aetos/omniread
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: modernize docstring types (List → list, Optional → X | None) to match signatures; regenerate lib/MCP docs (pydoclint zero)

Browse Source
This commit is contained in:
Vishesh 'ironeagle' Bangotra
2026-09-13 16:21:09 +05:30
parent 14d89f5f91
commit cd06de5435
46 changed files with 187 additions and 99 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/lib/index.md
View File

@@ -1,3 +1,4 @@
# omniread # omniread
::: omniread ::: omniread
- [Omniread](omniread/)

3
docs/lib/omniread/core/content.md Normal file
View File

@@ -0,0 +1,3 @@
# Content
::: omniread.core.content

6
docs/lib/omniread/core/index.md Normal file
View File

@@ -0,0 +1,6 @@
# Core
::: omniread.core
- [Content](content.md)
- [Parser](parser.md)
- [Scraper](scraper.md)

3
docs/lib/omniread/core/parser.md Normal file
View File

@@ -0,0 +1,3 @@
# Parser
::: omniread.core.parser

3
docs/lib/omniread/core/scraper.md Normal file
View File

@@ -0,0 +1,3 @@
# Scraper
::: omniread.core.scraper

3
docs/lib/omniread/csv/client.md Normal file
View File

@@ -0,0 +1,3 @@
# Client
::: omniread.csv.client

7
docs/lib/omniread/csv/index.md Normal file
View File

@@ -0,0 +1,7 @@
# Csv
::: omniread.csv
- [Client](client.md)
- [Parser](parser.md)
- [Parser Base](parser_base.md)
- [Scraper](scraper.md)

3
docs/lib/omniread/csv/parser.md Normal file
View File

@@ -0,0 +1,3 @@
# Parser
::: omniread.csv.parser

3
docs/lib/omniread/csv/parser_base.md Normal file
View File

@@ -0,0 +1,3 @@
# Parser Base
::: omniread.csv.parser_base

3
docs/lib/omniread/csv/scraper.md Normal file
View File

@@ -0,0 +1,3 @@
# Scraper
::: omniread.csv.scraper

5
docs/lib/omniread/html/index.md Normal file
View File

@@ -0,0 +1,5 @@
# Html
::: omniread.html
- [Parser](parser.md)
- [Scraper](scraper.md)

3
docs/lib/omniread/html/parser.md Normal file
View File

@@ -0,0 +1,3 @@
# Parser
::: omniread.html.parser

3
docs/lib/omniread/html/scraper.md Normal file
View File

@@ -0,0 +1,3 @@
# Scraper
::: omniread.html.scraper

8
docs/lib/omniread/index.md Normal file
View File

@@ -0,0 +1,8 @@
# Omniread
::: omniread
- [Core](core/)
- [Csv](csv/)
- [Html](html/)
- [Pdf](pdf/)
- [Xlsx](xlsx/)

3
docs/lib/omniread/pdf/client.md Normal file
View File

@@ -0,0 +1,3 @@
# Client
::: omniread.pdf.client

6
docs/lib/omniread/pdf/index.md Normal file
View File

@@ -0,0 +1,6 @@
# Pdf
::: omniread.pdf
- [Client](client.md)
- [Parser](parser.md)
- [Scraper](scraper.md)

3
docs/lib/omniread/pdf/parser.md Normal file
View File

@@ -0,0 +1,3 @@
# Parser
::: omniread.pdf.parser

3
docs/lib/omniread/pdf/scraper.md Normal file
View File

@@ -0,0 +1,3 @@
# Scraper
::: omniread.pdf.scraper

3
docs/lib/omniread/xlsx/client.md Normal file
View File

@@ -0,0 +1,3 @@
# Client
::: omniread.xlsx.client

7
docs/lib/omniread/xlsx/index.md Normal file
View File

@@ -0,0 +1,7 @@
# Xlsx
::: omniread.xlsx
- [Client](client.md)
- [Parser](parser.md)
- [Parser Base](parser_base.md)
- [Scraper](scraper.md)

