scraping-tool", "scraping-data", "email-scraper", "google-trends-api", "scraper-api", "google-search-scraper", "google-sheets-web-scraping", "web-scraping-google-sheets", "amazon-scraper-python", "anti-bot-page", "anti-bot", "python-spider", "web-spider", "python-scraper", "tls-client", "cloudflare-bypass", "scraping-python", "python-web-scraping", "crawling-python", "anti-bot-detection", "cf-clearance", "cloudflare-scraper", "python-tls-client", "bioinformatics", "database", "analysis", "health", "plants", "cannabis", "biological-data-analysis", "biological-data", "terpenes", "cannabis-strains", "aromatherapy", "terpene-profile", "fastapi", "imagemagick", "computer-vision", "lda", "cvpr2019", "amazon", "tkinter", "flipkart", "ecommerce-sites-amazon", "corresponding-prices", "crawling", "python-package", "youtube", "social-media", "csv", "youtube-downloader", "lxml", "youtube-crawler", "comment-parser", "youtube-scraper", "data-mining-python", "requests-library-python", "python-script", "regular-expression", "data-visualization", "data-analysis", "matplotlib", "web-mining", "urllib", "python-developer", "os-module", "cli-tool", "zoominfo-client", "leadgen", "leadgeneration", "web-harvesting", "learning", "spider", "hacktoberfest", "hacktoberfest-accepted", "frequency-lists", "word-frequency", "data", "machine-learning", "mongodb", "nosql", "pymongo", "artificial-intelligence", "scrapping", "olx", "nosql-mongodb", "downloader", "recursive", "file-download", "pdf-extractor", "price-scraper", "price-scraping", "scraping-web", "alibaba-scraper", "dynamic-website", "nstl", "dynamic-web-crawler", "pdf", "parser", "pdf-converter", "html-to-pdf", "html-to-pdf-converter" ], "description": "Optional. Reads the site's own listing for this topics value instead of the pasted one (any value through the listing's proven URL template); its pages are read and revalidated like the collection, and every record holds the value. Omit to read the pasted listing." }, "programming_language": { "type": "string", "minLength": 1, "maxLength": 200, "examples": [ "Python", "HTML" ], "x-verified-values": [ "Python", "HTML" ], "description": "Optional. Records whose programming language is this value, read from the site's own listing for it (linked from the records); its pages are read and revalidated like the collection. Omit to read the whole collection." } }, "required": [], "additionalProperties": false, "allOf": [ { "not": { "required": [ "programming_language", "topics" ] } } ] }, "output_schema": { "type": "object", "additionalProperties": true, "required": [ "title", "url" ], "properties": { "description": { "type": "string" }, "programming_language": { "type": "string" }, "related_title": { "type": "string" }, "related_url": { "type": "string" }, "slug": { "type": "string" }, "title": { "type": "string" }, "topics": { "type": "array", "items": { "type": "string" } }, "url": { "type": "string", "format": "uri" }, "detail_description": { "type": "string" }, "formatted_description": { "type": "string" }, "topics_name": { "type": "string" }, "stargazer_count": { "type": "string" }, "watcher_count": { "type": "string" }, "forks_count": { "type": "string" }, "stargazers_path": { "type": "string" }, "watchers_path": { "type": "string" }, "fork_network_path": { "type": "string" }, "activity_path": { "type": "string" }, "report_path": { "type": "string" }, "owner_login": { "type": "string" }, "is_org": { "type": "string" }, "sponsors": { "type": "string" }, "deployments": { "type": "string" }, "packages": { "type": "string" }, "used_by": { "type": "string" }, "contributors": { "type": "string" }, "languages": { "type": "string" }, "cta": { "type": "string" }, "suggested_workflows": { "type": "string" }, "has_citation": { "type": "string" }, "is_private": { "type": "string" }, "is_template": { "type": "string" }, "is_fork": { "type": "string" }, "is_mirror": { "type": "string" }, "is_archived": { "type": "string" }, "visibility_label": { "type": "string" }, "is_advisory_workspace": { "type": "string" }, "is_org_owned": { "type": "string" }, "repository_id": { "type": "string" }, "repository_name": { "type": "string" }, "watchers_count": { "type": "string" }, "typed_forks_count": { "type": "integer", "minimum": 0, "description": "Reviewed numeric reading of forks_count; source value is preserved." }, "typed_stargazer_count": { "type": "integer", "minimum": 0, "description": "Reviewed numeric reading of stargazer_count; source value is preserved." }, "typed_watcher_count": { "type": "integer", "minimum": 0, "description": "Reviewed numeric reading of watcher_count; source value is preserved." }, "typed_watchers_count": { "type": "integer", "minimum": 0, "description": "Reviewed numeric reading of watchers_count; source value is preserved." } } }, "output_schema_note": "Some fields the source returns are not published here (identifiers, personal details and page-building noise). A record can carry fields this schema does not list, so additionalProperties is true. Do not reject a record for an extra field. The live contract, linked as live_contract, lists every field the saved definition declares.", "examples": [ { "kind": "saved_validation_records", "saved_at": "2026-10-26T03:38:05.421Z", "live_verified": false, "request": { "input": {} }, "records_shown": 2, "records_saved": 2, "records": [ { "title": "web-scraping-google-sheets", "description": "Guide to Using Google Sheets for Basic Web Scraping", "topics": [ "web-scraping", "web-crawler-python", "email-scraper", "google-trends-api", "python-web-scraper", "scraper-api", "web-scraping-python", "google-search-scraper", "google-sheets-web-scraping", "web-scraping-google-sheets" ], "url": "https://github.com/oxylabs/web-scraping-google-sheets" }, { "title": "creeper", "owner_login": "z7r1k3", "description": "Web Crawler and Scraper", "stargazer_count": "12", "forks_count": "1", "programming_language": "Python", "topics": [ "python", "windows", "macos", "linux", "cli", "crawler", "scraper", "osint", "web-crawler", "web-scraper", "information-gathering", "web-crawler-python", "redteam", "python39" ], "url": "https://github.com/z7r1k3/creeper" } ] } ], "request_example": { "body": { "input": { "topics": "web-scraping" }, "max_items": 25 }, "curl": "curl -X POST https://broker.cleanedweb.com/v1/catalog/public/apis/generated_047a8ebb25911ccf62f4a212/endpoints/generated_047a8ebb25911ccf62f4a212_search/run \\\n -H \"Authorization: Bearer YOUR_API_KEY\" \\\n -H \"Idempotency-Key: UNIQUE_REQUEST_ID\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"input\": {\n \"topics\": \"web-scraping\"\n },\n \"max_items\": 25\n}'" }, "result": { "method": "GET", "url": "https://broker.cleanedweb.com/v1/catalog/public/apis/generated_047a8ebb25911ccf62f4a212/endpoints/generated_047a8ebb25911ccf62f4a212_search/result", "note": "A run that does not end within wait_seconds answers 202. Read the result with the same API key and the same Idempotency-Key." }, "links": { "page": "https://cleanedweb.com/catalog/github-topics-repositories-api/", "markdown": "https://cleanedweb.com/catalog/github-topics-repositories-api/index.md", "live_contract": "https://app.cleanedweb.com/api/catalog/apis/generated_047a8ebb25911ccf62f4a212/endpoints/generated_047a8ebb25911ccf62f4a212_search/contract", "run_docs": "https://cleanedweb.com/docs/run-catalog-api/" } } ], "links": { "page": "https://cleanedweb.com/catalog/github-topics-repositories-api/", "markdown": "https://cleanedweb.com/catalog/github-topics-repositories-api/index.md", "contract": "https://cleanedweb.com/catalog/github-topics-repositories-api/contract.json", "catalog": "https://cleanedweb.com/catalog/", "index": "https://cleanedweb.com/catalog/index.json", "openapi": "https://cleanedweb.com/catalog/openapi.json" } }