419 lines
26 KiB
JSON
419 lines
26 KiB
JSON
{
|
|
"module": "omniread.pdf",
|
|
"content": {
|
|
"path": "omniread.pdf",
|
|
"docstring": "PDF format implementation for OmniRead.\n\nThis package provides **PDF-specific implementations** of the core OmniRead\ncontracts defined in `omniread.core`.\n\nUnlike HTML, PDF handling requires an explicit client layer for document\naccess. This package therefore includes:\n- PDF clients for acquiring raw PDF data\n- PDF scrapers that coordinate client access\n- PDF parsers that extract structured content from PDF binaries\n\nPublic exports from this package represent the supported PDF pipeline\nand are safe for consumers to import directly when working with PDFs.",
|
|
"objects": {
|
|
"FileSystemPDFClient": {
|
|
"name": "FileSystemPDFClient",
|
|
"kind": "class",
|
|
"path": "omniread.pdf.FileSystemPDFClient",
|
|
"signature": "<bound method Alias.signature of Alias('FileSystemPDFClient', 'omniread.pdf.client.FileSystemPDFClient')>",
|
|
"docstring": "PDF client that reads from the local filesystem.\n\nThis client reads PDF files directly from the disk and returns their raw\nbinary contents.",
|
|
"members": {
|
|
"fetch": {
|
|
"name": "fetch",
|
|
"kind": "function",
|
|
"path": "omniread.pdf.FileSystemPDFClient.fetch",
|
|
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.pdf.client.FileSystemPDFClient.fetch')>",
|
|
"docstring": "Read a PDF file from the local filesystem.\n\nArgs:\n path: Filesystem path to the PDF file.\n\nReturns:\n Raw PDF bytes.\n\nRaises:\n FileNotFoundError: If the path does not exist.\n ValueError: If the path exists but is not a file."
|
|
}
|
|
}
|
|
},
|
|
"PDFScraper": {
|
|
"name": "PDFScraper",
|
|
"kind": "class",
|
|
"path": "omniread.pdf.PDFScraper",
|
|
"signature": "<bound method Alias.signature of Alias('PDFScraper', 'omniread.pdf.scraper.PDFScraper')>",
|
|
"docstring": "Scraper for PDF sources.\n\nDelegates byte retrieval to a PDF client and normalizes\noutput into Content.\n\nThe scraper:\n- Does not perform parsing or interpretation\n- Does not assume a specific storage backend\n- Preserves caller-provided metadata",
|
|
"members": {
|
|
"fetch": {
|
|
"name": "fetch",
|
|
"kind": "function",
|
|
"path": "omniread.pdf.PDFScraper.fetch",
|
|
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.pdf.scraper.PDFScraper.fetch')>",
|
|
"docstring": "Fetch a PDF document from the given source.\n\nArgs:\n source: Identifier of the PDF source as understood by the\n configured PDF client.\n metadata: Optional metadata to attach to the returned content.\n\nReturns:\n A `Content` instance containing:\n - Raw PDF bytes\n - Source identifier\n - PDF content type\n - Optional metadata\n\nRaises:\n Exception: Retrieval-specific errors raised by the PDF client."
|
|
}
|
|
}
|
|
},
|
|
"PDFParser": {
|
|
"name": "PDFParser",
|
|
"kind": "class",
|
|
"path": "omniread.pdf.PDFParser",
|
|
"signature": "<bound method Alias.signature of Alias('PDFParser', 'omniread.pdf.parser.PDFParser')>",
|
|
"docstring": "Base PDF parser.\n\nThis class enforces PDF content-type compatibility and provides the\nextension point for implementing concrete PDF parsing strategies.\n\nConcrete implementations must define:\n- Define the output type `T`\n- Implement the `parse()` method",
|
|
"members": {
|
|
"supported_types": {
|
|
"name": "supported_types",
|
|
"kind": "attribute",
|
|
"path": "omniread.pdf.PDFParser.supported_types",
|
|
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.pdf.parser.PDFParser.supported_types')>",
|
|
"docstring": "Set of content types supported by this parser (PDF only)."
|
|
},
|
|
"parse": {
|
|
"name": "parse",
|
|
"kind": "function",
|
|
"path": "omniread.pdf.PDFParser.parse",
|
|
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.pdf.parser.PDFParser.parse')>",
|
|
"docstring": "Parse PDF content into a structured output.\n\nImplementations must fully interpret the PDF binary payload and\nreturn a deterministic, structured output.\n\nReturns:\n Parsed representation of type `T`.\n\nRaises:\n Exception: Parsing-specific errors as defined by the implementation."
|
|
}
|
|
}
|
|
},
|
|
"client": {
|
|
"name": "client",
|
|
"kind": "module",
|
|
"path": "omniread.pdf.client",
|
|
"signature": null,
|
|
"docstring": "PDF client abstractions for OmniRead.\n\nThis module defines the **client layer** responsible for retrieving raw PDF\nbytes from a concrete backing store.\n\nClients provide low-level access to PDF binaries and are intentionally\ndecoupled from scraping and parsing logic. They do not perform validation,\ninterpretation, or content extraction.\n\nTypical backing stores include:\n- Local filesystems\n- Object storage (S3, GCS, etc.)\n- Network file systems",
|
|
"members": {
|
|
"Any": {
|
|
"name": "Any",
|
|
"kind": "alias",
|
|
"path": "omniread.pdf.client.Any",
|
|
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
|
"docstring": null
|
|
},
|
|
"ABC": {
|
|
"name": "ABC",
|
|
"kind": "alias",
|
|
"path": "omniread.pdf.client.ABC",
|
|
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
|
"docstring": null
|
|
},
|
|
"abstractmethod": {
|
|
"name": "abstractmethod",
|
|
"kind": "alias",
|
|
"path": "omniread.pdf.client.abstractmethod",
|
|
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
|
"docstring": null
|
|
},
|
|
"Path": {
|
|
"name": "Path",
|
|
"kind": "alias",
|
|
"path": "omniread.pdf.client.Path",
|
|
"signature": "<bound method Alias.signature of Alias('Path', 'pathlib.Path')>",
|
|
"docstring": null
|
|
},
|
|
"BasePDFClient": {
|
|
"name": "BasePDFClient",
|
|
"kind": "class",
|
|
"path": "omniread.pdf.client.BasePDFClient",
|
|
"signature": "<bound method Class.signature of Class('BasePDFClient', 22, 48)>",
|
|
"docstring": "Abstract client responsible for retrieving PDF bytes\nfrom a specific backing store (filesystem, S3, FTP, etc.).\n\nImplementations must:\n- Accept a source identifier appropriate to the backing store\n- Return the full PDF binary payload\n- Raise retrieval-specific errors on failure",
|
|
"members": {
|
|
"fetch": {
|
|
"name": "fetch",
|
|
"kind": "function",
|
|
"path": "omniread.pdf.client.BasePDFClient.fetch",
|
|
"signature": "<bound method Function.signature of Function('fetch', 33, 48)>",
|
|
"docstring": "Fetch raw PDF bytes from the given source.\n\nArgs:\n source: Identifier of the PDF location, such as a file path,\n object storage key, or remote reference.\n\nReturns:\n Raw PDF bytes.\n\nRaises:\n Exception: Retrieval-specific errors defined by the implementation."
|
|
}
|
|
}
|
|
},
|
|
"FileSystemPDFClient": {
|
|
"name": "FileSystemPDFClient",
|
|
"kind": "class",
|
|
"path": "omniread.pdf.client.FileSystemPDFClient",
|
|
"signature": "<bound method Class.signature of Class('FileSystemPDFClient', 51, 80)>",
|
|
"docstring": "PDF client that reads from the local filesystem.\n\nThis client reads PDF files directly from the disk and returns their raw\nbinary contents.",
|
|
"members": {
|
|
"fetch": {
|
|
"name": "fetch",
|
|
"kind": "function",
|
|
"path": "omniread.pdf.client.FileSystemPDFClient.fetch",
|
|
"signature": "<bound method Function.signature of Function('fetch', 59, 80)>",
|
|
"docstring": "Read a PDF file from the local filesystem.\n\nArgs:\n path: Filesystem path to the PDF file.\n\nReturns:\n Raw PDF bytes.\n\nRaises:\n FileNotFoundError: If the path does not exist.\n ValueError: If the path exists but is not a file."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"parser": {
|
|
"name": "parser",
|
|
"kind": "module",
|
|
"path": "omniread.pdf.parser",
|
|
"signature": null,
|
|
"docstring": "PDF parser base implementations for OmniRead.\n\nThis module defines the **PDF-specific parser contract**, extending the\nformat-agnostic `BaseParser` with constraints appropriate for PDF content.\n\nPDF parsers are responsible for interpreting binary PDF data and producing\nstructured representations suitable for downstream consumption.",
|
|
"members": {
|
|
"Generic": {
|
|
"name": "Generic",
|
|
"kind": "alias",
|
|
"path": "omniread.pdf.parser.Generic",
|
|
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
|
"docstring": null
|
|
},
|
|
"TypeVar": {
|
|
"name": "TypeVar",
|
|
"kind": "alias",
|
|
"path": "omniread.pdf.parser.TypeVar",
|
|
