{ "openapi": "3.0.1", "info": { "title": "Internshala Scraper — Internships & Jobs + Employer Emails", "description": "Scrape Internshala internships and jobs — stipend, skills, applicant count, applicants-per-opening, employer hiring history (since / posted / hired), and optional contact email. Filter by keyword, city, badge, stipend, WFH or PPO. Change-only monitoring with applicant deltas. $0.50/1k.", "version": "1.0", "x-build-id": "MZhmUSac1ybxkHPwE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~internshala-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-internshala-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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. Merged with Cities below." }, "locations": { "title": "Cities (multiple)", "type": "array", "description": "Several cities at once — one Internshala search walk per city (e.g. [\"mumbai\", \"pune\"]). Merged with the single Location field. Work-from-home does not automatically match a city. Default: none.", "items": { "type": "string" } }, "specialFilters": { "title": "Verifiable badges", "type": "array", "description": "Keep only listings that carry every selected public badge. `actively_hiring` comes from the listing card. `early_applicant` is Internshala's 'Be an early applicant' prompt (no applicant count yet). `job_offer` is the PPO perk. Dropped rows are never billed. Default: none.", "items": { "type": "string", "enum": [ "actively_hiring", "early_applicant", "job_offer" ], "enumTitles": [ "Actively hiring", "Early applicant", "Job offer after internship" ] } }, "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." }, "datePosted": { "title": "Posted within", "enum": [ "all", "24h", "3d", "7d", "30d" ], "type": "string", "description": "Keep only postings whose posted date is within this window. Postings with no parseable date do not pass a selected window. Applied client-side, so filtered rows are never billed.", "default": "all" }, "minSalary": { "title": "Minimum salary / stipend (INR)", "minimum": 0, "type": "integer", "description": "Keep only postings whose minimum stipend or salary is at least this amount (INR). Undisclosed pay does not pass a positive minimum. Applied client-side, so filtered rows are never billed." }, "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, the run compares each listing to the previous baseline: `new` on first sight, `updated` when title/company/location/applicant count changed, otherwise skipped (unless Include unchanged is on). Applicant-count deltas ride on updated rows. The first run after enabling monitoring returns every match and builds the baseline. Combine with Apify's scheduler for a change-only 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 }, "includeUnchanged": { "title": "Include unchanged listings (monitoring)", "type": "boolean", "description": "Only used with Monitoring mode. OFF (default): return new listings and listings whose public fields or applicant count changed (`changeType` = `updated`). ON: also re-emit already-seen listings tagged `unchanged`. Re-emitted rows are billed. Default: false.", "default": false }, "monitorStateName": { "title": "Monitor state name (independent watches)", "type": "string", "description": "Name this monitor so one account can run several independent only-new watches — e.g. `mumbai-cs` and `remote-marketing`. Leave empty for a single default baseline. Only used when Monitoring mode is on." }, "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." }, "includeKeywords": { "title": "✅ Include keywords", "type": "array", "description": "Only keep jobs whose title, company or description contains at least one of these (case-insensitive). Filtered rows are never charged.", "items": { "type": "string" } }, "excludeKeywords": { "title": "🚫 Exclude keywords", "type": "array", "description": "Drop jobs whose title, company or description contains any of these (case-insensitive).", "items": { "type": "string" } }, "fromDate": { "title": "📅 Posted from", "type": "string", "description": "Only keep jobs posted on or after this date (ISO 8601, e.g. 2026-08-01)." }, "toDate": { "title": "📅 Posted to", "type": "string", "description": "Only keep jobs posted on or before this date (ISO 8601). A date-only value means through the end of that