{ "openapi": "3.0.1", "info": { "title": "Google Search Results Scraper (Question & Keyword Discovery)", "description": "Google Search Results Scraper for Question & Keyword Discovery extracts search results, related questions, autocomplete suggestions, titles, URLs, snippets, and keyword insights. Discover content opportunities, search intent, long-tail keywords, and topics for SEO and market research.", "version": "0.1", "x-build-id": "GgvIO9t7wcqQGJAHy" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/simpleapi~google-search-results-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-simpleapi-google-search-results-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/simpleapi~google-search-results-scraper/runs": { "post": { "operationId": "runs-sync-simpleapi-google-search-results-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/simpleapi~google-search-results-scraper/run-sync": { "post": { "operationId": "run-sync-simpleapi-google-search-results-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "๐Ÿ”Ž Seed keywords or Google Search URLs", "type": "string", "description": "One seed per line. Plain keywords, Google operators (site:example.com, javascript OR python) or pasted google.com/search URLs all work. Each seed becomes one discovery job: SERP results plus its related searches, autocomplete completions and People-also-ask questions. Keep every line under 32 words." }, "resultsPerPage": { "title": "๐Ÿ“Š Organic results per page (num)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Passed to Google as the num parameter. Google applies its own filtering, so the returned count often differs. This setting does not affect the discovery blocks (related searches / questions / autocomplete).", "default": 100 }, "maxPagesPerQuery": { "title": "๐Ÿ“‘ SERP pages per seed", "minimum": 1, "type": "integer", "description": "How many result pages to walk per seed. Discovery runs once per seed regardless of this number, so raising it does not multiply discovery requests.", "default": 1 }, "aiMode": { "title": "โฉ Add-on: Google AI Mode ($)", "enum": [ "aiModeOff", "aiModeWithSearchResults", "aiModeOnly" ], "type": "string", "description": "Kept from the base actor. Selecting a non-off mode drops udm=14 from the primary request and, together with a SerpApi key below, fills aiOverview. The discovery blocks in this Actor do not depend on it - they use their own request.", "default": "aiModeOff" }, "serpApiKey": { "title": "๐Ÿ”‘ SerpApi key (only for aiOverview)", "type": "string", "description": "Optional. When set and AI Mode is not off, aiOverview is fetched through SerpApi using your own account. Leave empty to skip." }, "perplexitySearch": { "title": "โฉ Add-on: Perplexity AI search (not implemented)", "type": "object", "description": "Retained for backward compatibility with the base actor's input. This Actor does not call Perplexity: the object is echoed verbatim into customData and has no other effect.", "properties": { "enablePerplexity": { "title": "โœจ Enable Perplexity AI", "type": "boolean", "description": "Fetch AI answer using Perplexity Sonar model.", "default": false }, "searchRecency": { "title": "๐Ÿ” Search Recency", "type": "string", "description": "Specify the time range for Perplexity search results.", "editor": "select", "nullable": true, "enum": [ "", "day", "week", "month", "year" ], "enumTitles": [ "None", "day", "week", "month", "year" ] }, "returnImages": { "title": "๐Ÿ–ผ๏ธ Include images in Perplexity AI answers", "type": "boolean", "description": "Include images in Perplexity response.", "default": false }, "returnRelatedQuestions": { "title": "โ“ Include related questions in Perplexity AI answers", "type": "boolean", "description": "Include related questions in Perplexity response.", "default": false } }, "default": { "enablePerplexity": false, "searchRecency": "", "returnImages": false, "returnRelatedQuestions": false } }, "chatGptSearch": { "title": "โฉ Add-on: ChatGPT Search (not implemented)", "type": "object", "description": "Retained for backward compatibility with the base actor's input. This Actor does not call ChatGPT: the object is echoed verbatim into customData and has no other effect.", "properties": { "enableChatGpt": { "title": "๐Ÿ’ฌ Enable ChatGPT search", "type": "boolean", "description": "Fetch AI answer using OpenAI search model.", "default": false } }, "default": { "enableChatGpt": false } }, "maximumLeadsEnrichmentRecords": { "title": "โฉ Add-on: leads per domain (not implemented)", "minimum": 0, "type": "integer", "description": "Retained for backward compatibility with the base actor's input. No lead data is collected; the value is echoed into customData and has no other effect.", "default": 0 }, "leadsEnrichmentDepartments": { "title": "๐Ÿข Leads departments (not implemented)", "type": "array", "description": "Retained for backward compatibility. Echoed into customData; no lead data is collected.", "items": { "type": "string", "enum": [ "c-suite", "product", "engineering-technical", "design", "education", "finance", "human-resources", "information-technology", "legal", "marketing", "medical-health", "operations", "sales", "consulting" ], "enumTitles": [ "C-Suite", "Product", "Engineering & Technical", "Design", "Education", "Finance", "Human Resources", "Information Technology", "Legal", "Marketing", "Medical & Health", "Operations", "Sales", "Consulting" ] }, "default": [] }, "focusOnPaidAds": { "title": "๐Ÿ’ฐ Add-on: retry pages that show no ads", "type": "boolean", "description": "When enabled, a page that parsed zero ads and zero shopping products is fetched once more on the same proxy before the row is pushed. Google injects ad markup with JavaScript, so paidResults is frequently empty over the HTTP path.", "default": false }, "countryCode": { "title": "๐ŸŒ Country (gl)", "enum": [ "af", "al", "dz", "as", "ad", "ao", "ai", "aq", "ag", "ar", "am", "aw", "au", "at", "az", "bs", "bh", "bd", "bb", "by", "be", "bz", "bj", "bm", "bt", "bo", "ba", "bw", "bv", "br", "io", "bn", "bg", "bf", "bi", "kh", "cm", "ca", "cv", "ky", "cf", "td", "cl", "cn", "cx", "cc", "co", "km", "cg", "cd", "ck", "cr", "ci", "hr", "cu", "cy", "cz", "dk", "dj", "dm", "do", "ec", "eg", "sv", "gq", "er", "ee", "et", "fk", "fo", "fj", "fi", "fr", "gf", "pf", "tf", "ga", "gm", "ge", "de", "gh", "gi", "gr", "gl", "gd", "gp", "gu", "gt", "gn", "gw", "gy", "ht", "hm", "va", "hn", "hk", "hu", "is", "in", "id", "ir", "iq", "ie", "il", "it", "jm", "jp", "jo", "kz", "ke", "ki", "kp", "kr", "kw", "kg", "la", "lv", "lb", "ls", "lr", "ly", "li", "lt", "lu", "mo", "mk", "mg", "mw", "my", "mv", "ml", "mt", "mh", "mq", "mr", "mu", "yt", "mx", "fm", "md", "mc", "mn", "ms", "ma", "mz", "mm", "na", "nr", "np", "nl", "an", "nc", "nz", "ni", "ne", "ng", "nu", "nf", "mp", "no", "om", "pk", "pw", "ps", "pa", "pg", "py", "pe", "ph", "pn", "pl", "pt", "pr", "qa", "re", "ro", "ru", "rw", "sh", "kn", "lc", "pm", "vc", "ws", "sm", "st", "sa", "sn", "cs", "sc", "sl", "sg", "sk", "si", "sb", "so", "za", "gs", "es", "lk", "sd", "sr", "sj", "sz", "se", "ch", "sy", "tw", "tj", "tz", "th", "tl", "tg", "tk", "to", "tt", "tn", "tr", "tm", "tc", "tv", "ug", "ua", "ae", "gb", "us", "um", "uy", "uz", "vu", "ve", "vn", "vg", "vi", "wf", "eh", "ye", "zm", "zw" ], "type": "string", "description": "Sent to Google as the gl parameter. It also decides which country's autocomplete completions and related searches you get. The request always goes to www.google.com.", "default": "us" }, "searchLanguage": { "title": "๐Ÿ”ค Restrict results to language (lr)", "enum": [ "", "ar", "bg", "ca", "cs", "da", "de", "el", "en", "es", "et", "fi", "fr", "hr", "hu", "id", "is", "it", "iw", "ja", "ko", "lt", "lv", "nl", "no", "pl", "pt", "ro", "ru", "sk", "sl", "sr", "sv", "tr", "zh-CN", "zh-TW" ], "type": "string", "description": "Restricts results to pages written in one language. Sent as lr=lang_xx." }, "languageCode": { "title": "๐Ÿ—ฃ๏ธ Interface language (hl)", "enum": [ "af", "sq", "sm", "ar", "az", "eu", "be", "bn", "bh", "bs", "bg", "ca", "zh-CN", "zh-TW", "hr", "cs", "da", "nl", "en", "eo", "et", "fo", "fi", "fr", "fy", "gl", "ka", "de", "el", "gu", "iw", "hi", "hu", "is", "id", "ia", "ga", "it", "ja", "jw", "kn", "ko", "la", "lv", "lt", "mk", "ms", "ml", "mt", "mr", "ne", "no", "nn", "oc", "fa", "pl", "pt-BR", "pt-PT", "pa", "ro", "ru", "gd", "sr", "si", "sk", "sl", "es", "su", "sw", "sv", "tl", "ta", "te", "th", "ti", "tr", "uk", "ur", "uz", "vi", "cy", "xh", "zu" ], "type": "string", "description": "Sent