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
|
"docstring": null
|
|
},
|
|
"abstractmethod": {
|
|
"name": "abstractmethod",
|
|
"kind": "alias",
|
|
"path": "omniread.pdf.parser.abstractmethod",
|
|
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
|
"docstring": null
|
|
},
|
|
"ContentType": {
|
|
"name": "ContentType",
|
|
"kind": "class",
|
|
"path": "omniread.pdf.parser.ContentType",
|
|
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
|
"docstring": "Supported MIME types for extracted content.\n\nThis enum represents the declared or inferred media type of the content\nsource. It is primarily used for routing content to the appropriate\nparser or downstream consumer.",
|
|
"members": {
|
|
"HTML": {
|
|
"name": "HTML",
|
|
"kind": "attribute",
|
|
"path": "omniread.pdf.parser.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.parser.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.parser.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.parser.ContentType.XML",
|
|
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
|
"docstring": "XML document content."
|
|
}
|
|
}
|
|
},
|
|
"BaseParser": {
|
|
"name": "BaseParser",
|
|
"kind": "class",
|
|
"path": "omniread.pdf.parser.BaseParser",
|
|
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
|
"docstring": "Base interface for all parsers.\n\nA parser is a self-contained object that owns the Content\nit is responsible for interpreting.\n\nImplementations must:\n- Declare supported content types via `supported_types`\n- Raise parsing-specific exceptions from `parse()`\n- Remain deterministic for a given input\n\nConsumers may rely on:\n- Early validation of content compatibility\n- Type-stable return values from `parse()`",
|
|
"members": {
|
|
"supported_types": {
|
|
"name": "supported_types",
|
|
"kind": "attribute",
|
|
"path": "omniread.pdf.parser.BaseParser.supported_types",
|
|
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.core.parser.BaseParser.supported_types')>",
|
|
"docstring": "Set of content types supported by this parser.\n\nAn empty set indicates that the parser is content-type agnostic."
|
|
},
|
|
"content": {
|
|
"name": "content",
|
|
"kind": "attribute",
|
|
"path": "omniread.pdf.parser.BaseParser.content",
|
|
"signature": "<bound method Alias.signature of Alias('content', 'omniread.core.parser.BaseParser.content')>",
|
|
"docstring": null
|
|
},
|
|
"parse": {
|
|
"name": "parse",
|
|
"kind": "function",
|
|
"path": "omniread.pdf.parser.BaseParser.parse",
|
|
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.core.parser.BaseParser.parse')>",
|
|
"docstring": "Parse the owned content into structured output.\n\nImplementations must fully consume the provided content and\nreturn a deterministic, structured output.\n\nReturns:\n Parsed, structured representation.\n\nRaises:\n Exception: Parsing-specific errors as defined by the implementation."
|
|
},
|
|
"supports": {
|
|
"name": "supports",
|
|
"kind": "function",
|
|
"path": "omniread.pdf.parser.BaseParser.supports",
|
|
"signature": "<bound method Alias.signature of Alias('supports', 'omniread.core.parser.BaseParser.supports')>",
|
|
"docstring": "Check whether this parser supports the content's type.\n\nReturns:\n True if the content type is supported; False otherwise."
|
|
}
|
|
}
|
|
},
|
|
"T": {
|
|
"name": "T",
|
|
"kind": "attribute",
|
|
"path": "omniread.pdf.parser.T",
|
|
"signature": null,
|
|
"docstring": null
|
|
},
|
|
"PDFParser": {
|
|
"name": "PDFParser",
|
|
"kind": "class",
|
|
"path": "omniread.pdf.parser.PDFParser",
|
|
"signature": "<bound method Class.signature of Class('PDFParser', 20, 49)>",
|
|
"docstring": "Base PDF parser.\n\nThis class enforces PDF content-type compatibility and provides the\nextension point for implementing concrete PDF parsing strategies.\n\nConcrete implementations must define:\n- Define the output type `T`\n- Implement the `parse()` method",
|
|
"members": {
|
|
"supported_types": {
|
|
"name": "supported_types",
|
|
"kind": "attribute",
|
|
"path": "omniread.pdf.parser.PDFParser.supported_types",
|
|
"signature": null,
|
|
"docstring": "Set of content types supported by this parser (PDF only)."
