Yandex News Story Clusters Across Russia & the CIS

{
  "description": "Search Yandex News / Dzen News by keyword, browse a category, read homepage top stories, or fetch story clusters by URL. Returns every linked article, source counts, topics and dates.",
  "properties": {
    "category": {
      "default": "politics",
      "description": "Rubric to browse (mode=browseCategory). `all` reads all 16 rubrics in one run.",
      "editor": "select",
      "enum": [
        "all",
        "politics",
        "society",
        "svo",
        "business",
        "world",
        "sport",
        "incident",
        "culture",
        "computers",
        "science",
        "auto",
        "army",
        "showbusiness",
        "health",
        "moscow",
        "personal_feed"
      ],
      "enumTitles": [
        "All categories",
        "Politics",
        "Society",
        "SVO / Ukraine conflict",
        "Business",
        "World",
        "Sport",
        "Incidents",
        "Culture",
        "Technology",
        "Science",
        "Cars",
        "Army and weapons",
        "Show business",
        "Health",
        "Moscow",
        "Interesting"
      ],
      "prefill": "politics",
      "title": "Category",
      "type": "string"
    },
    "excludeDomains": {
      "default": [],
      "description": "Drop a cluster when any linked article is from one of these domains.",
      "editor": "stringList",
      "items": {
        "type": "string"
      },
      "prefill": [],
      "title": "Exclude source domains",
      "type": "array"
    },
    "excludeKeywords": {
      "default": [],
      "description": "Drop a cluster when its headline, summary or an article headline/summary contains any of these values.",
      "editor": "stringList",
      "items": {
        "type": "string"
      },
      "prefill": [],
      "title": "Excluded keywords",
      "type": "array"
    },
    "excludePublishers": {
      "default": [],
      "description": "Drop a cluster when any linked source name contains one of these values (case-insensitive).",
      "editor": "stringList",
      "items": {
        "type": "string"
      },
      "prefill": [],
      "title": "Exclude publishers",
      "type": "array"
    },
    "includeArticles": {
      "default": true,
      "description": "Emit one record per linked article in every cluster. Turn this off for a story-only dataset.",
      "prefill": true,
      "title": "Include article records",
      "type": "boolean"
    },
    "includeDetails": {
      "default": true,
      "description": "Fetch the cluster page for topic labels, source-reported counts, images, country/region, comments and likes.",
      "prefill": true,
      "title": "Include story details",
      "type": "boolean"
    },
    "includeDomains": {
      "default": [],
      "description": "Keep a cluster when at least one linked article is from one of these domains (for example `rbc.ru`).",
      "editor": "stringList",
      "items": {
        "type": "string"
      },
      "prefill": [],
      "title": "Include source domains",
      "type": "array"
    },
    "includeKeywords": {
      "default": [],
      "description": "Keep a cluster when its headline, summary or an article headline/summary contains at least one of these values.",
      "editor": "stringList",
      "items": {
        "type": "string"
      },
      "prefill": [],
      "title": "Required keywords",
      "type": "array"
    },
    "includePublishers": {
      "default": [],
      "description": "Keep a cluster when any linked source name contains one of these values (case-insensitive).",
      "editor": "stringList",
      "items": {
        "type": "string"
      },
      "prefill": [],
      "title": "Include publishers",
      "type": "array"
    },
    "maxArticlesPerStory": {
      "default": 100,
      "description": "Maximum article records and article pages fetched per cluster. Yandex returns 100 articles per page.",
      "maximum": 1000,
      "minimum": 1,
      "prefill": 3,
      "title": "Maximum articles per story",
      "type": "integer"
    },
    "maxStories": {
      "default": 20,
      "description": "Maximum number of story clusters to return across the whole run. Yandex search depth varies by query.",
      "maximum": 500,
      "minimum": 1,
      "prefill": 3,
      "title": "Maximum story clusters",
      "type": "integer"
    },
    "mode": {
      "default": "searchNews",
      "description": "What to scrape. `searchNews` searches keywords, `browseCategory` reads a rubric feed, `topStories` reads the homepage sections, and `byStoryUrls` resolves specific story clusters.",
      "editor": "select",
      "enum": [
        "searchNews",
        "browseCategory",
        "topStories",
        "byStoryUrls"
      ],
      "enumTitles": [
        "Search news by keyword",
        "Browse a category",
        "Homepage top stories",
        "Fetch story clusters by URL"
      ],
      "prefill": "searchNews",
      "title": "Mode",
      "type": "string"
    },
    "publishedAfter": {
      "description": "Inclusive start date in YYYY-MM-DD format (mode=searchNews). Leave blank for no lower bound.",
      "editor": "textfield",
      "title": "Published after",
      "type": "string"
    },
    "publishedBefore": {
      "description": "Inclusive end date in YYYY-MM-DD format (mode=searchNews). Leave blank for no upper bound.",
      "editor": "textfield",
      "title": "Published before",
      "type": "string"
    },
    "searchQueries": {
      "description": "One or more keywords or phrases (mode=searchNews). Russian and English queries are supported. The daily-test prefill uses one query.",
      "editor": "stringList",
      "items": {
        "type": "string"
      },
      "prefill": [
        "Яндекс"
      ],
      "title": "Search queries",
      "type": "array"
    },
    "sortOrder": {
      "default": "newest",
      "description": "Order of the returned search clusters (mode=searchNews). Yandex search itself is relevance-ranked; these options sort the returned set.",
      "editor": "select",
      "enum": [
        "relevance",
        "newest",
        "oldest",
        "mostCovered"
      ],
      "enumTitles": [
        "Yandex relevance",
        "Newest first",
        "Oldest first",
        "Most covered first"
      ],
      "prefill": "newest",
      "title": "Sort order",
      "type": "string"
    },
    "storyUrls": {
      "description": "Dzen News story or instory URLs, or bare cluster UUIDs (mode=byStoryUrls). A bare numeric persistent ID is not a valid cluster URL.",
      "editor": "stringList",
      "items": {
        "type": "string"
      },
      "prefill": [],
      "title": "Story URLs or cluster IDs",
      "type": "array"
    },
    "timeRange": {
      "default": "any",
      "description": "Keep clusters published in this window (mode=searchNews). Applied to the results Yandex returns. A custom date range overrides this field.",
      "editor": "select",
      "enum": [
        "any",
        "day",
        "week",
        "month"
      ],
      "enumTitles": [
        "Any time",
        "Past day",
        "Past week",
        "Past month"
      ],
      "prefill": "any",
      "title": "Publication time",
      "type": "string"
    }
  },
  "required": [
    "mode"
  ],
  "schemaVersion": 1,
  "title": "Yandex News Story Clusters Input",
  "type": "object"
}