3
docs/lib/omniread/xlsx/parser.md Normal file
View File

@@ -0,0 +1,3 @@
# Parser
::: omniread.xlsx.parser

3
docs/lib/omniread/xlsx/parser_base.md Normal file
View File

@@ -0,0 +1,3 @@
# Parser Base
::: omniread.xlsx.parser_base

3
docs/lib/omniread/xlsx/scraper.md Normal file
View File

@@ -0,0 +1,3 @@
# Scraper
::: omniread.xlsx.scraper

4
docs/mcp/modules/omniread.core.json
View File

@@ -141,7 +141,7 @@
"kind": "function", "kind": "function",
"path": "omniread.core.BaseScraper.fetch", "path": "omniread.core.BaseScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.core.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\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Optional[Mapping[str, Any]], optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object." "docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Mapping[str, Any] | None, optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
} }
} }
}, },
@@ -523,7 +523,7 @@
"kind": "function", "kind": "function",
"path": "omniread.core.scraper.BaseScraper.fetch", "path": "omniread.core.scraper.BaseScraper.fetch",
"signature": "<bound method Function.signature of Function('fetch', 52, 83)>", "signature": "<bound method Function.signature of Function('fetch', 52, 83)>",
"docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Optional[Mapping[str, Any]], optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object." "docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Mapping[str, Any] | None, optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
} }
} }
} }

2
docs/mcp/modules/omniread.core.scraper.json
View File

@@ -81,7 +81,7 @@
"kind": "function", "kind": "function",
"path": "omniread.core.scraper.BaseScraper.fetch", "path": "omniread.core.scraper.BaseScraper.fetch",
"signature": "<bound method Function.signature of Function('fetch', 52, 83)>", "signature": "<bound method Function.signature of Function('fetch', 52, 83)>",
"docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Optional[Mapping[str, Any]], optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object." "docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Mapping[str, Any] | None, optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
} }
} }
} }

12
docs/mcp/modules/omniread.csv.json
View File

@@ -48,14 +48,14 @@
"kind": "function", "kind": "function",
"path": "omniread.csv.CsvParser.parse", "path": "omniread.csv.CsvParser.parse",
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.csv.parser.CsvParser.parse')>", "signature": "<bound method Alias.signature of Alias('parse', 'omniread.csv.parser.CsvParser.parse')>",
"docstring": "Parse the document into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the document." "docstring": "Parse the document into normalized string rows.\n\nReturns:\n list[list[str]]:\n Rows of the document."
}, },
"rows": { "rows": {
"name": "rows", "name": "rows",
"kind": "function", "kind": "function",
"path": "omniread.csv.CsvParser.rows", "path": "omniread.csv.CsvParser.rows",
"signature": "<bound method Alias.signature of Alias('rows', 'omniread.csv.parser.CsvParser.rows')>", "signature": "<bound method Alias.signature of Alias('rows', 'omniread.csv.parser.CsvParser.rows')>",
"docstring": "Extract normalized string rows from the document.\n\nArgs:\n skip_empty (bool):\n When True (default), rows whose cells are all blank are\n omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row." "docstring": "Extract normalized string rows from the document.\n\nArgs:\n skip_empty (bool):\n When True (default), rows whose cells are all blank are\n omitted.\n\nReturns:\n list[list[str]]:\n Normalized rows; trailing blank cells are trimmed per row."
} }
} }
}, },
@@ -94,7 +94,7 @@
"kind": "function", "kind": "function",
"path": "omniread.csv.CsvScraper.fetch", "path": "omniread.csv.CsvScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.csv.scraper.CsvScraper.fetch')>", "signature": "<bound method Alias.signature of Alias('fetch', 'omniread.csv.scraper.CsvScraper.fetch')>",
"docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." "docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
} }
} }
}, },
@@ -267,14 +267,14 @@
"kind": "function", "kind": "function",
"path": "omniread.csv.parser.CsvParser.parse", "path": "omniread.csv.parser.CsvParser.parse",
"signature": "<bound method Function.signature of Function('parse', 57, 65)>", "signature": "<bound method Function.signature of Function('parse', 57, 65)>",
"docstring": "Parse the document into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the document." "docstring": "Parse the document into normalized string rows.\n\nReturns:\n list[list[str]]:\n Rows of the document."
}, },
"rows": { "rows": {
"name": "rows", "name": "rows",
"kind": "function", "kind": "function",
"path": "omniread.csv.parser.CsvParser.rows", "path": "omniread.csv.parser.CsvParser.rows",
"signature": "<bound method Function.signature of Function('rows', 67, 95)>", "signature": "<bound method Function.signature of Function('rows', 67, 95)>",
"docstring": "Extract normalized string rows from the document.\n\nArgs:\n skip_empty (bool):\n When True (default), rows whose cells are all blank are\n omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row." "docstring": "Extract normalized string rows from the document.\n\nArgs:\n skip_empty (bool):\n When True (default), rows whose cells are all blank are\n omitted.\n\nReturns:\n list[list[str]]:\n Normalized rows; trailing blank cells are trimmed per row."
} }
} }
} }
@@ -565,7 +565,7 @@
"kind": "function", "kind": "function",
"path": "omniread.csv.scraper.CsvScraper.fetch", "path": "omniread.csv.scraper.CsvScraper.fetch",
"signature": "<bound method Function.signature of Function('fetch', 49, 81)>", "signature": "<bound method Function.signature of Function('fetch', 49, 81)>",
"docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." "docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
} }
} }
} }

