docs/mcp/omniread/modules/omniread.html.parser.json

{
  "module": "omniread.html.parser",
  "content": {
    "path": "omniread.html.parser",
    "docstring": "# Summary\n\nHTML 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\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": {
      "Content": {
        "name": "Content",
        "kind": "class",
        "path": "omniread.html.parser.Content",
        "signature": "Content(raw: bytes, source: str, content_type: ContentType | None = ..., metadata: Mapping[str, Any] | None = ...)",
        "docstring": "Normalized representation of extracted content.\n\nNotes:\n    **Responsibilities:**\n\n        - A `Content` instance represents a raw content payload along with\n          minimal contextual metadata describing its origin and type.\n        - This class is the primary exchange format between scrapers,\n          parsers, and downstream consumers.",
        "members": {
          "raw": {
            "name": "raw",
            "kind": "attribute",
            "path": "omniread.html.parser.Content.raw",
            "signature": null,
            "docstring": "Raw content bytes as retrieved from the source."
          },
          "source": {
            "name": "source",
            "kind": "attribute",
            "path": "omniread.html.parser.Content.source",
            "signature": null,
            "docstring": "Identifier of the content origin (URL, file path, or logical name)."
          },
          "content_type": {
            "name": "content_type",
            "kind": "attribute",
            "path": "omniread.html.parser.Content.content_type",
            "signature": null,
            "docstring": "Optional MIME type of the content, if known."
          },
          "metadata": {
            "name": "metadata",
            "kind": "attribute",
            "path": "omniread.html.parser.Content.metadata",
            "signature": null,
            "docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
          }
        }
      },
      "ContentType": {
        "name": "ContentType",
        "kind": "class",
        "path": "omniread.html.parser.ContentType",
        "signature": null,
        "docstring": "Supported MIME types for extracted content.\n\nNotes:\n    **Guarantees:**\n\n        - This enum represents the declared or inferred media type of the\n          content source.\n        - It is primarily used for routing content to the appropriate\n          parser or downstream consumer.",
        "members": {
          "HTML": {
            "name": "HTML",
            "kind": "attribute",
            "path": "omniread.html.parser.ContentType.HTML",
            "signature": null,
            "docstring": "HTML document content."
          },
          "PDF": {
            "name": "PDF",
            "kind": "attribute",
            "path": "omniread.html.parser.ContentType.PDF",
            "signature": null,
            "docstring": "PDF document content."
          },
          "XLSX": {
            "name": "XLSX",
            "kind": "attribute",
            "path": "omniread.html.parser.ContentType.XLSX",
            "signature": null,
            "docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
          },
          "CSV": {
            "name": "CSV",
            "kind": "attribute",
            "path": "omniread.html.parser.ContentType.CSV",
            "signature": null,
            "docstring": "Comma-separated-value document content."
          },
          "JSON": {
            "name": "JSON",
            "kind": "attribute",
            "path": "omniread.html.parser.ContentType.JSON",
            "signature": null,
            "docstring": "JSON document content."
          },
          "XML": {
            "name": "XML",
            "kind": "attribute",
            "path": "omniread.html.parser.ContentType.XML",
            "signature": null,
            "docstring": "XML document content."
          }
        }
      },
      "BaseParser": {
        "name": "BaseParser",
        "kind": "class",
        "path": "omniread.html.parser.BaseParser",
        "signature": "BaseParser(content: Content)",
        "docstring": "Base interface for all parsers.\n\nNotes:\n    **Guarantees:**\n\n        - A parser is a self-contained object that owns the `Content` it is\n          responsible for interpreting.\n        - Consumers may rely on early validation of content compatibility\n          and type-stable return values from `parse()`.\n\n    **Responsibilities:**\n\n        - Implementations must declare supported content types via `supported_types`.\n        - Implementations must raise parsing-specific exceptions from `parse()`.\n        - Implementations must remain deterministic for a given input.",
        "members": {
          "supported_types": {
            "name": "supported_types",
            "kind": "attribute",
            "path": "omniread.html.parser.BaseParser.supported_types",
            "signature": null,
            "docstring": "Set of content types supported by this parser. An empty set indicates that the parser is content-type agnostic."
