using doc-forge #1
3
.gitignore
vendored
3
.gitignore
vendored
@@ -37,4 +37,5 @@ Thumbs.db
|
|||||||
*.swp
|
*.swp
|
||||||
*.swo
|
*.swo
|
||||||
*~
|
*~
|
||||||
*.tmp
|
*.tmp
|
||||||
|
site
|
||||||
|
|||||||
16
docforge.nav.yml
Normal file
16
docforge.nav.yml
Normal file
@@ -0,0 +1,16 @@
|
|||||||
|
home: omniread/index.md
|
||||||
|
groups:
|
||||||
|
Core API:
|
||||||
|
- omniread/core/index.md
|
||||||
|
- omniread/core/content.md
|
||||||
|
- omniread/core/parser.md
|
||||||
|
- omniread/core/scraper.md
|
||||||
|
HTML Handling:
|
||||||
|
- omniread/html/index.md
|
||||||
|
- omniread/html/parser.md
|
||||||
|
- omniread/html/scraper.md
|
||||||
|
PDF Handling:
|
||||||
|
- omniread/pdf/index.md
|
||||||
|
- omniread/pdf/client.md
|
||||||
|
- omniread/pdf/parser.md
|
||||||
|
- omniread/pdf/scraper.md
|
||||||
@@ -1 +1,3 @@
|
|||||||
|
# Content
|
||||||
|
|
||||||
::: omniread.core.content
|
::: omniread.core.content
|
||||||
@@ -1 +1,3 @@
|
|||||||
|
# Core
|
||||||
|
|
||||||
::: omniread.core
|
::: omniread.core
|
||||||
@@ -1 +1,3 @@
|
|||||||
|
# Parser
|
||||||
|
|
||||||
::: omniread.core.parser
|
::: omniread.core.parser
|
||||||
@@ -1 +1,3 @@
|
|||||||
|
# Scraper
|
||||||
|
|
||||||
::: omniread.core.scraper
|
::: omniread.core.scraper
|
||||||
@@ -1 +1,3 @@
|
|||||||
|
# Html
|
||||||
|
|
||||||
::: omniread.html
|
::: omniread.html
|
||||||
@@ -1 +1,3 @@
|
|||||||
|
# Parser
|
||||||
|
|
||||||
::: omniread.html.parser
|
::: omniread.html.parser
|
||||||
@@ -1 +1,3 @@
|
|||||||
|
# Scraper
|
||||||
|
|
||||||
::: omniread.html.scraper
|
::: omniread.html.scraper
|
||||||
@@ -1 +1,3 @@
|
|||||||
|
# Omniread
|
||||||
|
|
||||||
::: omniread
|
::: omniread
|
||||||
@@ -1 +1,3 @@
|
|||||||
|
# Client
|
||||||
|
|
||||||
::: omniread.pdf.client
|
::: omniread.pdf.client
|
||||||
@@ -1 +1,3 @@
|
|||||||
|
# Pdf
|
||||||
|
|
||||||
::: omniread.pdf
|
::: omniread.pdf
|
||||||
@@ -1 +1,3 @@
|
|||||||
|
# Parser
|
||||||
|
|
||||||
::: omniread.pdf.parser
|
::: omniread.pdf.parser
|
||||||
@@ -1 +1,3 @@
|
|||||||
|
# Scraper
|
||||||
|
|
||||||
::: omniread.pdf.scraper
|
::: omniread.pdf.scraper
|
||||||
@@ -1,46 +0,0 @@
|
|||||||
"""
|
|
||||||
Programmatic MkDocs build script for OmniRead.
|
|
||||||
|
|
||||||
This script builds (or serves) the documentation by invoking MkDocs
|
|
||||||
*as a Python library*, not via shell commands.
|
|
||||||
|
|
||||||
Requirements:
|
|
||||||
- mkdocs
|
|
||||||
- mkdocs-material
|
|
||||||
- mkdocstrings[python]
|
|
||||||
|
|
||||||
Usage:
|
|
||||||
python generate_docs.py
|
|
||||||
python generate_docs.py --serve
|
|
||||||
"""
|
|
||||||
|
|
||||||
import sys
|
|
||||||
from pathlib import Path
|
|
||||||
|
|
||||||
from mkdocs.commands import build as mkdocs_build
|
|
||||||
from mkdocs.commands import serve as mkdocs_serve
|
|
||||||
from mkdocs.config import load_config
|
|
||||||
|
|
||||||
|
|
||||||
PROJECT_ROOT = Path(__file__).resolve().parent
|
|
||||||
MKDOCS_YML = PROJECT_ROOT / "mkdocs.yml"
|
|
||||||
|
|
||||||
|
|
||||||
def main() -> None:
|
|
||||||
if not MKDOCS_YML.exists():
|
|
||||||
raise FileNotFoundError("mkdocs.yml not found at project root")
|
|
||||||
|
|
||||||
# Load MkDocs configuration programmatically
|
|
||||||
config = load_config(str(MKDOCS_YML))
|
|
||||||
|
|
||||||
# Decide mode
|
|
||||||
if "--serve" in sys.argv:
|
|
||||||
# Live-reload development server
|
|
||||||
mkdocs_serve.serve(config)
|
|
||||||
else:
|
|
||||||
# Static site build
|
|
||||||
mkdocs_build.build(config)
|
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
|
||||||
main()
|
|
||||||
6
mcp_docs/index.json
Normal file
6
mcp_docs/index.json
Normal file
@@ -0,0 +1,6 @@
|
|||||||
|
{
|
||||||
|
"project": "omniread",
|
||||||
|
"type": "docforge-model",
|
||||||
|
"modules_count": 12,
|
||||||
|
"source": "docforge"
|
||||||
|
}
|
||||||
118
mcp_docs/modules/omniread.core.content.json
Normal file
118
mcp_docs/modules/omniread.core.content.json
Normal file
@@ -0,0 +1,118 @@
|
|||||||
|
{
|
||||||
|
"module": "omniread.core.content",
|
||||||
|
"content": {
|
||||||
|
"path": "omniread.core.content",
|
||||||
|
"docstring": "Canonical content models for OmniRead.\n\nThis module defines the **format-agnostic content representation** used across\nall parsers and scrapers in OmniRead.\n\nThe models defined here represent *what* was extracted, not *how* it was\nretrieved or parsed. Format-specific behavior and metadata must not alter\nthe semantic meaning of these models.",
|
||||||
|
"objects": {
|
||||||
|
"Enum": {
|
||||||
|
"name": "Enum",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.content.Enum",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Enum', 'enum.Enum')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"dataclass": {
|
||||||
|
"name": "dataclass",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.content.dataclass",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('dataclass', 'dataclasses.dataclass')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Any": {
|
||||||
|
"name": "Any",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.content.Any",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Mapping": {
|
||||||
|
"name": "Mapping",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.content.Mapping",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Mapping', 'typing.Mapping')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Optional": {
|
||||||
|
"name": "Optional",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.content.Optional",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Optional', 'typing.Optional')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"ContentType": {
|
||||||
|
"name": "ContentType",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.core.content.ContentType",
|
||||||
|
"signature": "<bound method Class.signature of Class('ContentType', 17, 36)>",
|
||||||
|
"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.core.content.ContentType.HTML",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": "HTML document content."
|
||||||
|
},
|
||||||
|
"PDF": {
|
||||||
|
"name": "PDF",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.core.content.ContentType.PDF",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": "PDF document content."
|
||||||
|
},
|
||||||
|
"JSON": {
|
||||||
|
"name": "JSON",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.core.content.ContentType.JSON",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": "JSON document content."
