{ "openapi": "3.0.1", "info": { "title": "Google SERP Scraper — Organic, AI Overviews & Leads", "description": "Scrape Google Search without an API key: ranked organic results, People Also Ask, related searches, shopping, knowledge panel and local pack, plus the AI Overview with every cited source resolved to a domain and citation index.", "version": "0.0", "x-build-id": "acp8HuTNLvz7tYJpw" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/brilliant_gum~google-serp-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-brilliant_gum-google-serp-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/brilliant_gum~google-serp-scraper/runs": { "post": { "operationId": "runs-sync-brilliant_gum-google-serp-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/brilliant_gum~google-serp-scraper/run-sync": { "post": { "operationId": "run-sync-brilliant_gum-google-serp-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "queries" ], "properties": { "queries": { "title": "Search queries or Google URLs", "type": "array", "description": "Search terms OR raw Google search URLs. A full https://www.google.com/search?q=... URL is used verbatim (missing params are filled in).", "default": [ "best running shoes 2026" ], "items": { "type": "string" } }, "maxResultsPerQuery": { "title": "Max organic results per page (num)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Target number of organic results per SERP page (Google 'num'). Note: Google deprecated num=100 in Sep 2025; values <= ~20 are reliable. Alias: num.", "default": 10 }, "maxPagesPerQuery": { "title": "Max pages per query", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many SERP pages to paginate per query.", "default": 1 }, "includeUnfilteredResults": { "title": "Include unfiltered results", "type": "boolean", "description": "Append &filter=0 to include omitted / near-duplicate results.", "default": false }, "countryCode": { "title": "Country (gl)", "type": "string", "description": "Country of the search (Google 'gl'). Alias: gl.", "default": "us" }, "languageCode": { "title": "Language (hl)", "type": "string", "description": "Interface / results language (Google 'hl'). Alias: hl.", "default": "en" }, "searchLanguage": { "title": "Restrict results to language (lr)", "type": "string", "description": "Google 'lr', e.g. lang_en." }, "locationUule": { "title": "Pre-computed location string", "type": "string", "description": "Pre-computed canonical location string, for advanced users. Overrides locationName." }, "locationName": { "title": "Location name", "type": "string", "description": "Human location, e.g. 'New York,New York,United States'. Encoded for you automatically." }, "googleDomain": { "title": "Google domain", "type": "string", "description": "Google host to query, e.g. google.com or google.co.uk.", "default": "google.com" }, "resultLanguage": { "title": "Result country restrict (cr)", "type": "string", "description": "Google 'cr', e.g. countryUS." }, "device": { "title": "Device", "enum": [ "desktop", "mobile" ], "type": "string", "description": "Device layout / header fingerprint.", "default": "desktop" }, "safeSearch": { "title": "SafeSearch", "enum": [ "off", "active", "nfpr" ], "type": "string", "description": "off | active | nfpr (nfpr disables spelling auto-correction, &nfpr=1).", "default": "off" }, "quickDateRange": { "title": "Quick date range", "enum": [ "", "h", "d", "w", "m", "y" ], "type": "string", "description": "Recency filter -> tbs=qdr:*.", "default": "" }, "beforeDate": { "title": "Before date", "type": "string", "description": "Upper bound YYYY-MM-DD (tbs cdr cd_max)." }, "afterDate": { "title": "After date", "type": "string", "description": "Lower bound YYYY-MM-DD (tbs cdr cd_min)." }, "tbs": { "title": "Raw tbs", "type": "string", "description": "Raw tbs passthrough (overrides quickDateRange / before / after)." }, "forceExactMatch": { "title": "Force exact match", "type": "boolean", "description": "Wrap the whole query in quotes.", "default": false }, "site": { "title": "site:", "type": "string", "description": "Restrict to a site (site: operator)." }, "relatedToSite": { "title": "related:", "type": "string", "description": "related: operator." }, "wordsInTitle": { "title": "Words in