This commit is contained in:
2026-03-08 00:41:28 +05:30
parent 5842e6a227
commit 0fbf0ca0f0
14 changed files with 430 additions and 398 deletions

View File

@@ -2,7 +2,7 @@
"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",
"docstring": "HTML scraping implementation for OmniRead.\n\n---\n\n## Summary\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",
@@ -37,35 +37,35 @@
"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).",
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with minimal contextual metadata describing its origin and type\n - This class is the primary exchange format between Scrapers, Parsers, and Downstream consumers",
"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
"docstring": "Raw content bytes as retrieved from the source."
},
"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
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
},
"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
"docstring": "Optional MIME type of the content, if known."
},
"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
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
}
}
},
@@ -74,7 +74,7 @@
"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.",
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the content source\n - It is primarily used for routing content to the appropriate parser or downstream consumer",
"members": {
"HTML": {
"name": "HTML",
@@ -111,14 +111,14 @@
"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",
"docstring": "Base interface for all scrapers.\n\nNotes:\n **Responsibilities:**\n\n - A scraper is responsible ONLY for fetching raw content (bytes) from a source. It must not interpret or parse it\n - A scraper is a stateless acquisition component that retrieves raw content from a source and returns it as a `Content` object\n - Scrapers define how content is obtained, not what the content means\n - Implementations may vary in transport mechanism, authentication strategy, retry and backoff behavior\n\n **Constraints:**\n\n - Implementations must not parse content, modify content semantics, or 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."
"docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.)\n metadata (Optional[Mapping[str, Any]], optional):\n Optional hints for the scraper (headers, auth, etc.)\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source` and return it as raw bytes wrapped in a `Content` object"
}
}
},
@@ -126,8 +126,8 @@
"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",
"signature": "<bound method Class.signature of Class('HTMLScraper', 30, 139)>",
"docstring": "Base HTML scraper using httpx.\n\nNotes:\n **Responsibilities:**\n\n - This scraper retrieves HTML documents over HTTP(S) and returns them as raw content wrapped in a `Content` object\n - Fetches raw bytes and metadata only. The scraper uses `httpx.Client` for HTTP requests, enforces an HTML content type, preserves HTTP response metadata\n\n **Constraints:**\n \n - The scraper does not: Parse HTML, perform retries or backoff, handle non-HTML responses",
"members": {
"content_type": {
"name": "content_type",
@@ -140,15 +140,15 @@
"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."
"signature": "<bound method Function.signature of Function('validate_content_type', 74, 98)>",
"docstring": "Validate that the HTTP response contains HTML content.\n\nArgs:\n response (httpx.Response):\n HTTP response returned by `httpx`.\n\nRaises:\n ValueError:\n If the `Content-Type` header is missing or does not 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."
"signature": "<bound method Function.signature of Function('fetch', 100, 139)>",
"docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source (str):\n URL of the HTML document.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to be merged into the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw HTML bytes, source URL, HTML content type, and HTTP response metadata.\n\nRaises:\n httpx.HTTPError:\n If the HTTP request fails.\n ValueError:\n If the response is not valid HTML."
}
}
}