using doc-forge (#1)
Reviewed-on: #1 Co-authored-by: Vishesh 'ironeagle' Bangotra <aetoskia@gmail.com> Co-committed-by: Vishesh 'ironeagle' Bangotra <aetoskia@gmail.com>
This commit is contained in:
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
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user