4
docs/mcp/modules/omniread.csv.parser.json
View File

@@ -97,14 +97,14 @@
"kind": "function", "kind": "function",
"path": "omniread.csv.parser.CsvParser.parse", "path": "omniread.csv.parser.CsvParser.parse",
"signature": "<bound method Function.signature of Function('parse', 57, 65)>", "signature": "<bound method Function.signature of Function('parse', 57, 65)>",
"docstring": "Parse the document into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the document." "docstring": "Parse the document into normalized string rows.\n\nReturns:\n list[list[str]]:\n Rows of the document."
}, },
"rows": { "rows": {
"name": "rows", "name": "rows",
"kind": "function", "kind": "function",
"path": "omniread.csv.parser.CsvParser.rows", "path": "omniread.csv.parser.CsvParser.rows",
"signature": "<bound method Function.signature of Function('rows', 67, 95)>", "signature": "<bound method Function.signature of Function('rows', 67, 95)>",
"docstring": "Extract normalized string rows from the document.\n\nArgs:\n skip_empty (bool):\n When True (default), rows whose cells are all blank are\n omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row." "docstring": "Extract normalized string rows from the document.\n\nArgs:\n skip_empty (bool):\n When True (default), rows whose cells are all blank are\n omitted.\n\nReturns:\n list[list[str]]:\n Normalized rows; trailing blank cells are trimmed per row."
} }
} }
} }

2
docs/mcp/modules/omniread.csv.scraper.json
View File

@@ -134,7 +134,7 @@
"kind": "function", "kind": "function",
"path": "omniread.csv.scraper.CsvScraper.fetch", "path": "omniread.csv.scraper.CsvScraper.fetch",
"signature": "<bound method Function.signature of Function('fetch', 49, 81)>", "signature": "<bound method Function.signature of Function('fetch', 49, 81)>",
"docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." "docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
} }
} }
} }

