{
  "module": "omniread.pdf.scraper",
  "content": {
    "path": "omniread.pdf.scraper",
    "docstring": "PDF scraping implementation for OmniRead.\n\n---\n\n## Summary\n\nThis module provides a PDF-specific scraper that coordinates PDF byte\nretrieval via a client and normalizes the result into a `Content` object.\n\nThe scraper implements the core `BaseScraper` contract while delegating\nall storage and access concerns to a `BasePDFClient` implementation.",
    "objects": {
      "Any": {
        "name": "Any",
        "kind": "alias",
        "path": "omniread.pdf.scraper.Any",
        "signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
        "docstring": null
      },
      "Mapping": {
        "name": "Mapping",
        "kind": "alias",
        "path": "omniread.pdf.scraper.Mapping",
        "signature": "<bound method Alias.signature of Alias('Mapping', 'typing.Mapping')>",
        "docstring": null
      },
      "Optional": {
        "name": "Optional",
        "kind": "alias",
        "path": "omniread.pdf.scraper.Optional",
        "signature": "<bound method Alias.signature of Alias('Optional', 'typing.Optional')>",
        "docstring": null
      },
      "Content": {
        "name": "Content",
        "kind": "class",
        "path": "omniread.pdf.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 minimal contextual metadata describing its origin and type\n        - This class is the primary exchange format between Scrapers, Parsers, and Downstream consumers",
        "members": {
          "raw": {
            "name": "raw",
            "kind": "attribute",
            "path": "omniread.pdf.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.pdf.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.pdf.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.pdf.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.pdf.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 content source\n        - It is primarily used for routing content to the appropriate parser or downstream consumer",
        "members": {
          "HTML": {
            "name": "HTML",
            "kind": "attribute",
            "path": "omniread.pdf.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.pdf.scraper.ContentType.PDF",
            "signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
            "docstring": "PDF document content."
          },
          "JSON": {
            "name": "JSON",
            "kind": "attribute",
            "path": "omniread.pdf.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.pdf.scraper.ContentType.XML",
            "signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
            "docstring": "XML document content."
          }
        }
      },
      "BaseScraper": {
        "name": "BaseScraper",
        "kind": "class",
        "path": "omniread.pdf.scraper.BaseScraper",
        "signature": "<bound method Alias.signature of Alias('BaseScraper', 'omniread.core.scraper.BaseScraper')>",
        "docstring": "Base interface for all scrapers.\n\nNotes:\n    **Responsibilities:**\n\n        - A scraper is responsible ONLY for fetching raw content (bytes) from a source. It must not interpret or parse it\n        - A scraper is a stateless acquisition component that retrieves raw content from a source and returns it as a `Content` object\n        - Scrapers define how content is obtained, not what the content means\n        - Implementations may vary in transport mechanism, authentication strategy, retry and backoff behavior\n\n    **Constraints:**\n\n        - Implementations must not parse content, modify content semantics, or couple scraping logic to a specific parser",
        "members": {
          "fetch": {
            "name": "fetch",
            "kind": "function",
            "path": "omniread.pdf.scraper.BaseScraper.fetch",
            "signature": "<bound method Alias.signature of Alias('fetch', 'omniread.core.scraper.BaseScraper.fetch')>",
            "docstring": "Fetch raw content from the given source.\n\nArgs:\n    source (str):\n        Location identifier (URL, file path, S3 URI, etc.)\n    metadata (Optional[Mapping[str, Any]], optional):\n        Optional hints for the scraper (headers, auth, etc.)\n\nReturns:\n    Content:\n        Content object containing raw bytes and metadata.\n\nRaises:\n    Exception:\n        Retrieval-specific errors as defined by the implementation.\n\nNotes:\n    **Responsibilities:**\n\n        - Implementations must retrieve the content referenced by `source` and return it as raw bytes wrapped in a `Content` object"
          }
        }
      },
      "BasePDFClient": {
        "name": "BasePDFClient",
        "kind": "class",
        "path": "omniread.pdf.scraper.BasePDFClient",
        "signature": "<bound method Alias.signature of Alias('BasePDFClient', 'omniread.pdf.client.BasePDFClient')>",
        "docstring": "Abstract client responsible for retrieving PDF bytes\nfrom a specific backing store (filesystem, S3, FTP, etc.).\n\nNotes:\n    **Responsibilities:**\n\n        - Implementations must accept a source identifier appropriate to the backing store, return the full PDF binary payload, and raise retrieval-specific errors on failure",
        "members": {
          "fetch": {
            "name": "fetch",
            "kind": "function",
            "path": "omniread.pdf.scraper.BasePDFClient.fetch",
            "signature": "<bound method Alias.signature of Alias('fetch', 'omniread.pdf.client.BasePDFClient.fetch')>",
            "docstring": "Fetch raw PDF bytes from the given source.\n\nArgs:\n    source (Any):\n        Identifier of the PDF location, such as a file path, object storage key, or remote reference.\n\nReturns:\n    bytes:\n        Raw PDF bytes.\n\nRaises:\n    Exception:\n        Retrieval-specific errors defined by the implementation."
          }
        }
      },
      "PDFScraper": {
        "name": "PDFScraper",
        "kind": "class",
        "path": "omniread.pdf.scraper.PDFScraper",
        "signature": "<bound method Class.signature of Class('PDFScraper', 22, 77)>",
        "docstring": "Scraper for PDF sources.\n\nNotes:\n    **Responsibilities:**\n\n        - Delegates byte retrieval to a PDF client and normalizes output into Content\n        - Preserves caller-provided metadata\n\n    **Constraints:**\n    \n        - The scraper: Does not perform parsing or interpretation, does not assume a specific storage backend",
        "members": {
          "fetch": {
            "name": "fetch",
            "kind": "function",
            "path": "omniread.pdf.scraper.PDFScraper.fetch",
            "signature": "<bound method Function.signature of Function('fetch', 47, 77)>",
            "docstring": "Fetch a PDF document from the given source.\n\nArgs:\n    source (Any):\n        Identifier of the PDF source as understood by the configured PDF 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 PDF bytes, source identifier, PDF content type, and optional metadata.\n\nRaises:\n    Exception:\n        Retrieval-specific errors raised by the PDF client."
          }
        }
      }
    }
  }
}