{
  "module": "omniread.csv.scraper",
  "content": {
    "path": "omniread.csv.scraper",
    "docstring": "# Summary\n\nCSV scraper for OmniRead.\n\nThis module defines the scraper responsible for acquiring raw\ncomma-separated-value document content from a backing store via a\nconfigured client.\n\nThe scraper does not interpret or parse the acquired bytes; it wraps them in\nthe canonical `Content` model.",
    "objects": {
      "Mapping": {
        "name": "Mapping",
        "kind": "alias",
        "path": "omniread.csv.scraper.Mapping",
        "signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
        "docstring": null
      },
      "Any": {
        "name": "Any",
        "kind": "alias",
        "path": "omniread.csv.scraper.Any",
        "signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
        "docstring": null
      },
      "Content": {
        "name": "Content",
        "kind": "class",
        "path": "omniread.csv.scraper.Content",
        "signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
        "docstring": "Normalized representation of extracted content.\n\nNotes:\n    **Responsibilities:**\n\n        - A `Content` instance represents a raw content payload along with\n          minimal contextual metadata describing its origin and type.\n        - This class is the primary exchange format between scrapers,\n          parsers, and downstream consumers.",
        "members": {
          "raw": {
            "name": "raw",
            "kind": "attribute",
            "path": "omniread.csv.scraper.Content.raw",
            "signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
            "docstring": "Raw content bytes as retrieved from the source."
          },
          "source": {
            "name": "source",
            "kind": "attribute",
            "path": "omniread.csv.scraper.Content.source",
            "signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
            "docstring": "Identifier of the content origin (URL, file path, or logical name)."
          },
          "content_type": {
            "name": "content_type",
            "kind": "attribute",
            "path": "omniread.csv.scraper.Content.content_type",
            "signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
            "docstring": "Optional MIME type of the content, if known."
          },
          "metadata": {
            "name": "metadata",
            "kind": "attribute",
            "path": "omniread.csv.scraper.Content.metadata",
            "signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
            "docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
          }
        }
      },
      "ContentType": {
        "name": "ContentType",
        "kind": "class",
        "path": "omniread.csv.scraper.ContentType",
        "signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
        "docstring": "Supported MIME types for extracted content.\n\nNotes:\n    **Guarantees:**\n\n        - This enum represents the declared or inferred media type of the\n          content source.\n        - It is primarily used for routing content to the appropriate\n          parser or downstream consumer.",
        "members": {
          "HTML": {
            "name": "HTML",
            "kind": "attribute",
            "path": "omniread.csv.scraper.ContentType.HTML",
            "signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
            "docstring": "HTML document content."
          },
          "PDF": {
            "name": "PDF",
            "kind": "attribute",
            "path": "omniread.csv.scraper.ContentType.PDF",
            "signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
            "docstring": "PDF document content."
          },
          "XLSX": {
            "name": "XLSX",
            "kind": "attribute",
            "path": "omniread.csv.scraper.ContentType.XLSX",
            "signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
            "docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
          },
          "CSV": {
            "name": "CSV",
            "kind": "attribute",
            "path": "omniread.csv.scraper.ContentType.CSV",
            "signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
            "docstring": "Comma-separated-value document content."
          },
          "JSON": {
            "name": "JSON",
            "kind": "attribute",
            "path": "omniread.csv.scraper.ContentType.JSON",
            "signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
            "docstring": "JSON document content."
          },
          "XML": {
            "name": "XML",
            "kind": "attribute",
            "path": "omniread.csv.scraper.ContentType.XML",
            "signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
            "docstring": "XML document content."
          }
        }
      },
      "BaseCsvClient": {
        "name": "BaseCsvClient",
        "kind": "class",
        "path": "omniread.csv.scraper.BaseCsvClient",
        "signature": "<bound method Alias.signature of Alias('BaseCsvClient', 'omniread.csv.client.BaseCsvClient')>",
        "docstring": "Abstract client responsible for retrieving csv bytes.\n\nRetrieves bytes from a specific backing store (filesystem, S3, FTP, etc.).\n\nNotes:\n    **Responsibilities:**\n\n        - Implementations must accept a source identifier appropriate to\n          the backing store.\n        - Return the full csv binary payload.\n        - Raise retrieval-specific errors on failure.",
        "members": {
          "fetch": {
            "name": "fetch",
            "kind": "function",
            "path": "omniread.csv.scraper.BaseCsvClient.fetch",
            "signature": "<bound method Alias.signature of Alias('fetch', 'omniread.csv.client.BaseCsvClient.fetch')>",
            "docstring": "Fetch raw csv bytes from the given source.\n\nArgs:\n    source (Any):\n        Identifier of the csv location, such as a file path,\n        object storage key, or remote reference.\n\nReturns:\n    bytes:\n        Raw csv bytes.\n\nRaises:\n    Exception:\n        Retrieval-specific errors defined by the implementation."
          }
        }
      },
      "CsvScraper": {
        "name": "CsvScraper",
        "kind": "class",
        "path": "omniread.csv.scraper.CsvScraper",
        "signature": "<bound method Class.signature of Class('CsvScraper', 22, 81)>",
        "docstring": "Scraper for csv documents.\n\nNotes:\n    **Responsibilities:**\n\n        - Fetch raw csv bytes via the configured client.\n        - Wrap the payload in a canonical `Content` instance with the\n          CSV content type and source identifier.\n\n    **Constraints:**\n\n        - The scraper does not perform parsing or interpretation.\n        - Does not assume a specific storage backend.",
        "members": {
          "fetch": {
            "name": "fetch",
            "kind": "function",
            "path": "omniread.csv.scraper.CsvScraper.fetch",
            "signature": "<bound method Function.signature of Function('fetch', 49, 81)>",
            "docstring": "Fetch a csv document from the given source.\n\nArgs:\n    source (Any):\n        Identifier of the csv source as understood by the\n        configured client.\n    metadata (Optional[Mapping[str, Any]], optional):\n        Optional metadata to attach to the returned content.\n\nReturns:\n    Content:\n        A `Content` instance containing raw csv bytes, source\n        identifier, CSV content type, and optional metadata.\n\nRaises:\n    Exception:\n        Retrieval-specific errors raised by the client."
          }
        }
      }
    }
  }
}