as hl. It drives the language of the questions, related searches and autocomplete completions you get back, so set it to the market you are researching.", "default": "en" }, "locationUule": { "title": "๐Ÿ“ Exact place (UULE)", "type": "string", "description": "Google UULE location code, sent as the uule parameter." }, "forceExactMatch": { "title": "๐ŸŽฏ Wrap the seed in quotes", "type": "boolean", "description": "Wraps the whole seed in quotation marks for an exact-phrase search. Narrows results and usually shrinks the related-searches block.", "default": false }, "site": { "title": "๐ŸŒ Only this site (site:)", "type": "string", "description": "Adds site:example.com. Takes precedence over 'Related to site'." }, "relatedToSite": { "title": "๐Ÿ”— Sites related to (related:)", "type": "string", "description": "Adds related:example.com. Ignored when 'Only this site' is filled in." }, "wordsInTitle": { "title": "๐Ÿ“ Words in the title (intitle:)", "maxItems": 32, "type": "array", "description": "Each entry becomes intitle:\"word\".", "default": [], "items": { "type": "string" } }, "wordsInText": { "title": "๐Ÿ“„ Words in the body (intext:)", "maxItems": 32, "type": "array", "description": "Each entry becomes intext:\"word\".", "default": [], "items": { "type": "string" } }, "wordsInUrl": { "title": "๐Ÿ”— Words in the URL (inurl:)", "maxItems": 32, "type": "array", "description": "Each entry becomes inurl:\"word\".", "default": [], "items": { "type": "string" } }, "quickDateRange": { "title": "โฑ๏ธ Quick recency (tbs=qdr:)", "type": "string", "description": "d7, w2, m6, y1 ... sent as tbs=qdr:. Do not combine with the before/after dates." }, "beforeDate": { "title": "๐Ÿ“… Published before", "pattern": "^(\\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$|^(\\d+)\\s*(day|week|month|year)s?$", "type": "string", "description": "Absolute (2024-05-03) or relative (8 days, 3 months). UTC." }, "afterDate": { "title": "๐Ÿ“† Published after", "pattern": "^(\\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$|^(\\d+)\\s*(day|week|month|year)s?$", "type": "string", "description": "Absolute (2024-05-03) or relative (8 days, 3 months). UTC." }, "fileTypes": { "title": "๐Ÿ“Ž File types (filetype:)", "maxItems": 10, "type": "array", "description": "OR-joined into filetype: operators.", "items": { "type": "string", "enum": [ "pdf", "csv", "epub", "ps", "htm", "html", "xls", "xlsx", "ppt", "pptx", "doc", "docx", "odp", "ods", "odt", "rtf", "svg", "tex", "txt", "wml", "wap", "xml", "xps", "md", "readme", "log", "yml", "yaml", "toml", "ipynb", "sas", "sql", "rdf", "avif", "avi", "mkv", "mov", "flv", "asf", "ogv" ], "enumTitles": [ "Adobe Portable Document Format (pdf)", "Comma-Separated Values (csv)", "Electronic Publication (epub)", "Adobe PostScript (ps)", "HTML (htm)", "HTML (html)", "Microsoft Excel (xls)", "Microsoft Excel (xlsx)", "Microsoft PowerPoint (ppt)", "Microsoft PowerPoint (pptx)", "Microsoft Word (doc)", "Microsoft Word (docx)", "OpenOffice presentation (odp)", "OpenOffice spreadsheet (ods)", "OpenOffice text (odt)", "Rich Text Format (rtf)", "Scalable Vector Graphics (svg)", "TeX/LaTeX (tex)", "Text (txt)", "Wireless Markup Language (wml)", "Wireless Markup Language (wap)", "XML (xml)", "XML Paper Specification (xps)", "Markdown (md)", "Readme (readme)", "Log file (log)", "YAML (yml)", "YAML (yaml)", "TOML (toml)", "Jupyter Notebook (ipynb)", "SAS (sas)", "SQL (sql)", "Resource Description Framework (rdf)", "AV1 Image File Format (avif)", "Audio Video Interleave (avi)", "Matroska Multimedia Container (mkv)", "QuickTime Movie (mov)", "Flash Video (flv)", "Advanced Systems Format (asf)", "Ogg Video (ogv)" ] }, "default": [] }, "mobileResults": { "title": "๐Ÿ“ฑ Use a mobile user agent", "type": "boolean", "description": "Switches the user-agent pool. Note that searchQuery.device is reported as DESKTOP either way, exactly as in the base actor.", "default": false }, "includeUnfilteredResults": { "title": "๐Ÿ”“ Add tbs=li:1 to the query", "type": "boolean", "description": "Sends tbs=li:1. Note this is Google's VERBATIM switch, which narrows rather than widens the result set - the name is inherited from the base actor's input schema.", "default": false }, "saveHtml": { "title": "๐Ÿ’พ Attach page HTML to each row", "type": "boolean", "description": "Stores the raw HTML of every SERP page in the html field. Makes the dataset very large.", "default": false }, "saveHtmlToKeyValueStore": { "title": "๐Ÿ—„๏ธ Store page HTML in the key-value store", "type": "boolean", "description": "Writes each SERP page to the run's key-value store. htmlSnapshotUrl then carries the record KEY of the first page.", "default": true }, "includeIcons": { "title": "๐Ÿ–ผ๏ธ Include result favicons when present", "type": "boolean", "description": "Adds an icon field to organic results whose card exposes a favicon URL.", "default": false }, "proxyConfiguration": { "title": "๐Ÿ”’ Proxy", "type": "object", "description": "Google SERP proxy by default, escalating to residential (3 retries, then sticky) when a page comes back without any result container. There is no no-proxy or datacenter tier." }, "includeRelatedSearches": { "title": "๐Ÿ” Collect Google's real related searches", "type": "boolean", "description": "Reads the genuine related-searches block Google renders at the bottom of the page (#botstuff). The numeric pagination strip that lives in the same node is excluded. Output: relatedSearches[].", "default": true }, "includeAutocompleteSuggestions": { "title": "โŒจ๏ธ Collect Google Autocomplete completions", "type": "boolean", "description": "Calls Google's completion service for the seed and attaches the completions to the SERP row as autocompleteSuggestions[]. This is one signal on the SERP row, not a standalone autocomplete export.", "default": true }, "autocompleteAlphabetFanOut": { "title": "๐Ÿ”  A-Z autocomplete fan-out", "type": "boolean", "description": "Also requests completions for ' a' through ' z'. Adds 26 keyless requests per seed and typically multiplies the completion count several times over. Off by default.", "default": false }, "expandPeopleAlsoAsk": { "title": "โ“ Collect People-also-ask questions", "type": "boolean", "description": "Collects the real People-also-ask questions Google prints on the results page into expandedQuestions[]. Answers are NOT returned: Google serves no answer-box or expansion payload to a server-side exit (measured - see the README limits section). The base peopleAlsoAsk field is left exactly as the base produced it.", "default": true }, "maxQuestionsPerQuery": { "title": "๐Ÿงฎ Max questions per seed", "minimum": 0, "maximum": 100, "type": "integer", "description": "Caps how many People-also-ask questions are returned per seed. Google normally prints 4-8 of them on one page. Set to 0 to skip questions entirely. Default 5.", "default": 5 }, "includeKeywordIdeas": { "title": "๐Ÿ’ก Merge everything into keywordIdeas[]", "type": "boolean", "description": "Builds one de-duplicated list of every real phrase Google returned - related searches, autocomplete completions and question texts - each with the sources it came from.", "default": true }, "useFullResultsPage": { "title": "๐Ÿงช Fetch the full results page for discovery", "type": "boolean", "description": "The base actor sends udm=14 whenever AI Mode is off, and that page carries NO People-also-ask block and NO related searches. This option issues one extra request per seed WITHOUT udm=14 to read them. The primary SERP request is never modified. Turn this off to make the Actor issue exactly the same requests as the base actor - discovery fields then come back null except autocomplete.", "default": true }, "deduplicateResultsAcrossPages": { "title": "๐Ÿงน De-duplicate organic results across pages", "type": "boolean", "description": "The base actor makes page N's row re-contain the organic results of pages 1..N, and every page is a separate charged row. Default false keeps that behaviour byte-for-byte. Set true to make each row carry only the results of its own page.", "default": false }, "saveQuestionsToSeparateDataset": { "title": "๐Ÿ—ƒ๏ธ Mirror questions to a second dataset", "type": "boolean", "description": "Also writes one row per question to a named dataset '-questions'. The mirror is never charged; the SERP rows in the default dataset are unaffected.", "default": false } } }, "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 } } } } } } } } } }