{ "openapi": "3.0.1", "info": { "title": "Internshala Scraper - Internships & Jobs + Employer Emails", "description": "Internshala scraper — pull internships and jobs by keyword, category, city and filters (stipend, duration, work-from-home, part-time, PPO). Full details per posting: company, stipend, skills, openings, apply-by date. Optional employer-email enrichment + incremental monitoring. JSON/CSV", "version": "0.0", "x-build-id": "cjyBrcpa616o9Wckb" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~internshala-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/memo23~internshala-scraper/runs": { "post": { "operationId": "runs-sync-memo23-internshala-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/memo23~internshala-scraper/run-sync": { "post": { "operationId": "run-sync-memo23-internshala-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "listingType": { "title": "Listing type", "enum": [ "internship", "job", "both" ], "type": "string", "description": "Scrape internships, jobs, or both. `both` uses Internshala's internships surface (the superset).", "default": "both" }, "searchQuery": { "title": "Search keyword", "type": "string", "description": "Free-text keyword to search for, e.g. `python`, `content writing`. Becomes the `keywords-...` segment of the search URL." }, "category": { "title": "Category / stream", "type": "string", "description": "Field or stream to filter by, e.g. `computer science`, `marketing`, `graphic design`, `human resources`." }, "location": { "title": "Location (city)", "type": "string", "description": "City to filter by, e.g. `mumbai`, `delhi`, `bangalore`. Ignored for work-from-home-only searches." }, "workFromHome": { "title": "Work from home only", "type": "boolean", "description": "Only return work-from-home (remote) listings.", "default": false }, "partTime": { "title": "Part-time only", "type": "boolean", "description": "Only return part-time listings.", "default": false }, "withJobOffer": { "title": "With job offer (PPO) only", "type": "boolean", "description": "Only return listings that come with a job offer / pre-placement offer (PPO).", "default": false }, "forWomen": { "title": "For women", "type": "boolean", "description": "Only return listings from Internshala's `Internships for women` category.", "default": false }, "maxDurationMonths": { "title": "Maximum duration (months)", "minimum": 1, "maximum": 6, "type": "integer", "description": "Only return listings up to this duration, in months. Snapped to a supported value (1-6). Applied only when no category/city/keyword is set (Internshala can't combine the two)." }, "minStipend": { "title": "Minimum stipend (INR / month)", "minimum": 0, "type": "integer", "description": "Only return listings paying at least this monthly stipend, in INR. Snapped to a supported bracket (2000, 4000, 6000, 8000, 10000). Applied only when no category/city/keyword is set." }, "startUrls": { "title": "Internshala URLs", "type": "array", "description": "Full internshala.com search or detail URLs. Mix listing and detail URLs freely.", "items": { "type": "string" } }, "includeDetails": { "title": "Include full detail pages", "type": "boolean", "description": "Fetch each listing's detail page to capture the complete JobPosting record (description, stipend, skills, company website, dates, etc.). Turn off to skip the extra requests.", "default": true }, "enrichEmails": { "title": "Enrich with employer contact emails (experimental, billed per email)", "type": "boolean", "description": "If enabled, tries to find a contact email for each hiring company by using its on-page website (or discovering one via Clearbit) and reading its contact/about pages. Adds contactEmail + contactWebsite columns plus a detailed emailEnrichment object. Best-effort, billed per contact email found; only charged when an email is returned, never for misses.", "default": false }, "maxItems": { "title": "Maximum items to scrape", "minimum": 1, "type": "integer", "description": "Hard cap on the number of listings collected. Internshala pages return ~40-50 cards each; use this cap to limit billing.", "default": 1000 }, "monitoringMode": { "title": "Monitoring mode (only return listings not seen on previous runs)", "type": "boolean", "description": "When enabled, listings whose Internshala numeric ID has already been delivered to you are silently skipped (the detail page is not fetched and no charge applies). The first run after enabling monitoring returns every match — that builds your baseline. Every subsequent run returns only new postings. Combine with Apify's scheduler for a 'posted since last run' feed.", "default": false }, "resetMonitoringState": { "title": "Reset monitoring state (one-shot)", "type": "boolean", "description": "One-shot toggle: clear the saved 'already seen' record at the start of this run. Use this when you change the search, want to rebuild the baseline, or recover from a missed delivery. Has no effect when monitoring mode is off.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "type": "integer", "description": "Maximum number of detail pages processed in parallel.", "default": 10 }, "minConcurrency": { "title": "Min concurrency", "minimum": 1, "type": "integer", "description": "Minimum number of detail pages processed in parallel.", "default": 1 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "type": "integer", "description": "Number of retries before a failed request is given up.", "default": 5 }, "proxy": { "title": "Proxy configuration (optional override)", "type": "object", "description": "Leave empty — the actor already routes all traffic through its own built-in residential proxy at no extra cost to you. Only set this if you want to use your own proxies." } } }, "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 } } } } } } } } } }