|
|
},
|
|
"parse": {
|
|
"name": "parse",
|
|
"kind": "function",
|
|
"path": "omniread.pdf.parser.PDFParser.parse",
|
|
"signature": "<bound method Function.signature of Function('parse', 35, 49)>",
|
|
"docstring": "Parse PDF content into a structured output.\n\nImplementations must fully interpret the PDF binary payload and\nreturn a deterministic, structured output.\n\nReturns:\n Parsed representation of type `T`.\n\nRaises:\n Exception: Parsing-specific errors as defined by the implementation."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"scraper": {
|
|
"name": "scraper",
|
|
"kind": "module",
|
|
"path": "omniread.pdf.scraper",
|
|
"signature": null,
|
|
"docstring": "PDF scraping implementation for OmniRead.\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.",
|
|
"members": {
|
|
"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\nA `Content` instance represents a raw content payload along with minimal\ncontextual metadata describing its origin and type.\n\nThis class is the **primary exchange format** between:\n- Scrapers\n- Parsers\n- Downstream consumers\n\nAttributes:\n raw: Raw content bytes as retrieved from the source.\n source: Identifier of the content origin (URL, file path, or logical name).\n content_type: Optional MIME type of the content, if known.\n metadata: Optional, implementation-defined metadata associated with\n the content (e.g., headers, encoding hints, extraction notes).",
|
|
"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": null
|
|
},
|
|
"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": null
|
|
},
|
|
"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": null
|
|
},
|
|
"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": null
|
|
}
|
|
}
|
|
},
|
|
"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\nThis enum represents the declared or inferred media type of the content\nsource. It is primarily used for routing content to the appropriate\nparser 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\nA scraper is responsible ONLY for fetching raw content\n(bytes) from a source. It must not interpret or parse it.\n\nA scraper is a **stateless acquisition component** that retrieves raw\ncontent from a source and returns it as a `Content` object.\n\nScrapers define *how content is obtained*, not *what the content means*.\n\nImplementations may vary in:\n- Transport mechanism (HTTP, filesystem, cloud storage)\n- Authentication strategy\n- Retry and backoff behavior\n\nImplementations must not:\n- Parse content\n- Modify content semantics\n- 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\nImplementations must retrieve the content referenced by `source`\nand return it as raw bytes wrapped in a `Content` object.\n\nArgs:\n source: Location identifier (URL, file path, S3 URI, etc.)\n metadata: Optional hints for the scraper (headers, auth, etc.)\n\nReturns:\n Content object containing raw bytes and metadata.\n - Raw content bytes\n - Source identifier\n - Optional metadata\n\nRaises:\n Exception: Retrieval-specific errors as defined by the implementation."
|
|
}
|
|
}
|
|
},
|
|
"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\nImplementations must:\n- Accept a source identifier appropriate to the backing store\n- Return the full PDF binary payload\n- 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: Identifier of the PDF location, such as a file path,\n object storage key, or remote reference.\n\nReturns:\n Raw PDF bytes.\n\nRaises:\n Exception: 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', 18, 71)>",
|
|
"docstring": "Scraper for PDF sources.\n\nDelegates byte retrieval to a PDF client and normalizes\noutput into Content.\n\nThe scraper:\n- Does not perform parsing or interpretation\n- Does not assume a specific storage backend\n- Preserves caller-provided metadata",
|
|
"members": {
|
|
"fetch": {
|
|
"name": "fetch",
|
|
"kind": "function",
|
|
"path": "omniread.pdf.scraper.PDFScraper.fetch",
|
|
"signature": "<bound method Function.signature of Function('fetch', 40, 71)>",
|
|
"docstring": "Fetch a PDF document from the given source.\n\nArgs:\n source: Identifier of the PDF source as understood by the\n configured PDF client.\n metadata: Optional metadata to attach to the returned content.\n\nReturns:\n A `Content` instance containing:\n - Raw PDF bytes\n - Source identifier\n - PDF content type\n - Optional metadata\n\nRaises:\n Exception: Retrieval-specific errors raised by the PDF client."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
} |