{ "openapi": "3.0.1", "info": { "title": "Al Jazeera News Rss Scraper", "description": "Al Jazeera News RSS Scraper is a Python tool designed to parse RSS feeds from Al Jazeera. It extracts breaking headlines, article summaries, publication timestamps, section categories, and direct story links into clean CSV or JSON formats for media monitoring and international news analysis.", "version": "0.0", "x-build-id": "ypjexuPhJbYFocPmn" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/real-estate-api~al-jazeera-news-rss-scraper-202610120341/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-real-estate-api-al-jazeera-news-rss-scraper-202610120341", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/real-estate-api~al-jazeera-news-rss-scraper-202610120341/runs": { "post": { "operationId": "runs-sync-real-estate-api-al-jazeera-news-rss-scraper-202610120341", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/real-estate-api~al-jazeera-news-rss-scraper-202610120341/run-sync": { "post": { "operationId": "run-sync-real-estate-api-al-jazeera-news-rss-scraper-202610120341", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "feedUrls": { "title": "Feed URLs", "type": "array", "description": "RSS feed URLs to read. Only https://www.aljazeera.com/xml/rss/all.xml is requested. Any other URL is saved as an error row and is not fetched.", "default": [ "https://www.aljazeera.com/xml/rss/all.xml" ], "items": { "type": "string" } }, "keyword": { "title": "Keyword", "type": "string", "description": "Optional case-insensitive filter matched against the headline and the short summary. Leave empty to keep every item in the feed." }, "maxItems": { "title": "Max items", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of headline rows to save. Values are clamped between 1 and 1000.", "default": 100 }, "timeoutSecs": { "title": "Timeout seconds", "minimum": 1, "maximum": 3600, "type": "integer", "description": "Maximum seconds for the whole run, including retries and the gap between feed requests.", "default": 300 }, "requestTimeoutSecs": { "title": "Request timeout seconds", "minimum": 5, "maximum": 120, "type": "integer", "description": "Maximum seconds to wait for a single HTTP response before retrying.", "default": 30 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional proxy for the feed request. Leave Apify proxy off unless the feed blocks your IP.", "default": { "useApifyProxy": 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 } } } } } } } } } }