|
||||||
|
},
|
||||||
|
"XML": {
|
||||||
|
"name": "XML",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.core.content.ContentType.XML",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": "XML document content."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"Content": {
|
||||||
|
"name": "Content",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.core.content.Content",
|
||||||
|
"signature": "<bound method Class.signature of Class('Content', 39, 63)>",
|
||||||
|
"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.core.content.Content.raw",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"source": {
|
||||||
|
"name": "source",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.core.content.Content.source",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"content_type": {
|
||||||
|
"name": "content_type",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.core.content.Content.content_type",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"metadata": {
|
||||||
|
"name": "metadata",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.core.content.Content.metadata",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": null
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
513
mcp_docs/modules/omniread.core.json
Normal file
513
mcp_docs/modules/omniread.core.json
Normal file
@@ -0,0 +1,513 @@
|
|||||||
|
{
|
||||||
|
"module": "omniread.core",
|
||||||
|
"content": {
|
||||||
|
"path": "omniread.core",
|
||||||
|
"docstring": "Core domain contracts for OmniRead.\n\nThis package defines the **format-agnostic domain layer** of OmniRead.\nIt exposes canonical content models and abstract interfaces that are\nimplemented by format-specific modules (HTML, PDF, etc.).\n\nPublic exports from this package are considered **stable contracts** and\nare safe for downstream consumers to depend on.\n\nSubmodules:\n- content: Canonical content models and enums\n- parser: Abstract parsing contracts\n- scraper: Abstract scraping contracts\n\nFormat-specific behavior must not be introduced at this layer.",
|
||||||
|
"objects": {
|
||||||
|
"Content": {
|
||||||
|
"name": "Content",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.core.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.core.Content.raw",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"source": {
|
||||||
|
"name": "source",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.core.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.core.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.core.Content.metadata",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||||
|
"docstring": null
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"ContentType": {
|
||||||
|
"name": "ContentType",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.core.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.core.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.core.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.core.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.core.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.core.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.core.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.core.BaseParser.content",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('content', 'omniread.core.parser.BaseParser.content')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"parse": {
|
||||||
|
"name": "parse",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.core.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.core.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."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"BaseScraper": {
|
||||||
|
"name": "BaseScraper",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.core.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.core.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."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"content": {
|
||||||
|
"name": "content",
|
||||||
|
"kind": "module",
|
||||||
|
"path": "omniread.core.content",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": "Canonical content models for OmniRead.\n\nThis module defines the **format-agnostic content representation** used across\nall parsers and scrapers in OmniRead.\n\nThe models defined here represent *what* was extracted, not *how* it was\nretrieved or parsed. Format-specific behavior and metadata must not alter\nthe semantic meaning of these models.",
|
||||||
|
"members": {
|
||||||
|
"Enum": {
|
||||||
|
"name": "Enum",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.content.Enum",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Enum', 'enum.Enum')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"dataclass": {
|
||||||
|
"name": "dataclass",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.content.dataclass",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('dataclass', 'dataclasses.dataclass')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Any": {
|
||||||
|
"name": "Any",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.content.Any",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Mapping": {
|
||||||
|
"name": "Mapping",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.content.Mapping",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Mapping', 'typing.Mapping')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Optional": {
|
||||||
|
"name": "Optional",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.content.Optional",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Optional', 'typing.Optional')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"ContentType": {
|
||||||
|
"name": "ContentType",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.core.content.ContentType",
|
||||||
|
"signature": "<bound method Class.signature of Class('ContentType', 17, 36)>",
|
||||||
|
"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.core.content.ContentType.HTML",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": "HTML document content."
|
||||||
|
},
|
||||||
|
"PDF": {
|
||||||
|
"name": "PDF",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.core.content.ContentType.PDF",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": "PDF document content."
|
||||||
|
},
|
||||||
|
"JSON": {
|
||||||
|
"name": "JSON",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.core.content.ContentType.JSON",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": "JSON document content."
|
||||||
|
},
|
||||||
|
"XML": {
|
||||||
|
"name": "XML",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.core.content.ContentType.XML",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": "XML document content."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"Content": {
|
||||||
|
"name": "Content",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.core.content.Content",
|
||||||
|
"signature": "<bound method Class.signature of Class('Content', 39, 63)>",
|
||||||
|
"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.core.content.Content.raw",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"source": {
|
||||||
|
"name": "source",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.core.content.Content.source",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"content_type": {
|
||||||
|
"name": "content_type",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.core.content.Content.content_type",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"metadata": {
|
||||||
|
"name": "metadata",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.core.content.Content.metadata",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": null
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"parser": {
|
||||||
|
"name": "parser",
|
||||||
|
"kind": "module",
|
||||||
|
"path": "omniread.core.parser",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": "Abstract parsing contracts for OmniRead.\n\nThis module defines the **format-agnostic parser interface** used to transform\nraw content into structured, typed representations.\n\nParsers are responsible for:\n- Interpreting a single `Content` instance\n- Validating compatibility with the content type\n- Producing a structured output suitable for downstream consumers\n\nParsers are not responsible for:\n- Fetching or acquiring content\n- Performing retries or error recovery\n- Managing multiple content sources",
|
||||||
|
"members": {
|
||||||
|
"ABC": {
|
||||||
|
"name": "ABC",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.parser.ABC",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"abstractmethod": {
|
||||||
|
"name": "abstractmethod",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.parser.abstractmethod",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Generic": {
|
||||||
|
"name": "Generic",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.parser.Generic",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"TypeVar": {
|
||||||
|
"name": "TypeVar",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.parser.TypeVar",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Set": {
|
||||||
|
"name": "Set",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.parser.Set",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Set', 'typing.Set')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Content": {
|
||||||
|
"name": "Content",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.core.parser.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.core.parser.Content.raw",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"source": {
|
||||||
|
"name": "source",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.core.parser.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.core.parser.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.core.parser.Content.metadata",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||||
|
"docstring": null
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"ContentType": {
|
||||||
|
"name": "ContentType",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.core.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.core.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.core.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.core.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.core.parser.ContentType.XML",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||||
|
"docstring": "XML document content."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"T": {
|
||||||
|
"name": "T",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.core.parser.T",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"BaseParser": {
|
||||||
|
"name": "BaseParser",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.core.parser.BaseParser",
|
||||||
|
"signature": "<bound method Class.signature of Class('BaseParser', 26, 98)>",
|
||||||
|
"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.core.parser.BaseParser.supported_types",
|
||||||
|
"signature": null,
|
||||||
|
"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.core.parser.BaseParser.content",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"parse": {
|
||||||
|
"name": "parse",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.core.parser.BaseParser.parse",
|
||||||
|
"signature": "<bound method Function.signature of Function('parse', 68, 82)>",
|
||||||
|
"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.core.parser.BaseParser.supports",
|
||||||
|
"signature": "<bound method Function.signature of Function('supports', 84, 98)>",
|
||||||
|
"docstring": "Check whether this parser supports the content's type.\n\nReturns:\n True if the content type is supported; False otherwise."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"scraper": {
|
||||||
|
"name": "scraper",
|
||||||
|
"kind": "module",
|
||||||
|