10
docs/mcp/modules/omniread.html.json
View File

@@ -30,7 +30,7 @@
"kind": "function", "kind": "function",
"path": "omniread.html.HTMLScraper.fetch", "path": "omniread.html.HTMLScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.html.scraper.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 (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." "docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source (str):\n URL of the HTML document.\n metadata (Mapping[str, Any] | None, 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."
} }
} }
}, },
@@ -67,7 +67,7 @@
"kind": "function", "kind": "function",
"path": "omniread.html.HTMLParser.parse_link", "path": "omniread.html.HTMLParser.parse_link",
"signature": "<bound method Alias.signature of Alias('parse_link', 'omniread.html.parser.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 (Tag):\n BeautifulSoup tag representing an anchor.\n\nReturns:\n Optional[str]:\n The value of the `href` attribute, or None if absent." "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": { "parse_table": {
"name": "parse_table", "name": "parse_table",
@@ -299,7 +299,7 @@
"kind": "function", "kind": "function",
"path": "omniread.html.parser.HTMLParser.parse_link", "path": "omniread.html.parser.HTMLParser.parse_link",
"signature": "<bound method Function.signature of Function('parse_link', 119, 132)>", "signature": "<bound method Function.signature of Function('parse_link', 119, 132)>",
"docstring": "Extract the hyperlink reference from an `<a>` element.\n\nArgs:\n a (Tag):\n BeautifulSoup tag representing an anchor.\n\nReturns:\n Optional[str]:\n The value of the `href` attribute, or None if absent." "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": { "parse_table": {
"name": "parse_table", "name": "parse_table",
@@ -447,7 +447,7 @@
"kind": "function", "kind": "function",
"path": "omniread.html.scraper.BaseScraper.fetch", "path": "omniread.html.scraper.BaseScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.core.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\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Optional[Mapping[str, Any]], optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object." "docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Mapping[str, Any] | None, optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
} }
} }
}, },
@@ -477,7 +477,7 @@
"kind": "function", "kind": "function",
"path": "omniread.html.scraper.HTMLScraper.fetch", "path": "omniread.html.scraper.HTMLScraper.fetch",
"signature": "<bound method Function.signature of Function('fetch', 104, 143)>", "signature": "<bound method Function.signature of Function('fetch', 104, 143)>",
"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." "docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source (str):\n URL of the HTML document.\n metadata (Mapping[str, Any] | None, 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."
} }
} }
} }

2
docs/mcp/modules/omniread.html.parser.json
View File

@@ -211,7 +211,7 @@
"kind": "function", "kind": "function",
"path": "omniread.html.parser.HTMLParser.parse_link", "path": "omniread.html.parser.HTMLParser.parse_link",
"signature": "<bound method Function.signature of Function('parse_link', 119, 132)>", "signature": "<bound method Function.signature of Function('parse_link', 119, 132)>",
"docstring": "Extract the hyperlink reference from an `<a>` element.\n\nArgs:\n a (Tag):\n BeautifulSoup tag representing an anchor.\n\nReturns:\n Optional[str]:\n The value of the `href` attribute, or None if absent." "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": { "parse_table": {
"name": "parse_table", "name": "parse_table",

4
docs/mcp/modules/omniread.html.scraper.json
View File

@@ -125,7 +125,7 @@
"kind": "function", "kind": "function",
"path": "omniread.html.scraper.BaseScraper.fetch", "path": "omniread.html.scraper.BaseScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.core.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\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Optional[Mapping[str, Any]], optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object." "docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Mapping[str, Any] | None, optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
} }
} }
}, },
@@ -155,7 +155,7 @@
"kind": "function", "kind": "function",
"path": "omniread.html.scraper.HTMLScraper.fetch", "path": "omniread.html.scraper.HTMLScraper.fetch",
"signature": "<bound method Function.signature of Function('fetch', 104, 143)>", "signature": "<bound method Function.signature of Function('fetch', 104, 143)>",
"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." "docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source (str):\n URL of the HTML document.\n metadata (Mapping[str, Any] | None, 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."
} }
} }
} }

