{
  "openapi": "3.0.1",
  "info": {
    "title": "News Scraper & Monitor: RSS Feeds & Keyword Alerts",
    "description": "Monitor news by keyword, website or any RSS, Atom or JSON feed. Finds feeds and news sitemaps, merges duplicates across sources and returns only new articles: title, publisher URL, date, summary, language, matched keywords. Optional full text. Respects robots.txt.",
    "version": "0.1",
    "x-build-id": "GbJmCP2qFkGj2mccD"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/koivu-data~news-scraper-monitor/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-koivu-data-news-scraper-monitor",
        "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": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/koivu-data~news-scraper-monitor/runs": {
      "post": {
        "operationId": "runs-sync-koivu-data-news-scraper-monitor",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/koivu-data~news-scraper-monitor/run-sync": {
      "post": {
        "operationId": "run-sync-koivu-data-news-scraper-monitor",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": {
          "feeds": {
            "title": "Feeds, sitemaps or websites",
            "type": "array",
            "description": "One per line: an RSS, Atom or JSON feed URL (<code>https://feeds.bbci.co.uk/news/world/rss.xml</code>), a news sitemap URL, or a website (<code>techcrunch.com</code>), for which the Actor finds the feed and the news sitemap itself. With no feeds and no keywords, the Actor reads two example feeds.",
            "items": {
              "type": "string"
            }
          },
          "keywords": {
            "title": "Keywords",
            "type": "array",
            "description": "Words or phrases to find, one per line (case-insensitive). <code>nokia</code> matches the whole word; <code>nokia*</code> also matches inflected forms such as <i>Nokian</i> (useful for Finnish); <code>electric vehicles</code> matches the phrase. Keywords filter the articles of your feeds and websites (title, summary and tags). Leave empty to get every article.",
            "items": {
              "type": "string"
            }
          },
          "maxArticles": {
            "title": "Max articles per run",
            "minimum": 1,
            "maximum": 100000,
            "type": "integer",
            "description": "Maximum number of articles saved per run, newest first. You only pay for articles that are saved.",
            "default": 100
          },
          "onlyNew": {
            "title": "Only new articles since the last run (monitoring)",
            "type": "boolean",
            "description": "For scheduled runs. The first run returns the current articles (marked INITIAL) and remembers them; later runs return only articles that are new since the previous run (marked NEW), also across sources. The memory is kept per saved task.",
            "default": false
          },
          "returnExistingOnFirstRun": {
            "title": "Return current articles on the first monitoring run",
            "type": "boolean",
            "description": "On by default. Turn off to start monitoring silently: the first run only remembers the current articles and saves nothing. The same applies to a source you add to a task later.",
            "default": true
          },
          "excludeKeywords": {
            "title": "Exclude keywords",
            "type": "array",
            "description": "Drop articles whose title, summary or tags contain any of these words or phrases. Same syntax as Keywords.",
            "items": {
              "type": "string"
            }
          },
          "keywordsFilterFeeds": {
            "title": "Apply keywords to feeds",
            "type": "boolean",
            "description": "On: keep only articles that mention a keyword in the title, summary or tags. Off: keep every article from your feeds (keywords are then only used for the GDELT search and for the matchedKeywords field).",
            "default": true
          },
          "languages": {
            "title": "Languages",
            "type": "array",
            "description": "Keep only articles in these languages: two-letter codes such as <code>en</code>, <code>fi</code>, <code>sv</code>, <code>de</code>. The language comes from the feed, the sitemap or GDELT; articles whose language is unknown are dropped when this is set.",
            "items": {
              "type": "string"
            }
          },
          "publishedSince": {
            "title": "Published since",
            "type": "string",
            "description": "Keep articles published on or after this date. Absolute (<code>2026-09-01</code>) or relative (<code>24 hours</code>, <code>7 days</code>). The GDELT search covers this range (default: the last 24 hours, or since the previous monitoring run)."
          },
          "dedupe": {
            "title": "Duplicates",
            "enum": [
              "article",
              "story",
              "url"
            ],
            "type": "string",
            "description": "<b>Same article</b>: one row per article even if it appears in several feeds, sitemaps or GDELT (same address, or the same title from the same publisher). <b>Same story</b>: also merge near-identical headlines from different publishers (for example wire stories); the other publishers are listed in <i>alsoPublishedBy</i>. <b>Same URL only</b>: merge only identical addresses.",
            "default": "article"
          },
          "fetchFullText": {
            "title": "Fetch full article text",
            "type": "boolean",
            "description": "Also open each saved article on the publisher's site and extract the text. Only where the site's robots.txt allows it; paywalled articles are skipped (status <code>paywalled</code>) and never bypassed. Charged per article with text. <b>You are responsible</b> for having the right to store and use the text (copyright).",
            "default": false
          },
          "searchGdelt": {
            "title": "Also search worldwide news with GDELT (experimental)",
            "type": "boolean",
            "description": "Also search the keywords in the GDELT Project's free index of worldwide online news (about 65 languages, last 3 months). Experimental: in our tests in October 2026 GDELT's free API refused most requests as rate-limited (HTTP 429) and its few answers were empty. The Actor then waits once, retries once and continues with your feeds; it never works around the limit, and a monitoring run catches up when GDELT answers again. GDELT matches the article text (write keywords in English; names work in any language) and returns no summary.",
            "default": false
          },
          "countries": {
            "title": "GDELT source countries",
            "type": "array",
            "description": "GDELT search only: keep news from publishers in these countries. Two-letter codes (<code>FI</code>, <code>US</code>, <code>GB</code>) or English names.",
            "items": {
              "type": "string"
            }
          },
          "stateKey": {
            "title": "Monitoring state key",
            "type": "string",
            "description": "Advanced. Name of the memory slot used by monitoring. Leave empty to use the task ID automatically."
          }
        }
      },
      "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
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}