"path": "omniread.core.scraper",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": "Abstract 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- Locating and retrieving raw content bytes\n- Attaching minimal contextual metadata\n- Returning normalized `Content` objects\n\nScrapers are explicitly NOT responsible for:\n- Parsing or interpreting content\n- Inferring structure or semantics\n- Performing content-type specific processing\n\nAll interpretation must be delegated to parsers.",
|
||||||
|
"members": {
|
||||||
|
"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\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.core.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.core.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.core.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.core.scraper.Content.metadata",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||||
|
"docstring": null
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"BaseScraper": {
|
||||||
|
"name": "BaseScraper",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.core.scraper.BaseScraper",
|
||||||
|
"signature": "<bound method Class.signature of Class('BaseScraper', 26, 75)>",
|
||||||
|
"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.core.scraper.BaseScraper.fetch",
|
||||||
|
"signature": "<bound method Function.signature of Function('fetch', 49, 75)>",
|
||||||
|
"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."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
162
mcp_docs/modules/omniread.core.parser.json
Normal file
162
mcp_docs/modules/omniread.core.parser.json
Normal file
@@ -0,0 +1,162 @@
|
|||||||
|
{
|
||||||
|
"module": "omniread.core.parser",
|
||||||
|
"content": {
|
||||||
|
"path": "omniread.core.parser",
|
||||||
|
"docstring": "Abstract parsing contracts for OmniRead.\n\nThis module defines the **format-agnostic parser interface** used to transform\nraw content into structured, typed representations.\n\nParsers are responsible for:\n- Interpreting a single `Content` instance\n- Validating compatibility with the content type\n- Producing a structured output suitable for downstream consumers\n\nParsers are not responsible for:\n- Fetching or acquiring content\n- Performing retries or error recovery\n- Managing multiple content sources",
|
||||||
|
"objects": {
|
||||||
|
"ABC": {
|
||||||
|
"name": "ABC",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.parser.ABC",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"abstractmethod": {
|
||||||
|
"name": "abstractmethod",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.parser.abstractmethod",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Generic": {
|
||||||
|
"name": "Generic",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.parser.Generic",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"TypeVar": {
|
||||||
|
"name": "TypeVar",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.parser.TypeVar",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Set": {
|
||||||
|
"name": "Set",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.core.parser.Set",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Set', 'typing.Set')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Content": {
|
||||||
|
"name": "Content",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.core.parser.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.core.parser.Content.raw",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"source": {
|
||||||
|
"name": "source",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.core.parser.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.core.parser.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.core.parser.Content.metadata",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||||
|
"docstring": null
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"ContentType": {
|
||||||
|
"name": "ContentType",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.core.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.core.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.core.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.core.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.core.parser.ContentType.XML",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||||
|
"docstring": "XML document content."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"T": {
|
||||||
|
"name": "T",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.core.parser.T",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"BaseParser": {
|
||||||
|
"name": "BaseParser",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.core.parser.BaseParser",
|
||||||
|
"signature": "<bound method Class.signature of Class('BaseParser', 26, 98)>",
|
||||||
|
"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.core.parser.BaseParser.supported_types",
|
||||||
|
"signature": null,
|
||||||
|
"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.core.parser.BaseParser.content",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"parse": {
|
||||||
|
"name": "parse",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.core.parser.BaseParser.parse",
|
||||||
|
"signature": "<bound method Function.signature of Function('parse', 68, 82)>",
|
||||||
|
"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.core.parser.BaseParser.supports",
|
||||||
|
"signature": "<bound method Function.signature of Function('supports', 84, 98)>",
|
||||||
|
"docstring": "Check whether this parser supports the content's type.\n\nReturns:\n True if the content type is supported; False otherwise."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
97
mcp_docs/modules/omniread.core.scraper.json
Normal file
97
mcp_docs/modules/omniread.core.scraper.json
Normal file
@@ -0,0 +1,97 @@
|
|||||||
|
{
|
||||||
|
"module": "omniread.core.scraper",
|
||||||
|
"content": {
|
||||||
|
"path": "omniread.core.scraper",
|
||||||
|
"docstring": "Abstract 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- Locating and retrieving raw content bytes\n- Attaching minimal contextual metadata\n- Returning normalized `Content` objects\n\nScrapers are explicitly NOT responsible for:\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\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.core.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.core.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.core.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.core.scraper.Content.metadata",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||||
|
"docstring": null
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"BaseScraper": {
|
||||||
|
"name": "BaseScraper",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.core.scraper.BaseScraper",
|
||||||
|
"signature": "<bound method Class.signature of Class('BaseScraper', 26, 75)>",
|
||||||
|
"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.core.scraper.BaseScraper.fetch",
|
||||||
|
"signature": "<bound method Function.signature of Function('fetch', 49, 75)>",
|
||||||
|
"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."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
488
mcp_docs/modules/omniread.html.json
Normal file
488
mcp_docs/modules/omniread.html.json
Normal file
@@ -0,0 +1,488 @@
|
|||||||
|
{
|
||||||
|
"module": "omniread.html",
|
||||||
|
"content": {
|
||||||
|
"path": "omniread.html",
|
||||||
|
"docstring": "HTML format implementation for OmniRead.\n\nThis package provides **HTML-specific implementations** of the core OmniRead\ncontracts defined in `omniread.core`.\n\nIt includes:\n- HTML parsers that interpret HTML content\n- HTML scrapers that retrieve HTML documents\n\nThis package:\n- Implements, but does not redefine, core contracts\n- May contain HTML-specific behavior and edge-case handling\n- Produces canonical content models defined in `omniread.core.content`\n\nConsumers should depend on `omniread.core` interfaces wherever possible and\nuse this package only when HTML-specific behavior is required.",
|
||||||
|
"objects": {
|
||||||
|
"HTMLScraper": {
|
||||||
|
"name": "HTMLScraper",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.html.HTMLScraper",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('HTMLScraper', 'omniread.html.scraper.HTMLScraper')>",
|
||||||
|
"docstring": "Base HTML scraper using httpx.\n\nThis scraper retrieves HTML documents over HTTP(S) and returns them\nas raw content wrapped in a `Content` object.\n\nFetches raw bytes and metadata only.\nThe scraper:\n- Uses `httpx.Client` for HTTP requests\n- Enforces an HTML content type\n- Preserves HTTP response metadata\n\nThe scraper does not:\n- Parse HTML\n- Perform retries or backoff\n- Handle non-HTML responses",
|
||||||
|
"members": {
|
||||||
|
"content_type": {
|
||||||
|
"name": "content_type",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.html.HTMLScraper.content_type",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.html.scraper.HTMLScraper.content_type')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"validate_content_type": {
|
||||||
|
"name": "validate_content_type",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.HTMLScraper.validate_content_type",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('validate_content_type', 'omniread.html.scraper.HTMLScraper.validate_content_type')>",
|
||||||
|
"docstring": "Validate that the HTTP response contains HTML content.\n\nArgs:\n response: HTTP response returned by `httpx`.\n\nRaises:\n ValueError: If the `Content-Type` header is missing or does not\n indicate HTML content."
|
||||||
|
},
|
||||||
|
"fetch": {
|
||||||
|
"name": "fetch",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.HTMLScraper.fetch",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.html.scraper.HTMLScraper.fetch')>",
|
||||||
|
"docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source: URL of the HTML document.\n metadata: Optional metadata to be merged into the returned content.\n\nReturns:\n A `Content` instance containing:\n - Raw HTML bytes\n - Source URL\n - HTML content type\n - HTTP response metadata\n\nRaises:\n httpx.HTTPError: If the HTTP request fails.\n ValueError: If the response is not valid HTML."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"HTMLParser": {
|
||||||
|
"name": "HTMLParser",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.html.HTMLParser",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('HTMLParser', 'omniread.html.parser.HTMLParser')>",
|
||||||
|
"docstring": "Base HTML parser.\n\nThis class extends the core `BaseParser` with HTML-specific behavior,\nincluding DOM parsing via BeautifulSoup and reusable extraction helpers.\n\nProvides reusable helpers for HTML extraction.\nConcrete parsers must explicitly define the return type.\n\nCharacteristics:\n- Accepts only HTML content\n- Owns a parsed BeautifulSoup DOM tree\n- Provides pure helper utilities for common HTML structures\n\nConcrete subclasses must:\n- Define the output type `T`\n- Implement the `parse()` method",
|
||||||
|
"members": {
|
||||||
|
"supported_types": {
|
||||||
|
"name": "supported_types",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.html.HTMLParser.supported_types",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.html.parser.HTMLParser.supported_types')>",
|
||||||
|
"docstring": "Set of content types supported by this parser (HTML only)."
|
||||||
|
},
|
||||||
|
"parse": {
|
||||||
|
"name": "parse",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.HTMLParser.parse",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.html.parser.HTMLParser.parse')>",
|
||||||
|
"docstring": "Fully parse the HTML content into structured output.\n\nImplementations must fully interpret the HTML DOM and return\na deterministic, structured output.\n\nReturns:\n Parsed representation of type `T`."