62
docs/mcp/modules/omniread.json
View File

@@ -120,14 +120,14 @@
"kind": "function", "kind": "function",
"path": "omniread.CsvParser.parse", "path": "omniread.CsvParser.parse",
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.csv.parser.CsvParser.parse')>", "signature": "<bound method Alias.signature of Alias('parse', 'omniread.csv.parser.CsvParser.parse')>",
"docstring": "Parse the document into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the document." "docstring": "Parse the document into normalized string rows.\n\nReturns:\n list[list[str]]:\n Rows of the document."
}, },
"rows": { "rows": {
"name": "rows", "name": "rows",
"kind": "function", "kind": "function",
"path": "omniread.CsvParser.rows", "path": "omniread.CsvParser.rows",
"signature": "<bound method Alias.signature of Alias('rows', 'omniread.csv.parser.CsvParser.rows')>", "signature": "<bound method Alias.signature of Alias('rows', 'omniread.csv.parser.CsvParser.rows')>",
"docstring": "Extract normalized string rows from the document.\n\nArgs:\n skip_empty (bool):\n When True (default), rows whose cells are all blank are\n omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row." "docstring": "Extract normalized string rows from the document.\n\nArgs:\n skip_empty (bool):\n When True (default), rows whose cells are all blank are\n omitted.\n\nReturns:\n list[list[str]]:\n Normalized rows; trailing blank cells are trimmed per row."
} }
} }
}, },
@@ -166,7 +166,7 @@
"kind": "function", "kind": "function",
"path": "omniread.CsvScraper.fetch", "path": "omniread.CsvScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.csv.scraper.CsvScraper.fetch')>", "signature": "<bound method Alias.signature of Alias('fetch', 'omniread.csv.scraper.CsvScraper.fetch')>",
"docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." "docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
} }
} }
}, },
@@ -212,7 +212,7 @@
"kind": "function", "kind": "function",
"path": "omniread.HTMLScraper.fetch", "path": "omniread.HTMLScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.html.scraper.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 (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." "docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source (str):\n URL of the HTML document.\n metadata (Mapping[str, Any] | None, 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."
} }
} }
}, },
@@ -249,7 +249,7 @@
"kind": "function", "kind": "function",
"path": "omniread.HTMLParser.parse_link", "path": "omniread.HTMLParser.parse_link",
"signature": "<bound method Alias.signature of Alias('parse_link', 'omniread.html.parser.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 (Tag):\n BeautifulSoup tag representing an anchor.\n\nReturns:\n Optional[str]:\n The value of the `href` attribute, or None if absent." "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": { "parse_table": {
"name": "parse_table", "name": "parse_table",
@@ -295,7 +295,7 @@
"kind": "function", "kind": "function",
"path": "omniread.PDFScraper.fetch", "path": "omniread.PDFScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.pdf.scraper.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 (Any):\n Identifier of the PDF source as understood by the configured PDF client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw PDF bytes, source identifier, PDF content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the PDF client." "docstring": "Fetch a PDF document from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF source as understood by the configured PDF client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw PDF bytes, source identifier, PDF content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the PDF client."
} }
} }
}, },
@@ -380,14 +380,14 @@
"kind": "function", "kind": "function",
"path": "omniread.XlsxParser.parse", "path": "omniread.XlsxParser.parse",
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.xlsx.parser.XlsxParser.parse')>", "signature": "<bound method Alias.signature of Alias('parse', 'omniread.xlsx.parser.XlsxParser.parse')>",
"docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the default (first) worksheet." "docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n list[list[str]]:\n Rows of the default (first) worksheet."
}, },
"rows": { "rows": {
"name": "rows", "name": "rows",
"kind": "function", "kind": "function",
"path": "omniread.XlsxParser.rows", "path": "omniread.XlsxParser.rows",
"signature": "<bound method Alias.signature of Alias('rows', 'omniread.xlsx.parser.XlsxParser.rows')>", "signature": "<bound method Alias.signature of Alias('rows', 'omniread.xlsx.parser.XlsxParser.rows')>",
"docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (Optional[Union[int, str]]):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist." "docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (int | str | None):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n list[list[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist."
} }
} }
}, },
@@ -426,7 +426,7 @@
"kind": "function", "kind": "function",
