{ "openapi": "3.0.1", "info": { "title": "Google Search Results (SERP) Scraper By Site & File Type", "description": "Scrape Google SERPs by specific websites, domains, and file types. Extract organic results, titles, URLs, snippets, rankings, and indexed PDFs or documents for SEO research, competitor analysis, site audits, and content discovery.", "version": "0.1", "x-build-id": "8CXjnQwbFCMoB4Nrf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/api-empire~google-search-results-serp-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-api-empire-google-search-results-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/api-empire~google-search-results-serp-scraper/runs": { "post": { "operationId": "runs-sync-api-empire-google-search-results-serp-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/api-empire~google-search-results-serp-scraper/run-sync": { "post": { "operationId": "run-sync-api-empire-google-search-results-serp-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "keyword" ], "properties": { "keyword": { "title": "🔍 Keywords (one search per line)", "type": "string", "description": "One search per line. Operators you type here **win** over the fields below — a line reading `site:europa.eu budget` keeps its own `site:` and the **Limit to one site** field is skipped for it, so you never end up with two `site:` operators in one query.", "default": "nike" }, "site": { "title": "🌐 Limit to one site or domain", "type": "string", "description": "Adds `site:` to the query, e.g. `europa.eu`, `docs.python.org`, `gov.uk`. Subdomains are included. A result counts as matching only when its own hostname is that domain or a subdomain of it — you can see the verdict per result in `matchedOperators`.", "default": "" }, "fileTypes": { "title": "📄 File types", "type": "array", "description": "Adds `filetype:` to the query. Pick one for a clean `filetype:pdf` search, or several for a `filetype:pdf OR filetype:docx` search. Each result then carries the file-type badge Google printed in `documentResults[].fileType`.", "items": { "type": "string", "enum": [ "pdf", "doc", "docx", "xls", "xlsx", "ppt", "pptx", "txt", "rtf", "epub", "ps", "xml", "csv", "odt", "ods", "odp" ], "enumTitles": [ "PDF", "DOC", "DOCX", "XLS", "XLSX", "PPT", "PPTX", "TXT", "RTF", "EPUB", "PS", "XML", "CSV", "ODT", "ODS", "ODP" ] }, "default": [] }, "wordsInTitle": { "title": "🏷️ Words that must be in the page title", "type": "array", "description": "Each entry becomes an `intitle:\"…\"` operator. A result matches only when the phrase really is inside the `

` Google printed.", "default": [], "items": { "type": "string" } }, "wordsInUrl": { "title": "🔗 Words that must be in the URL", "type": "array", "description": "Each entry becomes an `inurl:\"…\"` operator. Checked against the result's real URL and its printed `cite` line.", "default": [], "items": { "type": "string" } }, "forceExactMatch": { "title": "❝ Exact-phrase match", "type": "boolean", "description": "Wraps your keyword line in quotes so Google matches the phrase verbatim. The phrase is audited per result against the title and the snippet.", "default": false }, "limit": { "title": "📊 How many result pages to walk", "enum": [ "10", "20", "30", "40", "50", "100", "all" ], "type": "string", "description": "Each page returns up to 10 results. `all` walks up to 100 pages per keyword — **every page is a charged row**, so keep it low for a narrow operator search that only has one page of hits.", "default": "all" }, "include_merged": { "title": "🧩 Add a merged row per keyword", "type": "boolean", "description": "Adds **one extra row per keyword** merging every page (`searchQuery.page = \"all\"`). The audited document table is copied onto it, never re-counted.", "default": true }, "start": { "title": "⏩ Start at result #", "type": "integer", "description": "Google `start` offset for the first result. Leave empty to begin at the top." }, "page": { "title": "📄 Single page only", "type": "integer", "description": "Fetch only this page number (1 = the first page of results)." }, "country": { "title": "🌍 Country", "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", "VG", "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", "SZ", "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", "HN", "HK", "HU", "IS", "IN", "ID", "IR", "IQ", "IE", "IL", "IT", "JM", "JP", "JO", "KZ", "KE", "KI", "KW", "KG", "LA", "LV", "LB", "LS", "LR", "LY", "LI", "LT", "LU", "MO", "MG", "MW", "MY", "MV", "ML", "MT", "MH", "MQ", "MR", "MU", "YT", "MX", "FM", "MD", "MC", "MN", "MS", "MA", "MZ", "MM", "NA", "NR", "NP", "NL", "NC", "NZ", "NI", "NE", "NG", "NU", "NF", "KP", "MK", "MP", "NO", "OM", "PK", "PW", "PS", "PA", "PG", "PY", "PE", "PH", "PN", "PL", "PT", "PR", "QA", "RE", "RO", "RU", "RW", "WS", "SM", "ST", "SA", "SN", "RS", "SC", "SL", "SG", "SK", "SI", "SB", "SO", "ZA", "GS", "KR", "ES", "LK", "SH", "KN", "LC", "PM", "VC", "SD", "SR", "SJ", "SE", "CH", "SY", "TW", "TJ", "TZ", "TH", "TG", "TK", "TO", "TT", "TN", "TR", "TM", "TC", "TV", "VI", "UG", "UA", "AE", "GB", "US", "UY", "UZ", "VU", "VA", "VE", "VN", "WF", "EH", "YE", "ZM", "ZW" ], "type": "string", "description": "Main