|
||||||
|
},
|
||||||
|
"parse_div": {
|
||||||
|
"name": "parse_div",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.HTMLParser.parse_div",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('parse_div', 'omniread.html.parser.HTMLParser.parse_div')>",
|
||||||
|
"docstring": "Extract normalized text from a `<div>` element.\n\nArgs:\n div: BeautifulSoup tag representing a `<div>`.\n separator: String used to separate text nodes.\n\nReturns:\n Flattened, whitespace-normalized text content."
|
||||||
|
},
|
||||||
|
"parse_link": {
|
||||||
|
"name": "parse_link",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.HTMLParser.parse_link",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('parse_link', 'omniread.html.parser.HTMLParser.parse_link')>",
|
||||||
|
"docstring": "Extract the hyperlink reference from an `<a>` element.\n\nArgs:\n a: BeautifulSoup tag representing an anchor.\n\nReturns:\n The value of the `href` attribute, or None if absent."
|
||||||
|
},
|
||||||
|
"parse_table": {
|
||||||
|
"name": "parse_table",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.HTMLParser.parse_table",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('parse_table', 'omniread.html.parser.HTMLParser.parse_table')>",
|
||||||
|
"docstring": "Parse an HTML table into a 2D list of strings.\n\nArgs:\n table: BeautifulSoup tag representing a `<table>`.\n\nReturns:\n A list of rows, where each row is a list of cell text values."
|
||||||
|
},
|
||||||
|
"parse_meta": {
|
||||||
|
"name": "parse_meta",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.HTMLParser.parse_meta",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('parse_meta', 'omniread.html.parser.HTMLParser.parse_meta')>",
|
||||||
|
"docstring": "Extract high-level metadata from the HTML document.\n\nThis includes:\n- Document title\n- `<meta>` tag name/property → content mappings\n\nReturns:\n Dictionary containing extracted metadata."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"parser": {
|
||||||
|
"name": "parser",
|
||||||
|
"kind": "module",
|
||||||
|
"path": "omniread.html.parser",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": "HTML parser base implementations for OmniRead.\n\nThis module provides reusable HTML parsing utilities built on top of\nthe abstract parser contracts defined in `omniread.core.parser`.\n\nIt supplies:\n- Content-type enforcement for HTML inputs\n- BeautifulSoup initialization and lifecycle management\n- Common helper methods for extracting structured data from HTML elements\n\nConcrete parsers must subclass `HTMLParser` and implement the `parse()` method\nto return a structured representation appropriate for their use case.",
|
||||||
|
"members": {
|
||||||
|
"Any": {
|
||||||
|
"name": "Any",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.parser.Any",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Generic": {
|
||||||
|
"name": "Generic",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.parser.Generic",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"TypeVar": {
|
||||||
|
"name": "TypeVar",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.parser.TypeVar",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Optional": {
|
||||||
|
"name": "Optional",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.parser.Optional",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Optional', 'typing.Optional')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"abstractmethod": {
|
||||||
|
"name": "abstractmethod",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.parser.abstractmethod",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"BeautifulSoup": {
|
||||||
|
"name": "BeautifulSoup",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.parser.BeautifulSoup",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('BeautifulSoup', 'bs4.BeautifulSoup')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Tag": {
|
||||||
|
"name": "Tag",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.parser.Tag",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Tag', 'bs4.Tag')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"ContentType": {
|
||||||
|
"name": "ContentType",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.html.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.html.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.html.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.html.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.html.parser.ContentType.XML",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||||
|
"docstring": "XML document content."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"Content": {
|
||||||
|
"name": "Content",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.html.parser.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.html.parser.Content.raw",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"source": {
|
||||||
|
"name": "source",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.html.parser.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.html.parser.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.html.parser.Content.metadata",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||||
|
"docstring": null
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"BaseParser": {
|
||||||
|
"name": "BaseParser",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.html.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.html.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.html.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.html.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.html.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.html.parser.T",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"HTMLParser": {
|
||||||
|
"name": "HTMLParser",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.html.parser.HTMLParser",
|
||||||
|
"signature": "<bound method Class.signature of Class('HTMLParser', 27, 177)>",
|
||||||
|
"docstring": "Base HTML parser.\n\nThis class extends the core `BaseParser` with HTML-specific behavior,\nincluding DOM parsing via BeautifulSoup and reusable extraction helpers.\n\nProvides reusable helpers for HTML extraction.\nConcrete parsers must explicitly define the return type.\n\nCharacteristics:\n- Accepts only HTML content\n- Owns a parsed BeautifulSoup DOM tree\n- Provides pure helper utilities for common HTML structures\n\nConcrete subclasses must:\n- Define the output type `T`\n- Implement the `parse()` method",
|
||||||
|
"members": {
|
||||||
|
"supported_types": {
|
||||||
|
"name": "supported_types",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.html.parser.HTMLParser.supported_types",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": "Set of content types supported by this parser (HTML only)."
|
||||||
|
},
|
||||||
|
"parse": {
|
||||||
|
"name": "parse",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.parser.HTMLParser.parse",
|
||||||
|
"signature": "<bound method Function.signature of Function('parse', 70, 81)>",
|
||||||
|
"docstring": "Fully parse the HTML content into structured output.\n\nImplementations must fully interpret the HTML DOM and return\na deterministic, structured output.\n\nReturns:\n Parsed representation of type `T`."
|
||||||
|
},
|
||||||
|
"parse_div": {
|
||||||
|
"name": "parse_div",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.parser.HTMLParser.parse_div",
|
||||||
|
"signature": "<bound method Function.signature of Function('parse_div', 87, 99)>",
|
||||||
|
"docstring": "Extract normalized text from a `<div>` element.\n\nArgs:\n div: BeautifulSoup tag representing a `<div>`.\n separator: String used to separate text nodes.\n\nReturns:\n Flattened, whitespace-normalized text content."
|
||||||
|
},
|
||||||
|
"parse_link": {
|
||||||
|
"name": "parse_link",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.parser.HTMLParser.parse_link",
|
||||||
|
"signature": "<bound method Function.signature of Function('parse_link', 101, 112)>",
|
||||||
|
"docstring": "Extract the hyperlink reference from an `<a>` element.\n\nArgs:\n a: BeautifulSoup tag representing an anchor.\n\nReturns:\n The value of the `href` attribute, or None if absent."
|
||||||
|
},
|
||||||
|
"parse_table": {
|
||||||
|
"name": "parse_table",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.parser.HTMLParser.parse_table",
|
||||||
|
"signature": "<bound method Function.signature of Function('parse_table', 114, 133)>",
|
||||||
|
"docstring": "Parse an HTML table into a 2D list of strings.\n\nArgs:\n table: BeautifulSoup tag representing a `<table>`.\n\nReturns:\n A list of rows, where each row is a list of cell text values."