"path": "omniread.XlsxScraper.fetch", "path": "omniread.XlsxScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.xlsx.scraper.XlsxScraper.fetch')>", "signature": "<bound method Alias.signature of Alias('fetch', 'omniread.xlsx.scraper.XlsxScraper.fetch')>",
"docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." "docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
} }
} }
}, },
@@ -574,7 +574,7 @@
"kind": "function", "kind": "function",
"path": "omniread.core.BaseScraper.fetch", "path": "omniread.core.BaseScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.core.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\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Optional[Mapping[str, Any]], optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object." "docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Mapping[str, Any] | None, optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
} }
} }
}, },
@@ -956,7 +956,7 @@
"kind": "function", "kind": "function",
"path": "omniread.core.scraper.BaseScraper.fetch", "path": "omniread.core.scraper.BaseScraper.fetch",
"signature": "<bound method Function.signature of Function('fetch', 52, 83)>", "signature": "<bound method Function.signature of Function('fetch', 52, 83)>",
"docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Optional[Mapping[str, Any]], optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object." "docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Mapping[str, Any] | None, optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
} }
} }
} }
@@ -1015,14 +1015,14 @@
"kind": "function", "kind": "function",
"path": "omniread.csv.CsvParser.parse", "path": "omniread.csv.CsvParser.parse",
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.csv.parser.CsvParser.parse')>", "signature": "<bound method Alias.signature of Alias('parse', 'omniread.csv.parser.CsvParser.parse')>",
"docstring": "Parse the document into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the document." "docstring": "Parse the document into normalized string rows.\n\nReturns:\n list[list[str]]:\n Rows of the document."
}, },
"rows": { "rows": {
"name": "rows", "name": "rows",
"kind": "function", "kind": "function",
"path": "omniread.csv.CsvParser.rows", "path": "omniread.csv.CsvParser.rows",
"signature": "<bound method Alias.signature of Alias('rows', 'omniread.csv.parser.CsvParser.rows')>", "signature": "<bound method Alias.signature of Alias('rows', 'omniread.csv.parser.CsvParser.rows')>",
"docstring": "Extract normalized string rows from the document.\n\nArgs:\n skip_empty (bool):\n When True (default), rows whose cells are all blank are\n omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row." "docstring": "Extract normalized string rows from the document.\n\nArgs:\n skip_empty (bool):\n When True (default), rows whose cells are all blank are\n omitted.\n\nReturns:\n list[list[str]]:\n Normalized rows; trailing blank cells are trimmed per row."
} }
} }
}, },
@@ -1061,7 +1061,7 @@
"kind": "function", "kind": "function",
"path": "omniread.csv.CsvScraper.fetch", "path": "omniread.csv.CsvScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.csv.scraper.CsvScraper.fetch')>", "signature": "<bound method Alias.signature of Alias('fetch', 'omniread.csv.scraper.CsvScraper.fetch')>",
"docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." "docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
} }
} }
}, },
@@ -1234,14 +1234,14 @@
"kind": "function", "kind": "function",
"path": "omniread.csv.parser.CsvParser.parse", "path": "omniread.csv.parser.CsvParser.parse",
"signature": "<bound method Function.signature of Function('parse', 57, 65)>", "signature": "<bound method Function.signature of Function('parse', 57, 65)>",
"docstring": "Parse the document into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the document." "docstring": "Parse the document into normalized string rows.\n\nReturns:\n list[list[str]]:\n Rows of the document."
}, },
"rows": { "rows": {
"name": "rows", "name": "rows",
"kind": "function", "kind": "function",
"path": "omniread.csv.parser.CsvParser.rows", "path": "omniread.csv.parser.CsvParser.rows",
"signature": "<bound method Function.signature of Function('rows', 67, 95)>", "signature": "<bound method Function.signature of Function('rows', 67, 95)>",
"docstring": "Extract normalized string rows from the document.\n\nArgs:\n skip_empty (bool):\n When True (default), rows whose cells are all blank are\n omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row." "docstring": "Extract normalized string rows from the document.\n\nArgs:\n skip_empty (bool):\n When True (default), rows whose cells are all blank are\n omitted.\n\nReturns:\n list[list[str]]:\n Normalized rows; trailing blank cells are trimmed per row."
} }
} }
} }
@@ -1532,7 +1532,7 @@
"kind": "function", "kind": "function",
"path": "omniread.csv.scraper.CsvScraper.fetch", "path": "omniread.csv.scraper.CsvScraper.fetch",
"signature": "<bound method Function.signature of Function('fetch', 49, 81)>", "signature": "<bound method Function.signature of Function('fetch', 49, 81)>",
"docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." "docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
} }
} }
} }
@@ -1573,7 +1573,7 @@
"kind": "function", "kind": "function",
"path": "omniread.html.HTMLScraper.fetch", "path": "omniread.html.HTMLScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.html.scraper.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 (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." "docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source (str):\n URL of the HTML document.\n metadata (Mapping[str, Any] | None, 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."
} }
} }
}, },
@@ -1610,7 +1610,7 @@
"kind": "function", "kind": "function",
"path": "omniread.html.HTMLParser.parse_link", "path": "omniread.html.HTMLParser.parse_link",
"signature": "<bound method Alias.signature of Alias('parse_link', 'omniread.html.parser.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 (Tag):\n BeautifulSoup tag representing an anchor.\n\nReturns:\n Optional[str]:\n The value of the `href` attribute, or None if absent." "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": { "parse_table": {
"name": "parse_table", "name": "parse_table",
@@ -1842,7 +1842,7 @@
"kind": "function", "kind": "function",
"path": "omniread.html.parser.HTMLParser.parse_link", "path": "omniread.html.parser.HTMLParser.parse_link",
"signature": "<bound method Function.signature of Function('parse_link', 119, 132)>", "signature": "<bound method Function.signature of Function('parse_link', 119, 132)>",
"docstring": "Extract the hyperlink reference from an `<a>` element.\n\nArgs:\n a (Tag):\n BeautifulSoup tag representing an anchor.\n\nReturns:\n Optional[str]:\n The value of the `href` attribute, or None if absent." "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": { "parse_table": {
"name": "parse_table", "name": "parse_table",
@@ -1990,7 +1990,7 @@
"kind": "function", "kind": "function",
"path": "omniread.html.scraper.BaseScraper.fetch", "path": "omniread.html.scraper.BaseScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.core.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\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Optional[Mapping[str, Any]], optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object." "docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Mapping[str, Any] | None, optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
} }
} }
}, },
@@ -2020,7 +2020,7 @@
"kind": "function", "kind": "function",
"path": "omniread.html.scraper.HTMLScraper.fetch", "path": "omniread.html.scraper.HTMLScraper.fetch",
"signature": "<bound method Function.signature of Function('fetch', 104, 143)>", "signature": "<bound method Function.signature of Function('fetch', 104, 143)>",
"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." "docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source (str):\n URL of the HTML document.\n metadata (Mapping[str, Any] | None, 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."
} }
} }
} }
@@ -2063,7 +2063,7 @@
"kind": "function", "kind": "function",
"path": "omniread.pdf.PDFScraper.fetch", "path": "omniread.pdf.PDFScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.pdf.scraper.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 (Any):\n Identifier of the PDF source as understood by the configured PDF client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw PDF bytes, source identifier, PDF content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the PDF client." "docstring": "Fetch a PDF document from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF source as understood by the configured PDF client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw PDF bytes, source identifier, PDF content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the PDF client."
} }
} }
}, },
@@ -2428,7 +2428,7 @@
"kind": "function", "kind": "function",
"path": "omniread.pdf.scraper.BaseScraper.fetch", "path": "omniread.pdf.scraper.BaseScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.core.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\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Optional[Mapping[str, Any]], optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object." "docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Mapping[str, Any] | None, optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
} }
} }
}, },
@@ -2460,7 +2460,7 @@
"kind": "function", "kind": "function",
"path": "omniread.pdf.scraper.PDFScraper.fetch", "path": "omniread.pdf.scraper.PDFScraper.fetch",
"signature": "<bound method Function.signature of Function('fetch', 48, 78)>", "signature": "<bound method Function.signature of Function('fetch', 48, 78)>",
"docstring": "Fetch a PDF document from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF source as understood by the configured PDF client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw PDF bytes, source identifier, PDF content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the PDF client." "docstring": "Fetch a PDF document from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF source as understood by the configured PDF client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw PDF bytes, source identifier, PDF content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the PDF client."
