Apache Nutch · JSON Structure

Apache Nutch Job Config Structure

Configuration for creating a new crawl job.

Type: object Properties: 5 Required: 1
Web CrawlerIndexingSearchApacheJavaHadoopOpen Source

JobConfig is a JSON Structure definition published by Apache Nutch, describing 5 properties, of which 1 is required. It conforms to the https://json-structure.org/meta/core/v0/# meta-schema.

Properties

crawlId type confId jobClassName args

Meta-schema: https://json-structure.org/meta/core/v0/#

JSON Structure

Raw ↑ 
{
  "$schema": "https://json-structure.org/meta/core/v0/#",
  "$id": "https://raw.githubusercontent.com/api-evangelist/apache-nutch/refs/heads/main/json-structure/apache-nutch-job-config-structure.json",
  "name": "JobConfig",
  "description": "Configuration for creating a new crawl job.",
  "type": "object",
  "properties": {
    "crawlId": {
      "type": "string",
      "description": "The crawl identifier."
    },
    "type": {
      "type": "string",
      "description": "The type of Nutch crawl job.",
      "enum": [
        "INJECT",
        "GENERATE",
        "FETCH",
        "PARSE",
        "UPDATEDB",
        "INDEX",
        "READDB",
        "CLASS",
        "INVERTLINKS",
        "DEDUP"
      ]
    },
    "confId": {
      "type": "string",
      "description": "The configuration ID to use for this job. Defaults to \"default\" if not specified."
    },
    "jobClassName": {
      "type": "string",
      "description": "Fully qualified class name when type is CLASS."
    },
    "args": {
      "type": "object",
      "additionalProperties": true,
      "description": "Additional arguments for the job."
    }
  },
  "required": [
    "type"
  ],
  "example": {
    "crawlId": "crawl-01",
    "type": "INJECT",
    "confId": "default",
    "args": {
      "seedDir": "seedFiles/seed-1700000000000"
    }
  }
}