|
||||||
|
},
|
||||||
|
"parse_meta": {
|
||||||
|
"name": "parse_meta",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.parser.HTMLParser.parse_meta",
|
||||||
|
"signature": "<bound method Function.signature of Function('parse_meta', 153, 177)>",
|
||||||
|
"docstring": "Extract high-level metadata from the HTML document.\n\nThis includes:\n- Document title\n- `<meta>` tag name/property → content mappings\n\nReturns:\n Dictionary containing extracted metadata."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"list": {
|
||||||
|
"name": "list",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.parser.list",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('list', 'typing.list')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"dict": {
|
||||||
|
"name": "dict",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.parser.dict",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('dict', 'typing.dict')>",
|
||||||
|
"docstring": null
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"scraper": {
|
||||||
|
"name": "scraper",
|
||||||
|
"kind": "module",
|
||||||
|
"path": "omniread.html.scraper",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": "HTML scraping implementation for OmniRead.\n\nThis module provides an HTTP-based scraper for retrieving HTML documents.\nIt implements the core `BaseScraper` contract using `httpx` as the transport\nlayer.\n\nThis scraper is responsible for:\n- Fetching raw HTML bytes over HTTP(S)\n- Validating response content type\n- Attaching HTTP metadata to the returned content\n\nThis scraper is not responsible for:\n- Parsing or interpreting HTML\n- Retrying failed requests\n- Managing crawl policies or rate limiting",
|
||||||
|
"members": {
|
||||||
|
"httpx": {
|
||||||
|
"name": "httpx",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.scraper.httpx",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('httpx', 'httpx')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Any": {
|
||||||
|
"name": "Any",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.scraper.Any",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Mapping": {
|
||||||
|
"name": "Mapping",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.scraper.Mapping",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Mapping', 'typing.Mapping')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Optional": {
|
||||||
|
"name": "Optional",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.scraper.Optional",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Optional', 'typing.Optional')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Content": {
|
||||||
|
"name": "Content",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.html.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.html.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.html.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.html.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.html.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.html.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.html.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.html.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.html.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.html.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.html.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.html.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."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"HTMLScraper": {
|
||||||
|
"name": "HTMLScraper",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.html.scraper.HTMLScraper",
|
||||||
|
"signature": "<bound method Class.signature of Class('HTMLScraper', 26, 134)>",
|
||||||
|
"docstring": "Base HTML scraper using httpx.\n\nThis scraper retrieves HTML documents over HTTP(S) and returns them\nas raw content wrapped in a `Content` object.\n\nFetches raw bytes and metadata only.\nThe scraper:\n- Uses `httpx.Client` for HTTP requests\n- Enforces an HTML content type\n- Preserves HTTP response metadata\n\nThe scraper does not:\n- Parse HTML\n- Perform retries or backoff\n- Handle non-HTML responses",
|
||||||
|
"members": {
|
||||||
|
"content_type": {
|
||||||
|
"name": "content_type",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.html.scraper.HTMLScraper.content_type",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"validate_content_type": {
|
||||||
|
"name": "validate_content_type",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.scraper.HTMLScraper.validate_content_type",
|
||||||
|
"signature": "<bound method Function.signature of Function('validate_content_type', 71, 94)>",
|
||||||
|
"docstring": "Validate that the HTTP response contains HTML content.\n\nArgs:\n response: HTTP response returned by `httpx`.\n\nRaises:\n ValueError: If the `Content-Type` header is missing or does not\n indicate HTML content."
|
||||||
|
},
|
||||||
|
"fetch": {
|
||||||
|
"name": "fetch",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.scraper.HTMLScraper.fetch",
|
||||||
|
"signature": "<bound method Function.signature of Function('fetch', 96, 134)>",
|
||||||
|
"docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source: URL of the HTML document.\n metadata: Optional metadata to be merged into the returned content.\n\nReturns:\n A `Content` instance containing:\n - Raw HTML bytes\n - Source URL\n - HTML content type\n - HTTP response metadata\n\nRaises:\n httpx.HTTPError: If the HTTP request fails.\n ValueError: If the response is not valid HTML."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
241
mcp_docs/modules/omniread.html.parser.json
Normal file
241
mcp_docs/modules/omniread.html.parser.json
Normal file
@@ -0,0 +1,241 @@
|
|||||||
|
{
|
||||||
|
"module": "omniread.html.parser",
|
||||||
|
"content": {
|
||||||
|
"path": "omniread.html.parser",
|
||||||
|
"docstring": "HTML parser base implementations for OmniRead.\n\nThis module provides reusable HTML parsing utilities built on top of\nthe abstract parser contracts defined in `omniread.core.parser`.\n\nIt supplies:\n- Content-type enforcement for HTML inputs\n- BeautifulSoup initialization and lifecycle management\n- Common helper methods for extracting structured data from HTML elements\n\nConcrete parsers must subclass `HTMLParser` and implement the `parse()` method\nto return a structured representation appropriate for their use case.",
|
||||||
|
"objects": {
|
||||||
|
"Any": {
|
||||||
|
"name": "Any",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.parser.Any",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Generic": {
|
||||||
|
"name": "Generic",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.parser.Generic",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"TypeVar": {
|
||||||
|
"name": "TypeVar",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.parser.TypeVar",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Optional": {
|
||||||
|
"name": "Optional",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.parser.Optional",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Optional', 'typing.Optional')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"abstractmethod": {
|
||||||
|
"name": "abstractmethod",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.parser.abstractmethod",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"BeautifulSoup": {
|
||||||
|
"name": "BeautifulSoup",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.parser.BeautifulSoup",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('BeautifulSoup', 'bs4.BeautifulSoup')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Tag": {
|
||||||
|
"name": "Tag",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.parser.Tag",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Tag', 'bs4.Tag')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"ContentType": {
|
||||||
|
"name": "ContentType",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.html.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.html.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.html.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.html.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.html.parser.ContentType.XML",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||||
|
"docstring": "XML document content."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"Content": {
|
||||||
|
"name": "Content",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.html.parser.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.html.parser.Content.raw",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"source": {
|
||||||
|
"name": "source",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.html.parser.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.html.parser.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.html.parser.Content.metadata",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||||
|
"docstring": null
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"BaseParser": {
|
||||||
|
"name": "BaseParser",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.html.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.html.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.html.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.html.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.html.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.html.parser.T",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"HTMLParser": {
|
||||||
|
"name": "HTMLParser",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.html.parser.HTMLParser",
|
||||||
|
"signature": "<bound method Class.signature of Class('HTMLParser', 27, 177)>",
|
||||||
|
"docstring": "Base HTML parser.\n\nThis class extends the core `BaseParser` with HTML-specific behavior,\nincluding DOM parsing via BeautifulSoup and reusable extraction helpers.\n\nProvides reusable helpers for HTML extraction.\nConcrete parsers must explicitly define the return type.\n\nCharacteristics:\n- Accepts only HTML content\n- Owns a parsed BeautifulSoup DOM tree\n- Provides pure helper utilities for common HTML structures\n\nConcrete subclasses must:\n- Define the output type `T`\n- Implement the `parse()` method",
|
||||||
|
"members": {
|
||||||
|
"supported_types": {
|
||||||
|
"name": "supported_types",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.html.parser.HTMLParser.supported_types",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": "Set of content types supported by this parser (HTML only)."
|
||||||
|
},
|
||||||
|
"parse": {
|
||||||
|
"name": "parse",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.parser.HTMLParser.parse",
|
||||||
|
"signature": "<bound method Function.signature of Function('parse', 70, 81)>",
|
||||||
|
"docstring": "Fully parse the HTML content into structured output.\n\nImplementations must fully interpret the HTML DOM and return\na deterministic, structured output.\n\nReturns:\n Parsed representation of type `T`."
|
||||||
|
},
|
||||||
|
"parse_div": {
|
||||||
|
"name": "parse_div",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.parser.HTMLParser.parse_div",
|
||||||
|
"signature": "<bound method Function.signature of Function('parse_div', 87, 99)>",
|
||||||
|
"docstring": "Extract normalized text from a `<div>` element.\n\nArgs:\n div: BeautifulSoup tag representing a `<div>`.\n separator: String used to separate text nodes.\n\nReturns:\n Flattened, whitespace-normalized text content."
|
||||||
|
},
|
||||||
|
"parse_link": {
|
||||||
|
"name": "parse_link",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.parser.HTMLParser.parse_link",
|
||||||
|
"signature": "<bound method Function.signature of Function('parse_link', 101, 112)>",
|
||||||
|
"docstring": "Extract the hyperlink reference from an `<a>` element.\n\nArgs:\n a: BeautifulSoup tag representing an anchor.\n\nReturns:\n The value of the `href` attribute, or None if absent."
|
||||||
|
},
|
||||||
|
"parse_table": {
|
||||||
|
"name": "parse_table",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.parser.HTMLParser.parse_table",
|
||||||
|
"signature": "<bound method Function.signature of Function('parse_table', 114, 133)>",
|
||||||
|
"docstring": "Parse an HTML table into a 2D list of strings.\n\nArgs:\n table: BeautifulSoup tag representing a `<table>`.\n\nReturns:\n A list of rows, where each row is a list of cell text values."