day." }, "maxAgeMinutes": { "title": "⏱️ Max age (minutes)", "minimum": 0, "type": "integer", "description": "Only keep jobs posted within the last N minutes. Empty or 0 = no age limit. Ideal for tight scheduled runs." }, "incrementalMode": { "title": "♻️ Incremental mode", "type": "boolean", "description": "Compare against the previous run and only emit jobs that are NEW, UPDATED, or REAPPEARED — you are only charged for what changed. The first run seeds the baseline. Each emitted row carries `changeType` and `firstSeenAt`.", "default": false }, "stateKey": { "title": "🔑 State key", "type": "string", "description": "Optional stable name for this tracked search (e.g. \"nurse-toronto\"). Leave empty to auto-derive one from the search inputs — same inputs, same baseline." }, "emitUnchanged": { "title": "♻️ Emit unchanged records", "type": "boolean", "description": "When incremental, also emit rows whose content did not change (charged as normal results).", "default": false }, "emitExpired": { "title": "⚰️ Emit expired records", "type": "boolean", "description": "When incremental, emit a small `changeType: EXPIRED` row for every previously-tracked job that vanished from the source.", "default": false }, "skipReposts": { "title": "🚫 Skip reposts", "type": "boolean", "description": "When incremental, skip jobs whose content matches a previously-expired posting (employer re-listed the same ad under a new id).", "default": false }, "resetIncrementalState": { "title": "🧨 Reset incremental state", "type": "boolean", "description": "One-shot: drop the stored baseline for this state key at the start of the run.", "default": false }, "compact": { "title": "📦 Compact output", "type": "boolean", "description": "Emit only the core fields — small payloads for AI-agent / MCP / LLM pipelines.", "default": false }, "excludeEmptyFields": { "title": "🧹 Exclude empty fields", "type": "boolean", "description": "Drop null / empty-string / empty-array fields from each record.", "default": false }, "descriptionMaxLength": { "title": "✂️ Description max length", "minimum": 0, "type": "integer", "description": "Truncate description fields to this many characters (0 = full text). Controls LLM prompt cost and dataset size." }, "telegramBotToken": { "title": "🔔 Telegram bot token", "type": "string", "description": "Your bot's token from @BotFather. With Chat ID set, a summary of new jobs is sent after each run." }, "telegramChatId": { "title": "🔔 Telegram chat ID", "type": "string", "description": "Chat or channel id the bot posts to (e.g. \"-1001234567890\")." }, "slackWebhookUrl": { "title": "💼 Slack webhook URL", "type": "string", "description": "Slack incoming-webhook URL (api.slack.com/messaging/webhooks)." }, "discordWebhookUrl": { "title": "🎮 Discord webhook URL", "type": "string", "description": "Discord incoming-webhook URL (Server Settings → Integrations → Webhooks)." }, "whatsappAccessToken": { "title": "📱 WhatsApp access token", "type": "string", "description": "WhatsApp Cloud API token (Meta Business system user). The recipient must have messaged your business number within the last 24h — Cloud API rule." }, "whatsappPhoneNumberId": { "title": "📱 WhatsApp phone-number ID", "type": "string", "description": "Your WhatsApp Business phone-number id (numeric, from the Meta dashboard)." }, "whatsappTo": { "title": "📱 WhatsApp recipient", "type": "string", "description": "Recipient phone in E.164 without + (e.g. \"14165551234\")." }, "webhookUrl": { "title": "🪝 Generic webhook URL", "type": "string", "description": "Receives one JSON POST with { metadata, items } after the run — the universal escape hatch for n8n / Make / Zapier / custom backends." }, "webhookHeaders": { "title": "🪝 Webhook headers", "type": "object", "description": "Optional custom headers for the generic webhook (e.g. {\"Authorization\": \"Bearer …\"})." }, "notificationLimit": { "title": "🔔 Max jobs per notification", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many job lines each chat notification includes (1–20). The rest are summarised as a count.", "default": 5 }, "notifyOnlyChanges": { "title": "🔔 Notify only new/updated", "type": "boolean", "description": "With Incremental mode on, notify only about NEW / UPDATED / REAPPEARED jobs.", "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }