{ "openapi": "3.0.1", "info": { "title": "💎ESG Scraper: Sustainability Reports & PDF Disclosures", "description": "Powerful ESG scraper (Environmental, Social, and Governance) to automatically extract sustainability reports, PDF disclosures, articles, and content from any website. Get clean, AI-ready datasets with keyword filtering, metadata extraction, images, links, and full PDF support.", "version": "0.0", "x-build-id": "ylYI89NLz3byuTCg7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/primeparse~esg-content-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-primeparse-esg-content-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/primeparse~esg-content-scraper/runs": { "post": { "operationId": "runs-sync-primeparse-esg-content-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/primeparse~esg-content-scraper/run-sync": { "post": { "operationId": "run-sync-primeparse-esg-content-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "URLs to start scraping ESG content from. Examples: ESG news sites, sustainability reports, ESG rating pages.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxRequestsPerCrawl": { "title": "Max Requests per Crawl", "minimum": 0, "type": "integer", "description": "Maximum number of pages to scrape (0 = unlimited).", "default": 100 }, "useApifyProxy": { "title": "Use Apify Proxy", "type": "boolean", "description": "Whether to use Apify Proxy (recommended). Set to true only if your account has Proxy External Access.", "default": false }, "allowedDomains": { "title": "Allowed Domains", "type": "array", "description": "Restrict crawling to these domains (e.g., ['www.ft.com', 'www.reuters.com']). Leave empty for unlimited.", "default": [], "items": { "type": "string" } }, "esgKeywords": { "title": "ESG Keywords", "type": "array", "description": "Keywords to filter ESG-related content. Pages without these keywords will be skipped.", "default": [ "ESG", "environmental", "social", "governance", "sustainability", "carbon", "emissions", "climate", "green", "renewable", "CSR", "corporate responsibility" ], "items": { "type": "string" } }, "extractContent": { "title": "Extract Full Content", "type": "boolean", "description": "Whether to extract the full text content of each page.", "default": true }, "extractMetadata": { "title": "Extract Metadata", "type": "boolean", "description": "Whether to extract metadata (publication date, author, description).", "default": true }, "followLinks": { "title": "Follow Links", "type": "boolean", "description": "Whether to follow and scrape linked pages.", "default": true }, "cleanDefaultDataset": { "title": "Clean Default Dataset Before Run", "type": "boolean", "description": "Delete all previous data before starting. Keep OFF to accumulate results across runs.", "default": false }, "useSeparateDatasets": { "title": "Use Separate Named Datasets", "type": "boolean", "description": "Split output into multiple datasets: esg-overview (light metadata), esg-full-content (long texts), esg-images (images only). Useful for large crawls or ML training.", "default": false }, "proxyUrls": { "title": "Custom Proxy URLs", "type": "array", "description": "Newline-separated proxy URLs (e.g. http://user:pass@host:port). If provided, these will be used instead of Apify Proxy.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } } } }, "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 } } } } } } } } } }