Files
omniread/mcp_docs/modules/omniread.core.scraper.json

97 lines
5.9 KiB
JSON

{
"module": "omniread.core.scraper",
"content": {
"path": "omniread.core.scraper",
"docstring": "# Summary\n\nAbstract scraping contracts for OmniRead.\n\nThis module defines the **format-agnostic scraper interface** responsible for\nacquiring raw content from external sources.\n\nScrapers are responsible for:\n\n- Locating and retrieving raw content bytes\n- Attaching minimal contextual metadata\n- Returning normalized `Content` objects\n\nScrapers are explicitly NOT responsible for:\n\n- Parsing or interpreting content\n- Inferring structure or semantics\n- Performing content-type specific processing\n\nAll interpretation must be delegated to parsers.",
"objects": {
"ABC": {
"name": "ABC",
"kind": "alias",
"path": "omniread.core.scraper.ABC",
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
"docstring": null
},
"abstractmethod": {
"name": "abstractmethod",
"kind": "alias",
"path": "omniread.core.scraper.abstractmethod",
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
"docstring": null
},
"Any": {
"name": "Any",
"kind": "alias",
"path": "omniread.core.scraper.Any",
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
"docstring": null
},
"Mapping": {
"name": "Mapping",
"kind": "alias",
"path": "omniread.core.scraper.Mapping",
"signature": "<bound method Alias.signature of Alias('Mapping', 'typing.Mapping')>",
"docstring": null
},
"Optional": {
"name": "Optional",
"kind": "alias",
"path": "omniread.core.scraper.Optional",
"signature": "<bound method Alias.signature of Alias('Optional', 'typing.Optional')>",
"docstring": null
},
"Content": {
"name": "Content",
"kind": "class",
"path": "omniread.core.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.core.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.core.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.core.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.core.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)."
}
}
},
"BaseScraper": {
"name": "BaseScraper",
"kind": "class",
"path": "omniread.core.scraper.BaseScraper",
"signature": "<bound method Class.signature of Class('BaseScraper', 30, 82)>",
"docstring": "Base interface for all scrapers.\n\nNotes:\n **Responsibilities:**\n\n - A scraper is responsible ONLY for fetching raw content (bytes)\n from a source. It must not interpret or parse it.\n - A scraper is a stateless acquisition component that retrieves raw\n 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\n strategy, retry and backoff behavior.\n\n **Constraints:**\n\n - Implementations must not parse content, modify content semantics,\n or couple scraping logic to a specific parser.",
"members": {
"fetch": {
"name": "fetch",
"kind": "function",
"path": "omniread.core.scraper.BaseScraper.fetch",
"signature": "<bound method Function.signature of Function('fetch', 51, 82)>",
"docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\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`\n and return it as raw bytes wrapped in a `Content` object."
}
}
}
}
}
}