title", "type": "string", "description": "intitle: / allintitle: operator." }, "wordsInText": { "title": "Words in text", "type": "string", "description": "intext: operator." }, "wordsInUrl": { "title": "Words in URL", "type": "string", "description": "inurl: operator." }, "fileTypes": { "title": "File types", "type": "string", "description": "filetype: operator. Comma list -> OR group." }, "excludeWords": { "title": "Exclude words", "type": "string", "description": "Space/comma list; each term is prefixed with '-'." }, "includeOrganic": { "title": "Include organic results", "type": "boolean", "description": "Include organic search results in the output.", "default": true }, "includeAds": { "title": "Include ads", "type": "boolean", "description": "Include paid ad results (when Google serves them).", "default": false }, "includePeopleAlsoAsk": { "title": "Include People Also Ask", "type": "boolean", "description": "Include the People Also Ask questions block.", "default": false }, "includeRelatedSearches": { "title": "Include related searches", "type": "boolean", "description": "Include the related searches shown at the bottom of the page.", "default": false }, "includeFeaturedSnippet": { "title": "Include featured snippet", "type": "boolean", "description": "Include the featured snippet (answer box) when present.", "default": false }, "includeKnowledgePanel": { "title": "Include knowledge panel", "type": "boolean", "description": "Include the knowledge panel (entity card) when present.", "default": false }, "includeLocalPack": { "title": "Include local pack", "type": "boolean", "description": "Include the local pack (map business results) when present.", "default": false }, "includeShopping": { "title": "Include shopping", "type": "boolean", "description": "Include shopping / popular product results when present.", "default": false }, "includeAiOverview": { "title": "Include AI Overview", "type": "boolean", "description": "Parse the AI Overview block (text + source domains + citation index). Opt-in add-on.", "default": true }, "includeAiMode": { "title": "Include AI Mode", "type": "boolean", "description": "Attempt to capture AI Mode (usually requires JS rendering).", "default": false }, "aiOverviewMode": { "title": "AI Overview capture mode", "enum": [ "http", "render" ], "type": "string", "description": "How to capture the AI Overview. 'http' (cheap default) parses the AIO from the search HTML — fast, but Google often defers the AIO behind a JS token, so it is captured only opportunistically (captureType async_pending / not_present). 'render' keeps the cheap HTTP pass for organic results and, whenever HTTP did NOT already return a full AIO, escalates that query to a real headless Chromium (also over the default proxy) that runs Google's JS to reliably render/expand the AI Overview (captureType 'rendered'). Render is slower and uses more CPU/memory. Requires the Playwright browser image.", "default": "http" }, "includeWebsiteContent": { "title": "Scrape organic page content", "type": "boolean", "description": "Opt-in: fetch each organic result URL and extract title, meta description and page text. NOTE: with the default proxy setting the result URL is the site ORIGIN only (deep paths are encrypted), so content is the landing/home page. Fetched directly (the default proxy serves only Google).", "default": false }, "websiteContentMaxPages": { "title": "Max organic pages to scrape content from", "minimum": 1, "maximum": 50, "type": "integer", "description": "Cap on how many organic URLs per SERP page are fetched when 'Scrape organic page content' is on.", "default": 10 }, "enrichLeads": { "title": "Enrich leads from result domains", "type": "boolean", "description": "Opt-in lead enrichment. After organic results are gathered, the top result domains are crawled for contacts — named people from team/about pages plus emails, phones and socials that the site publishes. `email` is filled only from an address found on the site; when none exists, a name-derived candidate appears in `emailGuess`, marked as an unverified guess.", "default": false }, "maximumLeadsEnrichmentRecords": { "title": "Max leads per query", "minimum": 1, "maximum": 100, "type": "integer", "description": "Cap