{ "openapi": "3.0.1", "info": { "title": "ClinicalTrials.gov Scraper - Trials, Sites & Sponsor Leads", "description": "Scrape ClinicalTrials.gov by condition, drug, sponsor, phase, status or location. Rich trial records, research-site & investigator contact leads, and sponsor pipeline analytics. Keyless, no browser, monitor mode. Independent tool, not affiliated with any government agency.", "version": "0.1", "x-build-id": "DKcD1l728rJTfu7fX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapesage~clinical-trials-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapesage-clinical-trials-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapesage~clinical-trials-scraper/runs": { "post": { "operationId": "runs-sync-scrapesage-clinical-trials-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapesage~clinical-trials-scraper/run-sync": { "post": { "operationId": "run-sync-scrapesage-clinical-trials-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "outputType": { "title": "Output type", "enum": [ "trials", "siteLeads", "sponsors" ], "type": "string", "description": "What to output. `Trials` = one rich record per study (the default). `Site & investigator leads` = one contactable lead per research site/contact (name, phone, email, facility, geo + trial context + lead score). `Sponsor pipeline` = one analytics record per lead sponsor (trial counts by phase/status, top conditions/interventions, recent trials).", "default": "trials" }, "condition": { "title": "Condition / disease", "type": "string", "description": "Condition or disease, e.g. `breast cancer`, `type 2 diabetes`, `alzheimer`. Maps to the ClinicalTrials.gov Condition field." }, "intervention": { "title": "Intervention (drug / device / treatment)", "type": "string", "description": "Drug, biologic, device or procedure name, e.g. `pembrolizumab`, `semaglutide`, `CAR-T`." }, "otherTerms": { "title": "Other search terms", "type": "string", "description": "Free-text keywords searched across the whole record (titles, summary, etc.), e.g. `biomarker`, `pediatric`." }, "sponsor": { "title": "Sponsor / collaborator", "type": "string", "description": "Sponsor or collaborator organization, e.g. `Pfizer`, `Mayo Clinic`, `National Cancer Institute`." }, "titleSearch": { "title": "Title contains", "type": "string", "description": "Search only the study title / acronym." }, "nctIds": { "title": "Specific NCT IDs", "type": "array", "description": "Scrape these exact studies by their NCT number (e.g. `NCT04368728`). Full detail including the results section is fetched for each.", "items": { "type": "string" } }, "searchUrls": { "title": "ClinicalTrials.gov URLs", "type": "array", "description": "Paste clinicaltrials.gov search URLs (e.g. `https://clinicaltrials.gov/search?cond=melanoma&aggFilters=status:rec,phase:2`) or study URLs (`/study/NCT…`). Filters in the URL are converted automatically.", "items": { "type": "string" } }, "status": { "title": "Recruitment status", "type": "array", "description": "Limit to these statuses. Leave empty for all.", "items": { "type": "string", "enum": [ "RECRUITING", "NOT_YET_RECRUITING", "ENROLLING_BY_INVITATION", "ACTIVE_NOT_RECRUITING", "COMPLETED", "SUSPENDED", "TERMINATED", "WITHDRAWN", "UNKNOWN", "AVAILABLE" ], "enumTitles": [ "Recruiting", "Not yet recruiting", "Enrolling by invitation", "Active, not recruiting", "Completed", "Suspended", "Terminated", "Withdrawn", "Unknown", "Available (expanded access)" ] } }, "phases": { "title": "Phase", "type": "array", "description": "Trial phase(s). Leave empty for all.", "items": { "type": "string", "enum": [ "EARLY_PHASE1", "PHASE1", "PHASE2", "PHASE3", "PHASE4", "NA" ], "enumTitles": [ "Early Phase 1", "Phase 1", "Phase 2", "Phase 3", "Phase 4", "Not Applicable" ] } }, "studyType": { "title": "Study type", "enum": [ "", "INTERVENTIONAL", "OBSERVATIONAL", "EXPANDED_ACCESS" ], "type": "string", "description": "Interventional, observational or expanded access.", "default": "" }, "funderTypes": { "title": "Lead sponsor type", "type": "array", "description": "Limit by who is leading the trial (e.g. Industry for pharma pipeline intelligence).", "items": { "type": "string", "enum": [ "NIH", "FED", "OTHER_GOV", "INDIV", "INDUSTRY", "NETWORK", "AMBIG", "OTHER", "UNKNOWN" ], "enumTitles": [ "NIH", "U.S. Fed", "Other gov", "Individual", "Industry", "Network", "Ambiguous", "Other", "Unknown" ] } }, "resultsAvailability": { "title": "Results availability", "enum": [ "", "with", "without" ], "type": "string", "description": "Whether posted results must be present.", "default": "" }, "sex": { "title": "Eligible sex", "enum": [ "", "FEMALE", "MALE" ], "type": "string", "description": "Limit to trials enrolling a specific sex.", "default": "" }, "ages": { "title": "Age groups", "type": "array", "description": "Eligible age groups.", "items": { "type": "string", "enum": [ "CHILD", "ADULT", "OLDER_ADULT" ], "enumTitles": [ "Child (0–17)", "Adult (18–64)", "Older adult (65+)" ] } }, "healthyVolunteersOnly": { "title": "Accepts healthy volunteers only", "type": "boolean", "description": "Only trials that accept healthy volunteers.", "default": false }, "locationCountry": { "title": "Country", "type": "string", "description": "Limit to trials with a site in this country, e.g. `United States`, `Canada`, `Germany`." }, "locationState": { "title": "State / region", "type": "string", "description": "Limit to trials with a site in this state/region, e.g. `California`, `Ontario`." }, "locationCity": { "title": "City", "type": "string", "description": "Limit to trials with a site in this city." }, "locationTerm": { "title": "Location free-text", "type": "string", "description": "Free-text location search (facility name, city, etc.)." }, "geoLatitude": { "title": "Geo latitude", "type": "string", "description": "Latitude for radius search (used with longitude + radius)." }, "geoLongitude": { "title": "Geo longitude", "type": "string", "description": "Longitude for radius search." }, "geoRadius": { "title": "Geo radius", "type": "string", "description": "Radius for the geo search, e.g. `50mi` or `100km`.", "default": "50mi" }, "studyStartDateFrom": { "title": "Study start date from", "type": "string", "description": "Earliest study start date, `YYYY-MM-DD` (or `YYYY-MM`)." }, "studyStartDateTo": { "title": "Study start date to", "type": "string", "description": "Latest study start date, `YYYY-MM-DD` (or `YYYY-MM`)." }, "lastUpdateDateFrom": { "title": "Last updated from", "type": "string", "description": "Only trials whose record was last updated on/after this date, `YYYY-MM-DD`. Great for incremental monitoring." }, "lastUpdateDateTo": { "title": "Last updated to", "type": "string", "description": "Only trials whose record was last updated on/before this date, `YYYY-MM-DD`." }, "sortBy": { "title": "Sort by", "enum": [ "relevance", "lastUpdate", "firstPosted", "enrollment", "startDate" ], "type": "string", "description": "Order of results. Use 'Most recently updated' with monitor mode for incremental runs.", "default": "relevance" }, "includeResults": { "title": "Include posted results", "type": "boolean", "description": "For trials that have posted results, attach a `resultsSummary` (outcome measures, participant flow, adverse-event totals). Adds one extra request per such trial.", "default": false }, "includeDetailedDescription": { "title": "Include detailed description", "type": "boolean", "description": "Include the long detailed-description text on each trial record.", "default": true }, "includeEligibilityText": { "title": "Include full eligibility criteria text", "type": "boolean", "description": "Include the full inclusion/exclusion criteria text on each trial record.", "default": true }, "maxResults": { "title": "Max results", "minimum": 1, "type": "integer", "description": "Maximum output records (trials, site leads, or sponsors depending on output type)." }, "maxTrialsToScan": { "title": "Max trials to scan (sponsor mode)", "minimum": 1, "type": "integer", "description": "For the Sponsor pipeline output: how many matching trials to scan before aggregating sponsors.", "default": 1000 }, "deduplicateResults": { "title": "Deduplicate results", "type": "boolean", "description": "Skip duplicate records within a run.", "default": true }, "monitorMode": { "title": "Monitor mode (only new/updated)", "type": "boolean", "description": "Remember records across runs and output only new or changed ones each time (a trial re-appears when its last-update date changes). Pairs perfectly with Apify Schedules for new-trial alerts. Uses its own named store — does not interfere with scheduling.", "default": false }, "monitorKey": { "title": "Monitor key", "type": "string", "description": "Name this monitor watchlist. Use different keys for different saved searches so their histories stay separate.", "default": "default" }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 12, "type": "integer", "description": "Parallel requests to the API. 5 is a good default.", "default": 5 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy settings. Datacenter proxy is plenty — the ClinicalTrials.gov API is clean and keyless.", "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 } } } } } } } } } }