|
||||||
|
},
|
||||||
|
"parse_meta": {
|
||||||
|
"name": "parse_meta",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.parser.HTMLParser.parse_meta",
|
||||||
|
"signature": "<bound method Function.signature of Function('parse_meta', 153, 177)>",
|
||||||
|
"docstring": "Extract high-level metadata from the HTML document.\n\nThis includes:\n- Document title\n- `<meta>` tag name/property → content mappings\n\nReturns:\n Dictionary containing extracted metadata."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"list": {
|
||||||
|
"name": "list",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.parser.list",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('list', 'typing.list')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"dict": {
|
||||||
|
"name": "dict",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.parser.dict",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('dict', 'typing.dict')>",
|
||||||
|
"docstring": null
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
157
mcp_docs/modules/omniread.html.scraper.json
Normal file
157
mcp_docs/modules/omniread.html.scraper.json
Normal file
@@ -0,0 +1,157 @@
|
|||||||
|
{
|
||||||
|
"module": "omniread.html.scraper",
|
||||||
|
"content": {
|
||||||
|
"path": "omniread.html.scraper",
|
||||||
|
"docstring": "HTML scraping implementation for OmniRead.\n\nThis module provides an HTTP-based scraper for retrieving HTML documents.\nIt implements the core `BaseScraper` contract using `httpx` as the transport\nlayer.\n\nThis scraper is responsible for:\n- Fetching raw HTML bytes over HTTP(S)\n- Validating response content type\n- Attaching HTTP metadata to the returned content\n\nThis scraper is not responsible for:\n- Parsing or interpreting HTML\n- Retrying failed requests\n- Managing crawl policies or rate limiting",
|
||||||
|
"objects": {
|
||||||
|
"httpx": {
|
||||||
|
"name": "httpx",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.scraper.httpx",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('httpx', 'httpx')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Any": {
|
||||||
|
"name": "Any",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.scraper.Any",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Mapping": {
|
||||||
|
"name": "Mapping",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.scraper.Mapping",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Mapping', 'typing.Mapping')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Optional": {
|
||||||
|
"name": "Optional",
|
||||||
|
"kind": "alias",
|
||||||
|
"path": "omniread.html.scraper.Optional",
|
||||||
|
"signature": "<bound method Alias.signature of Alias('Optional', 'typing.Optional')>",
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"Content": {
|
||||||
|
"name": "Content",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.html.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.html.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.html.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.html.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.html.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.html.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.html.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.html.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.html.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.html.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.html.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.html.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."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"HTMLScraper": {
|
||||||
|
"name": "HTMLScraper",
|
||||||
|
"kind": "class",
|
||||||
|
"path": "omniread.html.scraper.HTMLScraper",
|
||||||
|
"signature": "<bound method Class.signature of Class('HTMLScraper', 26, 134)>",
|
||||||
|
"docstring": "Base HTML scraper using httpx.\n\nThis scraper retrieves HTML documents over HTTP(S) and returns them\nas raw content wrapped in a `Content` object.\n\nFetches raw bytes and metadata only.\nThe scraper:\n- Uses `httpx.Client` for HTTP requests\n- Enforces an HTML content type\n- Preserves HTTP response metadata\n\nThe scraper does not:\n- Parse HTML\n- Perform retries or backoff\n- Handle non-HTML responses",
|
||||||
|
"members": {
|
||||||
|
"content_type": {
|
||||||
|
"name": "content_type",
|
||||||
|
"kind": "attribute",
|
||||||
|
"path": "omniread.html.scraper.HTMLScraper.content_type",
|
||||||
|
"signature": null,
|
||||||
|
"docstring": null
|
||||||
|
},
|
||||||
|
"validate_content_type": {
|
||||||
|
"name": "validate_content_type",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.scraper.HTMLScraper.validate_content_type",
|
||||||
|
"signature": "<bound method Function.signature of Function('validate_content_type', 71, 94)>",
|
||||||
|
"docstring": "Validate that the HTTP response contains HTML content.\n\nArgs:\n response: HTTP response returned by `httpx`.\n\nRaises:\n ValueError: If the `Content-Type` header is missing or does not\n indicate HTML content."
|
||||||
|
},
|
||||||
|
"fetch": {
|
||||||
|
"name": "fetch",
|
||||||
|
"kind": "function",
|
||||||
|
"path": "omniread.html.scraper.HTMLScraper.fetch",
|
||||||
|
"signature": "<bound method Function.signature of Function('fetch', 96, 134)>",
|
||||||
|
"docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source: URL of the HTML document.\n metadata: Optional metadata to be merged into the returned content.\n\nReturns:\n A `Content` instance containing:\n - Raw HTML bytes\n - Source URL\n - HTML content type\n - HTTP response metadata\n\nRaises:\n httpx.HTTPError: If the HTTP request fails.\n ValueError: If the response is not valid HTML."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
1639
mcp_docs/modules/omniread.json
Normal file
1639
mcp_docs/modules/omniread.json
Normal file
File diff suppressed because it is too large
Load Diff
69
mcp_docs/modules/omniread.pdf.client.json
Normal file
69
mcp_docs/modules/omniread.pdf.client.json
Normal file
@@ -0,0 +1,69 @@
|
|||||||
|
{
|
||||||
|
"module": "omniread.pdf.client",
|
||||||
|
"content": {
|
||||||
|
"path": "omniread.pdf.client",
|
||||||
|
"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",
|
||||||
|
"objects": {
|
||||||
|
"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."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
419
mcp_docs/modules/omniread.pdf.json
Normal file
419
mcp_docs/modules/omniread.pdf.json
Normal file
@@ -0,0 +1,419 @@
|
|||||||
|
{
|
||||||
|
"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."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
134
mcp_docs/modules/omniread.pdf.parser.json
Normal file
134
mcp_docs/modules/omniread.pdf.parser.json
Normal file
@@ -0,0 +1,134 @@
|
|||||||
|
{
|
||||||
|
"module": "omniread.pdf.parser",
|
||||||
|
"content": {
|
||||||
|
"path": "omniread.pdf.parser",
|
||||||
|
"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.",
|
||||||
|
"objects": {
|
||||||
|
"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."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
152
mcp_docs/modules/omniread.pdf.scraper.json
Normal file
152
mcp_docs/modules/omniread.pdf.scraper.json
Normal file
@@ -0,0 +1,152 @@
|
|||||||
|
{
|
||||||
|
"module": "omniread.pdf.scraper",
|
||||||
|
"content": {
|
||||||
|
"path": "omniread.pdf.scraper",
|
||||||
|
"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.",
|
||||||
|
"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\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."