country selector — sets Google's `gl` and the default proxy region. ISO 3166 A-2." }, "gl": { "title": "🌐 GL — country of results", "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", "VG", "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", "SZ", "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", "HN", "HK", "HU", "IS", "IN", "ID", "IR", "IQ", "IE", "IL", "IT", "JM", "JP", "JO", "KZ", "KE", "KI", "KW", "KG", "LA", "LV", "LB", "LS", "LR", "LY", "LI", "LT", "LU", "MO", "MG", "MW", "MY", "MV", "ML", "MT", "MH", "MQ", "MR", "MU", "YT", "MX", "FM", "MD", "MC", "MN", "MS", "MA", "MZ", "MM", "NA", "NR", "NP", "NL", "NC", "NZ", "NI", "NE", "NG", "NU", "NF", "KP", "MK", "MP", "NO", "OM", "PK", "PW", "PS", "PA", "PG", "PY", "PE", "PH", "PN", "PL", "PT", "PR", "QA", "RE", "RO", "RU", "RW", "WS", "SM", "ST", "SA", "SN", "RS", "SC", "SL", "SG", "SK", "SI", "SB", "SO", "ZA", "GS", "KR", "ES", "LK", "SH", "KN", "LC", "PM", "VC", "SD", "SR", "SJ", "SE", "CH", "SY", "TW", "TJ", "TZ", "TH", "TG", "TK", "TO", "TT", "TN", "TR", "TM", "TC", "TV", "VI", "UG", "UA", "AE", "GB", "US", "UY", "UZ", "VU", "VA", "VE", "VN", "WF", "EH", "YE", "ZM", "ZW" ], "type": "string", "description": "Override the results country (Google `gl`). ISO 3166 A-2." }, "hl": { "title": "🈶 HL — interface language", "enum": [ "af", "ar", "hy", "be", "bg", "ca", "zh-CN", "zh-TW", "hr", "cs", "da", "nl", "en", "eo", "et", "tl", "fi", "fr", "de", "el", "iw", "hi", "hu", "is", "id", "it", "ja", "ko", "lv", "lt", "no", "fa", "pl", "pt", "ro", "ru", "sr", "sk", "sl", "es", "sw", "sv", "th", "tr", "uk", "vi" ], "type": "string", "description": "Language of the Google interface (`hl`), e.g. `en`, `fr`, `de`. The `N pages` line is only parsed in English." }, "lr": { "title": "🈺 LR — restrict content language", "enum": [ "lang_af", "lang_ar", "lang_hy", "lang_be", "lang_bg", "lang_ca", "lang_zh-CN", "lang_zh-TW", "lang_hr", "lang_cs", "lang_da", "lang_nl", "lang_en", "lang_eo", "lang_et", "lang_tl", "lang_fi", "lang_fr", "lang_de", "lang_el", "lang_iw", "lang_hi", "lang_hu", "lang_is", "lang_id", "lang_it", "lang_ja", "lang_ko", "lang_lv", "lang_lt", "lang_no", "lang_fa", "lang_pl", "lang_pt", "lang_ro", "lang_ru", "lang_sr", "lang_sk", "lang_sl", "lang_es", "lang_sw", "lang_sv", "lang_th", "lang_tr", "lang_uk", "lang_vi" ], "type": "string", "description": "Restrict results by content language (Google `lr`), e.g. `lang_en`." }, "cr": { "title": "🚩 CR — restrict country of origin", "enum": [ "countryAF", "countryAL", "countryDZ", "countryAS", "countryAD", "countryAO", "countryAI", "countryAQ", "countryAG", "countryAR", "countryAM", "countryAW", "countryAU", "countryAT", "countryAZ", "countryBS", "countryBH", "countryBD", "countryBB", "countryBY", "countryBE", "countryBZ", "countryBJ", "countryBM", "countryBT", "countryBO", "countryBA", "countryBW", "countryBV", "countryBR", "countryIO", "countryVG", "countryBN", "countryBG", "countryBF", "countryBI", "countryKH", "countryCM", "countryCA", "countryCV", "countryKY", "countryCF", "countryTD", "countryCL", "countryCN", "countryCX", "countryCC", "countryCO", "countryKM", "countryCG", "countryCD", "countryCK", "countryCR", "countryCI", "countryHR", "countryCU", "countryCY", "countryCZ", "countryDK", "countryDJ", "countryDM", "countryDO", "countryEC", "countryEG", "countrySV", "countryGQ", "countryER", "countryEE", "countrySZ", "countryET", "countryFK", "countryFO", "countryFJ", "countryFI", "countryFR", "countryGF", "countryPF", "countryTF", "countryGA", "countryGM", "countryGE", "countryDE", "countryGH", "countryGI", "countryGR", "countryGL", "countryGD", "countryGP", "countryGU", "countryGT", "countryGN", "countryGW", "countryGY", "countryHT", "countryHM", "countryHN", "countryHK", "countryHU", "countryIS", "countryIN", "countryID", "countryIR", "countryIQ", "countryIE", "countryIL", "countryIT", "countryJM", "countryJP", "countryJO", "countryKZ", "countryKE", "countryKI", "countryKW", "countryKG", "countryLA", "countryLV", "countryLB", "countryLS", "countryLR", "countryLY", "countryLI", "countryLT", "countryLU", "countryMO", "countryMG", "countryMW", "countryMY", "countryMV", "countryML", "countryMT", "countryMH", "countryMQ", "countryMR", "countryMU", "countryYT", "countryMX", "countryFM", "countryMD", "countryMC", "countryMN", "countryMS", "countryMA", "countryMZ", "countryMM", "countryNA", "countryNR", "countryNP", "countryNL", "countryNC", "countryNZ", "countryNI", "countryNE", "countryNG", "countryNU", "countryNF", "countryKP", "countryMK", "countryMP", "countryNO", "countryOM", "countryPK", "countryPW", "countryPS", "countryPA", "countryPG", "countryPY", "countryPE", "countryPH", "countryPN", "countryPL", "countryPT", "countryPR", "countryQA", "countryRE", "countryRO", "countryRU", "countryRW", "countryWS", "countrySM", "countryST", "countrySA", "countrySN", "countryRS", "countrySC", "countrySL", "countrySG", "countrySK", "countrySI", "countrySB", "countrySO", "countryZA", "countryGS", "countryKR", "countryES", "countryLK", "countrySH", "countryKN", "countryLC", "countryPM", "countryVC", "countrySD", "countrySR", "countrySJ", "countrySE", "countryCH", "countrySY", "countryTW", "countryTJ", "countryTZ", "countryTH", "countryTG", "countryTK", "countryTO", "countryTT", "countryTN", "countryTR", "countryTM", "countryTC", "countryTV", "countryVI", "countryUG", "countryUA", "countryAE", "countryGB", "countryUS", "countryUY", "countryUZ", "countryVU", "countryVA", "countryVE", "countryVN", "countryWF", "countryEH", "countryYE", "countryZM", "countryZW" ], "type": "string", "description": "Restrict results by country of origin (Google `cr`), e.g. `countryUS`." }, "tbs": { "title": "⏱️ TBS — time filter", "type": "string", "description": "Raw Google time filter, e.g. `qdr:y` (past year) or `cdr:1,cd_min:01/01/2024,cd_max:01/31/2024`." }, "proxy_location": { "title": "🛡️ Proxy region", "enum": [ "us", "ca" ], "type": "string", "description": "Force the proxy exit region independently of the Google country. Supported values: `us`, `ca` — any other value is ignored by the proxy layer." }, "includeDocumentResults": { "title": "🗂️ Audit every result (documentResults)", "type": "boolean", "description": "Returns `documentResults[]` — one audited record per organic result with the file-type badge, the `N pages` line, the real `cite` displayed URL, the snippet with its emphasised runs, and `matchedOperators[]`. While this is on, Google's Web-only tab (`udm=14`) is **not** requested, because that tab drops the related-searches block this actor reads instead of inventing one.", "default": true }, "onlyResultsMatchingAllOperators": { "title": "✅ Keep only results that satisfy EVERY operator", "type": "boolean", "description": "Drops audited records that do not match all of `operatorsRequested`. Useful when Google loosens an `intitle:`/`inurl:` operator. `organicResults[]` is left untouched so the base output stays intact — the filter applies to `documentResults[]` only.", "default": false }, "onlyQueriesWithDocuments": { "title": "🎯 Keep only searches that returned documents", "type": "boolean", "description": "Drops a keyword whose SERP carried no file-type badge on any result. The dropped keyword still gets an **uncharged** accounting row with `errorReason: FILTERED_NO_DOCUMENT_RESULTS`, so nothing disappears silently. Judged on this run only — nothing is stored or compared with a past run.", "default": false }, "enrichOrganicResults": { "title": "✨ Upgrade organicResults with the printed values", "type": "boolean", "description": "Replaces `organicResults[].displayedUrl` with the real `cite` string, `.description` with the real snippet and `.emphasizedKeywords` with the real `` runs. Left off, those three fields keep the base actor's exact values (a stripped URL, a fallback snippet and a constant `[keyword]`), and the printed values are still available in `documentResults[]`.", "default": false }, "forceWebOnlyTab": { "title": "🌐 Force the Web-only tab (base actor request)", "type": "boolean", "description": "Sends `udm=14` on every request, which is exactly what the base actor does. Use it to reproduce the base's request shape byte-for-byte. Google strips the related-searches block from that tab, so `relatedQueries` / `suggestedResults` come back `null` rather than fabricated.", "default": false }, "dedupeResultsAcrossPages": { "title": "🧮 One page's results per row (no repeats)", "type": "boolean", "description": "The base actor re-sends pages 1..n inside page n's row, so a 10-page crawl repeats the first page ten times. Turn this on and each row carries only its own page's new results. Left off, row values stay identical to the base actor's.", "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 } } } } } } } } } }