{
  "actorOutputSchemaVersion": 1,
  "description": "Story clusters and their linked articles from Yandex News / Dzen News, including source counts, topics, images and publication times.",
  "properties": {
    "results": {
      "description": "Dataset containing scraped story clusters, linked articles and homepage sections.",
      "template": "{{links.apiDefaultDatasetUrl}}/items",
      "title": "Yandex News results",
      "type": "string"
    }
  },
  "title": "Yandex News Story Clusters Output"
}

{
  "actorSpecification": 1,
  "title": "Yandex News Results",
  "views": {
    "articles": {
      "display": {
        "component": "table",
        "properties": {
          "articleUrl": {
            "format": "link",
            "label": "Article URL"
          },
          "headline": {
            "format": "text",
            "label": "Headline"
          },
          "imageUrl": {
            "format": "link",
            "label": "Image"
          },
          "publishedAt": {
            "format": "text",
            "label": "Published"
          },
          "sourceName": {
            "format": "text",
            "label": "Source"
          },
          "storyId": {
            "format": "text",
            "label": "Story ID"
          }
        }
      },
      "title": "Articles",
      "transformation": {
        "fields": [
          "recordType",
          "storyId",
          "docId",
          "headline",
          "sourceName",
          "articleUrl",
          "publishedAt",
          "publishedAtIso",
          "imageUrl",
          "scrapedAt"
        ]
      }
    },
    "stories": {
      "display": {
        "component": "table",
        "properties": {
          "articleCount": {
            "format": "number",
            "label": "Sources (reported)"
          },
          "articlesReturned": {
            "format": "number",
            "label": "Articles returned"
          },
          "category": {
            "format": "text",
            "label": "Category"
          },
          "headline": {
            "format": "text",
            "label": "Headline"
          },
          "publishedAt": {
            "format": "text",
            "label": "Published"
          },
          "sourceCount": {
            "format": "number",
            "label": "Unique sources"
          },
          "storyId": {
            "format": "text",
            "label": "Story ID"
          },
          "storyUrl": {
            "format": "link",
            "label": "Story URL"
          },
          "topics": {
            "format": "array",
            "label": "Topics"
          }
        }
      },
      "title": "Stories",
      "transformation": {
        "fields": [
          "recordType",
          "storyId",
          "persistentId",
          "headline",
          "category",
          "topics",
          "articleCount",
          "articlesReturned",
          "sourceCount",
          "leadSource",
          "publishedAt",
          "storyUrl",
          "scrapedAt"
        ]
      }
    },
    "trending": {
      "display": {
        "component": "table",
        "properties": {
          "sectionCounts": {
            "format": "text",
            "label": "Counts"
          },
          "topics": {
            "format": "array",
            "label": "Sections"
          }
        }
      },
      "title": "Homepage sections",
      "transformation": {
        "fields": [
          "recordType",
          "topics",
          "sectionCounts",
          "domain",
          "scrapedAt"
        ]
      }
    }
  }
}