          },
          "content": {
            "name": "content",
            "kind": "attribute",
            "path": "omniread.html.parser.BaseParser.content",
            "signature": null,
            "docstring": null
          },
          "parse": {
            "name": "parse",
            "kind": "function",
            "path": "omniread.html.parser.BaseParser.parse",
            "signature": "parse()",
            "docstring": "Parse the owned content into structured output.\n\nReturns:\n    T:\n        Parsed, structured representation.\n\nRaises:\n    Exception:\n        Parsing-specific errors as defined by the implementation.\n\nNotes:\n    **Responsibilities:**\n\n        - Implementations must fully consume the provided content and\n          return a deterministic, structured output."
          },
          "supports": {
            "name": "supports",
            "kind": "function",
            "path": "omniread.html.parser.BaseParser.supports",
            "signature": "supports()",
            "docstring": "Check whether this parser supports the content's type.\n\nReturns:\n    bool:\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": "HTMLParser(content: Content, features: str = 'html.parser')",
        "docstring": "Base HTML parser.\n\nNotes:\n    **Responsibilities:**\n\n        - This class extends the core `BaseParser` with HTML-specific behavior,\n          including DOM parsing via BeautifulSoup and reusable extraction helpers.\n        - Provides reusable helpers for HTML extraction. Concrete parsers must\n          explicitly define the return type.\n\n    **Guarantees:**\n\n        - Accepts only HTML content.\n        - Owns a parsed BeautifulSoup DOM tree.\n        - Provides pure helper utilities for common HTML structures.\n\n    **Constraints:**\n\n        - Concrete subclasses must define the output type `T` and implement\n          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": "parse() -> T",
            "docstring": "Fully parse the HTML content into structured output.\n\nReturns:\n    T:\n        Parsed representation of type `T`.\n\nNotes:\n    **Responsibilities:**\n\n        - Implementations must fully interpret the HTML DOM and return a\n          deterministic, structured output."
          },
          "parse_div": {
            "name": "parse_div",
            "kind": "function",
            "path": "omniread.html.parser.HTMLParser.parse_div",
            "signature": "parse_div(div: Tag, *, separator: str = ' ') -> str",
            "docstring": "Extract normalized text from a `<div>` element.\n\nArgs:\n    div (Tag):\n        BeautifulSoup tag representing a `<div>`.\n    separator (str, optional):\n        String used to separate text nodes.\n\nReturns:\n    str:\n        Flattened, whitespace-normalized text content."
          },
          "parse_link": {
            "name": "parse_link",
            "kind": "function",
            "path": "omniread.html.parser.HTMLParser.parse_link",
            "signature": "parse_link(a: Tag) -> str | None",
            "docstring": "Extract the hyperlink reference from an `<a>` element.\n\nArgs:\n    a (Tag):\n        BeautifulSoup tag representing an anchor.\n\nReturns:\n    str | None:\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": "parse_table(table: Tag) -> list[list[str]]",
            "docstring": "Parse an HTML table into a 2D list of strings.\n\nArgs:\n    table (Tag):\n        BeautifulSoup tag representing a `<table>`.\n\nReturns:\n    list[list[str]]:\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": "parse_meta() -> dict[str, Any]",
            "docstring": "Extract high-level metadata from the HTML document.\n\nReturns:\n    dict[str, Any]:\n        Dictionary containing extracted metadata.\n\nNotes:\n    **Responsibilities:**\n\n        - Extract high-level metadata from the HTML document.\n        - This includes: Document title, `<meta>` tag name/property to\n          content mappings."
          }
        }
      }
    }
  }
}