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
50
mcp_docs/nav.json
Normal file
50
mcp_docs/nav.json
Normal file
@@ -0,0 +1,50 @@
|
|||||||
|
[
|
||||||
|
{
|
||||||
|
"module": "omniread",
|
||||||
|
"resource": "doc://modules/omniread"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"module": "omniread.core",
|
||||||
|
"resource": "doc://modules/omniread.core"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"module": "omniread.core.content",
|
||||||
|
"resource": "doc://modules/omniread.core.content"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"module": "omniread.core.parser",
|
||||||
|
"resource": "doc://modules/omniread.core.parser"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"module": "omniread.core.scraper",
|
||||||
|
"resource": "doc://modules/omniread.core.scraper"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"module": "omniread.html",
|
||||||
|
"resource": "doc://modules/omniread.html"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"module": "omniread.html.parser",
|
||||||
|
"resource": "doc://modules/omniread.html.parser"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"module": "omniread.html.scraper",
|
||||||
|
"resource": "doc://modules/omniread.html.scraper"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"module": "omniread.pdf",
|
||||||
|
"resource": "doc://modules/omniread.pdf"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"module": "omniread.pdf.client",
|
||||||
|
"resource": "doc://modules/omniread.pdf.client"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"module": "omniread.pdf.parser",
|
||||||
|
"resource": "doc://modules/omniread.pdf.parser"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"module": "omniread.pdf.scraper",
|
||||||
|
"resource": "doc://modules/omniread.pdf.scraper"
|
||||||
|
}
|
||||||
|
]
|
||||||
79
mkdocs.yml
79
mkdocs.yml
@@ -4,50 +4,51 @@ site_description: Format-agnostic document reading, parsing, and scraping framew
|
|||||||
theme:
|
theme:
|
||||||
name: material
|
name: material
|
||||||
palette:
|
palette:
|
||||||
- scheme: slate
|
- scheme: slate
|
||||||
primary: deep purple
|
primary: deep purple
|
||||||
accent: cyan
|
accent: cyan
|
||||||
font:
|
font:
|
||||||
text: Inter
|
text: Inter
|
||||||
code: JetBrains Mono
|
code: JetBrains Mono
|
||||||
features:
|
features:
|
||||||
- navigation.tabs
|
- navigation.tabs
|
||||||
- navigation.expand
|
- navigation.expand
|
||||||
- navigation.top
|
- navigation.top
|
||||||
- navigation.instant
|
- navigation.instant
|
||||||
- content.code.copy
|
- content.code.copy
|
||||||
- content.code.annotate
|
- content.code.annotate
|
||||||
|
|
||||||
plugins:
|
plugins:
|
||||||
- search
|
- search
|
||||||
- mkdocstrings:
|
- mkdocstrings:
|
||||||
handlers:
|
handlers:
|
||||||
python:
|
python:
|
||||||
paths: ["."]
|
paths:
|
||||||
options:
|
- .
|
||||||
docstring_style: google
|
options:
|
||||||
show_source: false
|
docstring_style: google
|
||||||
show_signature_annotations: true
|
show_source: false
|
||||||
separate_signature: true
|
show_signature_annotations: true
|
||||||
merge_init_into_class: true
|
separate_signature: true
|
||||||
inherited_members: true
|
merge_init_into_class: true
|
||||||
annotations_path: brief
|
inherited_members: true
|
||||||
show_root_heading: true
|
annotations_path: brief
|
||||||
group_by_category: true
|
show_root_heading: true
|
||||||
|
group_by_category: true
|
||||||
|
|
||||||
nav:
|
nav:
|
||||||
- Home: index.md
|
- Home: omniread/index.md
|
||||||
|
- Core API:
|
||||||
- Core (Contracts):
|
- omniread/core/index.md
|
||||||
- Content Models: core/content.md
|
- omniread/core/content.md
|
||||||
- Parsers: core/parser.md
|
- omniread/core/parser.md
|
||||||
- Scrapers: core/scraper.md
|
- omniread/core/scraper.md
|
||||||
|
- HTML Handling:
|
||||||
- HTML Implementation:
|
- omniread/html/index.md
|
||||||
- HTML Parser: html/parser.md
|
- omniread/html/parser.md
|
||||||
- HTML Scraper: html/scraper.md
|
- omniread/html/scraper.md
|
||||||
|
- PDF Handling:
|
||||||
- PDF Implementation:
|
- omniread/pdf/index.md
|
||||||
- PDF Client: pdf/client.md
|
- omniread/pdf/client.md
|
||||||
- PDF Parser: pdf/parser.md
|
- omniread/pdf/parser.md
|
||||||
- PDF Scraper: pdf/scraper.md
|
- omniread/pdf/scraper.md
|
||||||
|
|||||||
@@ -94,6 +94,27 @@ PDF:
|
|||||||
- FileSystemPDFClient
|
- FileSystemPDFClient
|
||||||
- PDFScraper
|
- PDFScraper
|
||||||
- PDFParser
|
- PDFParser
|
||||||
|
|
||||||
|
## Core Philosophy
|
||||||
|
|
||||||
|
`OmniRead` is designed as a **decoupled content engine**:
|
||||||
|
|
||||||
|
1. **Separation of Concerns**: Scrapers *fetch*, Parsers *interpret*. Neither knows about the other.
|
||||||
|
2. **Normalized Exchange**: All components communicate via the `Content` model, ensuring a consistent contract.
|
||||||
|
3. **Format Agnosticism**: The core logic is independent of whether the input is HTML, PDF, or JSON.
|
||||||
|
|
||||||
|
## Documentation Design
|
||||||
|
|
||||||
|
For those extending `OmniRead`, follow these "AI-Native" docstring principles:
|
||||||
|
|
||||||
|
### For Humans
|
||||||
|
- **Clear Contracts**: Explicitly state what a component is and is NOT responsible for.
|
||||||
|
- **Runnable Examples**: Include small, logical snippets in the package `__init__.py`.
|
||||||
|
|
||||||
|
### For LLMs
|
||||||
|
- **Structured Models**: Use dataclasses and enums for core data to ensure clean MCP JSON representation.
|
||||||
|
- **Type Safety**: All public APIs must be fully typed and have corresponding `.pyi` stubs.
|
||||||
|
- **Detailed Raises**: Include `: description` pairs in the `Raises` section to help agents handle errors gracefully.
|
||||||
"""
|
"""
|
||||||
|
|
||||||
from .core import Content, ContentType
|
from .core import Content, ContentType
|
||||||
|
|||||||
13
omniread/__init__.pyi
Normal file
13
omniread/__init__.pyi
Normal file
@@ -0,0 +1,13 @@
|
|||||||
|
from .core import Content, ContentType
|
||||||
|
from .html import HTMLScraper, HTMLParser
|
||||||
|
from .pdf import FileSystemPDFClient, PDFScraper, PDFParser
|
||||||
|
|
||||||
|
__all__ = [
|
||||||
|
"Content",
|
||||||
|
"ContentType",
|
||||||
|
"HTMLScraper",
|
||||||
|
"HTMLParser",
|
||||||
|
"FileSystemPDFClient",
|
||||||
|
"PDFScraper",
|
||||||
|
"PDFParser",
|
||||||
|
]
|
||||||
10
omniread/core/__init__.pyi
Normal file
10
omniread/core/__init__.pyi
Normal file
@@ -0,0 +1,10 @@
|
|||||||
|
from .content import Content, ContentType
|
||||||
|
from .parser import BaseParser
|
||||||
|
from .scraper import BaseScraper
|
||||||
|
|
||||||
|
__all__ = [
|
||||||
|
"Content",
|
||||||
|
"ContentType",
|
||||||
|
"BaseParser",
|
||||||
|
"BaseScraper",
|
||||||
|
]
|
||||||
15
omniread/core/content.pyi
Normal file
15
omniread/core/content.pyi
Normal file
@@ -0,0 +1,15 @@
|
|||||||
|
from enum import Enum
|
||||||
|
from typing import Any, Mapping, Optional
|
||||||
|
|
||||||
|
class ContentType(str, Enum):
|
||||||
|
HTML = "text/html"
|
||||||
|
PDF = "application/pdf"
|
||||||
|
JSON = "application/json"
|
||||||
|
XML = "application/xml"
|
||||||
|
|
||||||
|
class Content:
|
||||||
|
raw: bytes
|
||||||
|
source: str
|
||||||
|
content_type: Optional[ContentType]
|
||||||
|
metadata: Optional[Mapping[str, Any]]
|
||||||
|
def __init__(self, raw: bytes, source: str, content_type: Optional[ContentType] = ..., metadata: Optional[Mapping[str, Any]] = ...) -> None: ...
|
||||||
13
omniread/core/parser.pyi
Normal file
13
omniread/core/parser.pyi
Normal file
@@ -0,0 +1,13 @@
|
|||||||
|
from abc import ABC, abstractmethod
|
||||||
|
from typing import Generic, TypeVar, Set
|
||||||
|
from .content import Content, ContentType
|
||||||
|
|
||||||
|
T = TypeVar("T")
|
||||||
|
|
||||||
|
class BaseParser(ABC, Generic[T]):
|
||||||
|
supported_types: Set[ContentType]
|
||||||
|
content: Content
|
||||||
|
def __init__(self, content: Content) -> None: ...
|
||||||
|
@abstractmethod
|
||||||
|
def parse(self) -> T: ...
