{ "openapi": "3.0.1", "info": { "title": "Internshala Scraper: Jobs & Internship Monitor", "description": "Scrape and monitor public Internshala internship and job listings. Filter by keyword, city, category, work arrangement, compensation, age, and public badges; emit new or changed listings on recurring runs.", "version": "0.1", "x-build-id": "tyK4hteaU7x7mRLGa" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/getascraper~internshala-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-getascraper-internshala-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/getascraper~internshala-scraper/runs": { "post": { "operationId": "runs-sync-getascraper-internshala-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/getascraper~internshala-scraper/run-sync": { "post": { "operationId": "run-sync-getascraper-internshala-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "proxyConfiguration" ], "properties": { "mode": { "title": "What to scrape", "enum": [ "internships", "jobs" ], "type": "string", "description": "Choose public internship listings or public job listings.", "default": "internships" }, "startUrls": { "title": "Public listing URLs (optional)", "type": "array", "description": "Public Internshala internships, jobs, or fresher-jobs listing pages. These URLs replace automatic source URL construction, but verifiable record filters below still apply. Query parameters, fragments, detail pages, login pages, and non-Internshala URLs are rejected. Pagination follows each page's public Next link.", "default": [], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "keyword": { "title": "Role or keyword", "type": "string", "description": "Search public title, company, summary, and skill text. With automatic sources, this also selects Internshala's keyword results page.", "default": "" }, "locations": { "title": "Cities", "type": "array", "description": "Only keep listings whose public location contains one of these cities. Multiple cities create separate source pages when the URL pattern supports it. Work-from-home does not automatically match a city.", "default": [], "items": { "type": "string" } }, "category": { "title": "Internship category", "type": "string", "description": "Select an Internshala internship category source, for example 'Computer Science' or 'Marketing'. Supported only in internships mode and cannot be combined with startUrls.", "default": "" }, "workFromHome": { "title": "Work from home only", "type": "boolean", "description": "Only keep listings explicitly marked as work from home.", "default": false }, "partTime": { "title": "Part-time only", "type": "boolean", "description": "Only keep listings explicitly marked as part time.", "default": false }, "minStipend": { "title": "Minimum monthly stipend (INR)", "minimum": 0, "maximum": 200000, "type": "integer", "description": "Only keep internships whose published minimum monthly stipend is at least this amount. Unpaid or undisclosed stipends do not pass a positive minimum.", "default": 0 }, "minSalary": { "title": "Minimum annual salary (INR)", "minimum": 0, "maximum": 10000000, "type": "integer", "description": "Only keep jobs whose published minimum annual salary is at least this amount. Undisclosed salaries do not pass a positive minimum.", "default": 0 }, "maxDurationMonths": { "title": "Maximum internship duration", "minimum": 0, "maximum": 24, "type": "integer", "description": "Only keep listings with a published duration at or below this number of months. 0 disables the filter.", "default": 0 }, "maxExperienceYears": { "title": "Maximum required experience", "minimum": 0, "maximum": 20, "type": "integer", "description": "Only keep jobs whose published minimum experience requirement is at or below this number of years. 0 disables the filter.", "default": 0 }, "datePosted": { "title": "Posted within", "enum": [ "all", "24h", "3d", "7d", "30d" ], "type": "string", "description": "Filter using the public relative posting age shown on the listing card. Records without a parseable age do not pass a selected window.", "default": "all" }, "specialFilters": { "title": "Verifiable badges", "type": "array", "description": "Only keep listings carrying every selected public card badge.", "items": { "type": "string", "enum": [ "actively_hiring", "early_applicant", "job_offer" ], "enumTitles": [ "Actively hiring", "Early applicant", "Job offer after internship" ] }, "default": [] }, "sortBy": { "title": "Sort collected results", "enum": [ "relevance", "newest" ], "type": "string", "description": "Keep source relevance order or sort the collected matching window by the public relative posting age. Records with an unknown age sort last.", "default": "relevance" }, "includeDetails": { "title": "Fetch public detail pages", "type": "boolean", "description": "Request each selected public detail page for description, eligibility, perks, openings, application deadline, company text, and exact posted date when available. Core listing output is retained with detailsFetched=false if a detail request fails.", "default": false }, "monitoringMode": { "title": "Recurring monitoring mode", "enum": [ "off", "new_only", "new_and_changed", "all_with_status" ], "type": "string", "description": "Off emits all selected listings. Monitoring modes compare stable listing fingerprints with prior runs in a persistent named store. The first successful monitor run treats all selected listings as new.", "default": "off" }, "monitoringStoreName": { "title": "Monitoring store name", "pattern": "^[a-z0-9][a-z0-9-]{0,62}$", "type": "string", "description": "Persistent named key-value store shared by recurring runs. Change this to isolate environments or workflows.", "default": "internshala-monitor-state" }, "monitorStateKey": { "title": "Monitoring state key", "pattern": "^[A-Za-z0-9][A-Za-z0-9._-]{0,255}$", "type": "string", "description": "Use 'auto' to derive a deterministic key from the effective source, filters, and detail setting. Set an explicit key to control which recurring runs share history.", "default": "auto" }, "maxResults": { "title": "Maximum matching listings", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Stop after this many unique listings pass the filters. 0 means no Actor-side limit. Monitoring can emit fewer records because unchanged candidates may be suppressed.", "default": 100 }, "maxConcurrency": { "title": "Requests at once", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum parallel public page requests.", "default": 10 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional Apify proxy configuration for public page requests.", "default": { "useApifyProxy": true } }, "debugLogging": { "title": "Detailed logging", "type": "boolean", "description": "Enable additional page and parser diagnostics.", "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 } } } } } } } } } }