{
  "openapi": "3.0.1",
  "info": {
    "title": "Google News Scraper - Articles, Sources & Monitoring",
    "description": "Scrape Google News by keyword, topic, top headlines or city. Get real publisher URLs (decoded, not redirect links), source, date, snippet, related coverage and full article text, author & image. Monitor mode returns only new articles. Export JSON, CSV, Excel.",
    "version": "1.0",
    "x-build-id": "m2BephXms5D9cbx0P"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/scrapesage~google-news-scraper/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-scrapesage-google-news-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": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/scrapesage~google-news-scraper/runs": {
      "post": {
        "operationId": "runs-sync-scrapesage-google-news-scraper",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/scrapesage~google-news-scraper/run-sync": {
      "post": {
        "operationId": "run-sync-scrapesage-google-news-scraper",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": {
          "searchTerms": {
            "title": "Search terms / keywords",
            "type": "array",
            "description": "Keywords or phrases to search Google News for. Each term runs as its own feed and returns up to ~100 of the latest matching articles. Google News search operators work too: quotes for exact phrases (`\"electric vehicles\"`), `OR`, `-exclude`, `site:reuters.com`, `intitle:`, `allintitle:`, and `when:7d` for a time window.",
            "items": {
              "type": "string"
            }
          },
          "topics": {
            "title": "Topics",
            "type": "array",
            "description": "Google News topic feeds. Use a friendly name — `WORLD`, `NATION`, `BUSINESS`, `TECHNOLOGY`, `ENTERTAINMENT`, `SPORTS`, `SCIENCE`, `HEALTH` — or paste a raw Google News topic token (the `CAAq…` string from a topic URL) for niche topics.",
            "items": {
              "type": "string"
            }
          },
          "locations": {
            "title": "Locations (local news)",
            "type": "array",
            "description": "Cities, states or places to pull local news for, e.g. `New York`, `San Francisco`, `California`, `London`. Each returns the Google News local headlines feed for that place.",
            "items": {
              "type": "string"
            }
          },
          "includeTopHeadlines": {
            "title": "Include top headlines",
            "type": "boolean",
            "description": "Also pull the Google News top-stories feed for the chosen language/country.",
            "default": false
          },
          "startUrls": {
            "title": "Google News URLs",
            "type": "array",
            "description": "Paste Google News URLs directly: search pages (`news.google.com/search?q=…`), topic pages (`/topics/…`), RSS feeds (`/rss/search?q=…`), or individual article links (`/articles/…` / `/rss/articles/…`). Non-Google article URLs are also accepted and scraped for content directly.",
            "items": {
              "type": "string"
            }
          },
          "language": {
            "title": "Language (hl)",
            "type": "string",
            "description": "Google News interface language, e.g. `en-US`, `en-GB`, `es`, `fr`, `de`, `pt-BR`. Controls the `hl` parameter.",
            "default": "en-US"
          },
          "country": {
            "title": "Country (gl)",
            "type": "string",
            "description": "Two-letter country/edition, e.g. `US`, `GB`, `CA`, `AU`, `IN`, `DE`. Controls the `gl` parameter and the news edition.",
            "default": "US"
          },
          "timeWindow": {
            "title": "Time window (search terms only)",
            "type": "string",
            "description": "Restrict search-term feeds to recent articles using a Google News `when:` window — e.g. `1h`, `12h`, `1d`, `7d`, `1y`. Leave empty for no restriction. (Applies to `searchTerms`; topics/headlines/locations are always the latest.)",
            "default": ""
          },
          "resolveArticleUrls": {
            "title": "Resolve real publisher URLs",
            "type": "boolean",
            "description": "Decode each Google News redirect link into the article's REAL publisher URL (e.g. `https://www.reuters.com/...`). This is what makes the data usable for outreach, de-duplication and content extraction. Turn off for a faster, cheaper run that keeps only the Google News links.",
            "default": true
          },
          "includeArticleContent": {
            "title": "Extract full article content",
            "type": "boolean",
            "description": "Open each resolved article and extract the full text, author(s), publish/modified dates, lead image, section, keywords/tags and word count (from JSON-LD + meta tags with a readability fallback). Adds one request per article. Some paywalled sites expose only a summary.",
            "default": false
          },
          "includeRelatedArticles": {
            "title": "Include related coverage",
            "type": "boolean",
            "description": "Attach the cluster of related articles Google News groups under each story (title, source and Google News link for each).",
            "default": true
          },
          "maxItems": {
            "title": "Max articles",
            "minimum": 1,
            "type": "integer",
            "description": "Maximum number of articles to output across the whole run (hard cap to control cost).",
            "default": 100
          },
          "maxItemsPerFeed": {
            "title": "Max articles per feed",
            "minimum": 0,
            "type": "integer",
            "description": "Cap how many articles to take from each individual feed (0 = no per-feed cap; Google News returns up to ~100 per feed).",
            "default": 0
          },
          "sinceDate": {
            "title": "Only articles since",
            "type": "string",
            "description": "Keep only articles published on/after this point. Accepts an ISO date (`2026-06-01`) or a relative window (`24h`, `3d`, `2w`, `6m`).",
            "default": ""
          },
          "includeKeywords": {
            "title": "Must include keywords",
            "type": "array",
            "description": "Keep only articles whose title or snippet contains at least one of these words/phrases (case-insensitive).",
            "items": {
              "type": "string"
            }
          },
          "excludeKeywords": {
            "title": "Exclude keywords",
            "type": "array",
            "description": "Drop articles whose title or snippet contains any of these words/phrases (case-insensitive).",
            "items": {
              "type": "string"
            }
          },
          "includeSources": {
            "title": "Only these sources",
            "type": "array",
            "description": "Keep only articles from these publishers (matches the source name, case-insensitive substring), e.g. `Reuters`, `BBC`, `TechCrunch`.",
            "items": {
              "type": "string"
            }
          },
          "excludeSources": {
            "title": "Exclude these sources",
            "type": "array",
            "description": "Drop articles from these publishers (source-name substring, case-insensitive).",
            "items": {
              "type": "string"
            }
          },
          "dedupeByResolvedUrl": {
            "title": "Deduplicate by article URL",
            "type": "boolean",
            "description": "Remove duplicate articles (the same story can appear across several feeds) by their resolved publisher URL within a run.",
            "default": true
          },
          "monitorMode": {
            "title": "Monitor mode — only new articles",
            "type": "boolean",
            "description": "Remember which articles were emitted in previous runs (in a named key-value store) and return ONLY articles not seen before — ideal for brand, competitor and topic monitoring. Works with Apify Schedules: the schedule starts the run, monitor mode deduplicates against prior runs.",
            "default": false
          },
          "monitorKey": {
            "title": "Monitor key",
            "type": "string",
            "description": "Names the monitor store so you can keep separate watch-lists (e.g. one per brand or topic). Lowercase letters, numbers and hyphens.",
            "default": "default"
          },
          "maxConcurrency": {
            "title": "Max concurrency",
            "minimum": 1,
            "maximum": 20,
            "type": "integer",
            "description": "Maximum number of requests fetched in parallel (feed, URL-decode and content fetches).",
            "default": 8
          },
          "proxyConfiguration": {
            "title": "Proxy configuration",
            "type": "object",
            "description": "Proxy settings. Google News serves clean RSS to Apify datacenter IPs, so the default Apify proxy is plenty.",
            "default": {
              "useApifyProxy": true
            }
          }
        }
      },
      "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
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}