|
||||||
|
def supports(self) -> bool: ...
|
||||||
7
omniread/core/scraper.pyi
Normal file
7
omniread/core/scraper.pyi
Normal file
@@ -0,0 +1,7 @@
|
|||||||
|
from abc import ABC, abstractmethod
|
||||||
|
from typing import Any, Mapping, Optional
|
||||||
|
from .content import Content
|
||||||
|
|
||||||
|
class BaseScraper(ABC):
|
||||||
|
@abstractmethod
|
||||||
|
def fetch(self, source: str, *, metadata: Optional[Mapping[str, Any]] = ...) -> Content: ...
|
||||||
4
omniread/html/__init__.pyi
Normal file
4
omniread/html/__init__.pyi
Normal file
@@ -0,0 +1,4 @@
|
|||||||
|
from .scraper import HTMLScraper
|
||||||
|
from .parser import HTMLParser
|
||||||
|
|
||||||
|
__all__ = ["HTMLScraper", "HTMLParser"]
|
||||||
18
omniread/html/parser.pyi
Normal file
18
omniread/html/parser.pyi
Normal file
@@ -0,0 +1,18 @@
|
|||||||
|
from typing import Any, Generic, TypeVar, Optional, list, dict
|
||||||
|
from bs4 import BeautifulSoup, Tag
|
||||||
|
from omniread.core.content import ContentType, Content
|
||||||
|
from omniread.core.parser import BaseParser
|
||||||
|
|
||||||
|
T = TypeVar("T")
|
||||||
|
|
||||||
|
class HTMLParser(BaseParser[T], Generic[T]):
|
||||||
|
supported_types: set[ContentType]
|
||||||
|
def __init__(self, content: Content, features: str = ...) -> None: ...
|
||||||
|
def parse(self) -> T: ...
|
||||||
|
@staticmethod
|
||||||
|
def parse_div(div: Tag, *, separator: str = ...) -> str: ...
|
||||||
|
@staticmethod
|
||||||
|
def parse_link(a: Tag) -> Optional[str]: ...
|
||||||
|
@staticmethod
|
||||||
|
def parse_table(table: Tag) -> list[list[str]]: ...
|
||||||
|
def parse_meta(self) -> dict[str, Any]: ...
|
||||||
10
omniread/html/scraper.pyi
Normal file
10
omniread/html/scraper.pyi
Normal file
@@ -0,0 +1,10 @@
|
|||||||
|
import httpx
|
||||||
|
from typing import Any, Mapping, Optional
|
||||||
|
from omniread.core.content import Content, ContentType
|
||||||
|
from omniread.core.scraper import BaseScraper
|
||||||
|
|
||||||
|
class HTMLScraper(BaseScraper):
|
||||||
|
content_type: ContentType
|
||||||
|
def __init__(self, *, client: Optional[httpx.Client] = ..., timeout: float = ..., headers: Optional[Mapping[str, str]] = ..., follow_redirects: bool = ...) -> None: ...
|
||||||
|
def validate_content_type(self, response: httpx.Response) -> None: ...
|
||||||
|
def fetch(self, source: str, *, metadata: Optional[Mapping[str, Any]] = ...) -> Content: ...
|
||||||
5
omniread/pdf/__init__.pyi
Normal file
5
omniread/pdf/__init__.pyi
Normal file
@@ -0,0 +1,5 @@
|
|||||||
|
from .client import FileSystemPDFClient
|
||||||
|
from .scraper import PDFScraper
|
||||||
|
from .parser import PDFParser
|
||||||
|
|
||||||
|
__all__ = ["FileSystemPDFClient", "PDFScraper", "PDFParser"]
|
||||||
@@ -14,6 +14,7 @@ Typical backing stores include:
|
|||||||
- Network file systems
|
- Network file systems
|
||||||
"""
|
"""
|
||||||
|
|
||||||
|
from typing import Any
|
||||||
from abc import ABC, abstractmethod
|
from abc import ABC, abstractmethod
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
|
|
||||||
@@ -30,7 +31,7 @@ class BasePDFClient(ABC):
|
|||||||
"""
|
"""
|
||||||
|
|
||||||
@abstractmethod
|
@abstractmethod
|
||||||
def fetch(self, source: str) -> bytes:
|
def fetch(self, source: Any) -> bytes:
|
||||||
"""
|
"""
|
||||||
Fetch raw PDF bytes from the given source.
|
Fetch raw PDF bytes from the given source.
|
||||||
|
|
||||||
|
|||||||
10
omniread/pdf/client.pyi
Normal file
10
omniread/pdf/client.pyi
Normal file
@@ -0,0 +1,10 @@
|
|||||||
|
from abc import ABC, abstractmethod
|
||||||
|
from pathlib import Path
|
||||||
|
from typing import Any
|
||||||
|
|
||||||
|
class BasePDFClient(ABC):
|
||||||
|
@abstractmethod
|
||||||
|
def fetch(self, source: Any) -> bytes: ...
|
||||||
|
|
||||||
|
class FileSystemPDFClient(BasePDFClient):
|
||||||
|
def fetch(self, source: Path | str) -> bytes: ...
|
||||||
11
omniread/pdf/parser.pyi
Normal file
11
omniread/pdf/parser.pyi
Normal file
@@ -0,0 +1,11 @@
|
|||||||
|
from abc import abstractmethod
|
||||||
|
from typing import Generic, TypeVar
|
||||||
|
from omniread.core.content import ContentType
|
||||||
|
from omniread.core.parser import BaseParser
|
||||||
|
|
||||||
|
T = TypeVar("T")
|
||||||
|
|
||||||
|
class PDFParser(BaseParser[T], Generic[T]):
|
||||||
|
supported_types: set[ContentType]
|
||||||
|
@abstractmethod
|
||||||
|
def parse(self) -> T: ...
|
||||||
@@ -39,7 +39,7 @@ class PDFScraper(BaseScraper):
|
|||||||
|
|
||||||
def fetch(
|
def fetch(
|
||||||
self,
|
self,
|
||||||
source: str,
|
source: Any,
|
||||||
*,
|
*,
|
||||||
metadata: Optional[Mapping[str, Any]] = None,
|
metadata: Optional[Mapping[str, Any]] = None,
|
||||||
) -> Content:
|
) -> Content:
|
||||||
|
|||||||
8
omniread/pdf/scraper.pyi
Normal file
8
omniread/pdf/scraper.pyi
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
from typing import Any, Mapping, Optional
|
||||||
|
from omniread.core.content import Content, ContentType
|
||||||
|
from omniread.core.scraper import BaseScraper
|
||||||
|
from .client import BasePDFClient
|
||||||
|
|
||||||
|
class PDFScraper(BaseScraper):
|
||||||
|
def __init__(self, *, client: BasePDFClient) -> None: ...
|
||||||
|
def fetch(self, source: Any, *, metadata: Optional[Mapping[str, Any]] = ...) -> Content: ...
|
||||||
@@ -1,19 +0,0 @@
|
|||||||
httpx==0.27.0
|
|
||||||
beautifulsoup4==4.12.0
|
|
||||||
pydantic==2.12.3
|
|
||||||
jinja2==3.1.6
|
|
||||||
# lxml==5.2.0
|
|
||||||
|
|
||||||
# Test Packages
|
|
||||||
pytest==7.4.0
|
|
||||||
pytest-asyncio==0.21.0
|
|
||||||
pytest-cov==4.1.0
|
|
||||||
|
|
||||||
# Doc Packages
|
|
||||||
mkdocs==1.6.1
|
|
||||||
mkdocs-material==9.6.23
|
|
||||||
neoteroi-mkdocs==1.1.3
|
|
||||||
pymdown-extensions==10.16.1
|
|
||||||
mkdocs-swagger-ui-tag==0.7.2
|
|
||||||
mkdocstrings==1.0.0
|
|
||||||
mkdocstrings-python==2.0.1
|
|
||||||
Reference in New Issue
Block a user