on the number of leads returned per query. Also bounds how many of the top organic domains are crawled.", "default": 5 }, "leadsEnrichmentDepartments": { "title": "Lead departments (filter)", "type": "array", "description": "Optional. Keep only named people whose inferred department is in this list. Leave empty to keep all.", "items": { "type": "string", "enum": [ "executive", "engineering", "product", "sales", "marketing", "finance", "hr", "operations", "legal", "it" ], "enumTitles": [ "Executive", "Engineering", "Product", "Sales", "Marketing", "Finance", "HR", "Operations", "Legal", "IT" ] }, "default": [] }, "verifyLeadsEnrichmentEmails": { "title": "Verify lead emails", "type": "boolean", "description": "Check each published work email. On the Apify platform outbound port 25 is filtered, so the SMTP handshake cannot run and this falls back to an MX record check: it confirms the domain accepts mail, not that the address exists (emailStatus stays \"unknown\"). Addresses are never guessed from a person's name — only ones published on the site are returned.", "default": true }, "linkProspecting": { "title": "Link prospecting", "type": "boolean", "description": "Also emit a flat outreach list (one row per crawled domain: website, contact emails, phones, socials, named-contact count) for link-building / prospecting. Attached under enrichment.linkProspects and mirrored into a 'link-prospects' dataset.", "default": false }, "leadsEnrichmentPhones": { "title": "Collect phone numbers (leads)", "type": "boolean", "description": "Harvest phone numbers during the contact crawl (attached to leads / link-prospects).", "default": false }, "leadsEnrichmentMaxPagesPerDomain": { "title": "Max pages per domain (leads crawl)", "minimum": 1, "maximum": 40, "type": "integer", "description": "How many pages to crawl on each company domain while looking for contacts. Needs to be deep enough to reach team/about/leadership/contact pages where people and emails live.", "default": 15 }, "geminiSearch": { "title": "Also query Google Gemini (BYO key)", "type": "boolean", "description": "Add a geminiResult (answer + cited sources) via the Gemini API with Google Search grounding. Requires geminiApiKey (or GEMINI_API_KEY env). Emits a 'skipped, needs key' record when the key is missing.", "default": false }, "perplexitySearch": { "title": "Also query Perplexity (BYO key)", "type": "boolean", "description": "Add a perplexityResult via the Perplexity Sonar API. Requires perplexityApiKey (or PERPLEXITY_API_KEY env).", "default": false }, "chatGptSearch": { "title": "Also query ChatGPT / OpenAI (BYO key)", "type": "boolean", "description": "Add a chatGptResult via the OpenAI Responses API with web_search. Requires openaiApiKey (or OPENAI_API_KEY env).", "default": false }, "copilotSearch": { "title": "Also query Microsoft Copilot", "type": "boolean", "description": "Add a copilotResult. Microsoft Copilot has no public bring-your-own-key answer API, so this always emits an honest 'skipped / unsupported' record.", "default": false }, "geminiApiKey": { "title": "Gemini API key", "type": "string", "description": "Google AI (Gemini) API key for geminiSearch. Kept secret; falls back to the GEMINI_API_KEY env var." }, "perplexityApiKey": { "title": "Perplexity API key", "type": "string", "description": "Perplexity API key for perplexitySearch. Kept secret; falls back to the PERPLEXITY_API_KEY env var." }, "openaiApiKey": { "title": "OpenAI API key", "type": "string", "description": "OpenAI API key for chatGptSearch. Kept secret; falls back to the OPENAI_API_KEY env var." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy. Leave the default in place — it is the configuration this Actor is tuned for, and Google refuses most other networks on the search endpoint." }, "saveHtmlToKVS": { "title": "Save raw HTML to KVS", "type": "boolean", "description": "Persist raw SERP HTML to the key-value store (debugging / AIO re-parsing).", "default": false }, "mode": { "title": "Mode", "enum": [ "fast", "full" ], "type": "string", "description": "fast = organic only (cheapest); full = all enabled blocks incl. AIO.", "default": "full" } } }, "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 } } } } } } } } } }