} }
} }
} }
@@ -2533,14 +2533,14 @@
"kind": "function", "kind": "function",
"path": "omniread.xlsx.XlsxParser.parse", "path": "omniread.xlsx.XlsxParser.parse",
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.xlsx.parser.XlsxParser.parse')>", "signature": "<bound method Alias.signature of Alias('parse', 'omniread.xlsx.parser.XlsxParser.parse')>",
"docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the default (first) worksheet." "docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n list[list[str]]:\n Rows of the default (first) worksheet."
}, },
"rows": { "rows": {
"name": "rows", "name": "rows",
"kind": "function", "kind": "function",
"path": "omniread.xlsx.XlsxParser.rows", "path": "omniread.xlsx.XlsxParser.rows",
"signature": "<bound method Alias.signature of Alias('rows', 'omniread.xlsx.parser.XlsxParser.rows')>", "signature": "<bound method Alias.signature of Alias('rows', 'omniread.xlsx.parser.XlsxParser.rows')>",
"docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (Optional[Union[int, str]]):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist." "docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (int | str | None):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n list[list[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist."
} }
} }
}, },
@@ -2579,7 +2579,7 @@
"kind": "function", "kind": "function",
"path": "omniread.xlsx.XlsxScraper.fetch", "path": "omniread.xlsx.XlsxScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.xlsx.scraper.XlsxScraper.fetch')>", "signature": "<bound method Alias.signature of Alias('fetch', 'omniread.xlsx.scraper.XlsxScraper.fetch')>",
"docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." "docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
} }
} }
}, },
@@ -2773,14 +2773,14 @@
"kind": "function", "kind": "function",
"path": "omniread.xlsx.parser.XlsxParser.parse", "path": "omniread.xlsx.parser.XlsxParser.parse",
"signature": "<bound method Function.signature of Function('parse', 85, 93)>", "signature": "<bound method Function.signature of Function('parse', 85, 93)>",
"docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the default (first) worksheet." "docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n list[list[str]]:\n Rows of the default (first) worksheet."
}, },
"rows": { "rows": {
"name": "rows", "name": "rows",
"kind": "function", "kind": "function",
"path": "omniread.xlsx.parser.XlsxParser.rows", "path": "omniread.xlsx.parser.XlsxParser.rows",
"signature": "<bound method Function.signature of Function('rows', 95, 127)>", "signature": "<bound method Function.signature of Function('rows', 95, 127)>",
"docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (Optional[Union[int, str]]):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist." "docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (int | str | None):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n list[list[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist."
} }
} }
} }
@@ -3071,7 +3071,7 @@
"kind": "function", "kind": "function",
"path": "omniread.xlsx.scraper.XlsxScraper.fetch", "path": "omniread.xlsx.scraper.XlsxScraper.fetch",
"signature": "<bound method Function.signature of Function('fetch', 48, 80)>", "signature": "<bound method Function.signature of Function('fetch', 48, 80)>",
"docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." "docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
} }
} }
} }

6
docs/mcp/modules/omniread.pdf.json
View File

@@ -32,7 +32,7 @@
"kind": "function", "kind": "function",
"path": "omniread.pdf.PDFScraper.fetch", "path": "omniread.pdf.PDFScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.pdf.scraper.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 (Any):\n Identifier of the PDF source as understood by the configured PDF client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw PDF bytes, source identifier, PDF content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the PDF client." "docstring": "Fetch a PDF document from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF source as understood by the configured PDF client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw PDF bytes, source identifier, PDF content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the PDF client."
} }
} }
}, },
@@ -397,7 +397,7 @@
"kind": "function", "kind": "function",
"path": "omniread.pdf.scraper.BaseScraper.fetch", "path": "omniread.pdf.scraper.BaseScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.core.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\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Optional[Mapping[str, Any]], optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object." "docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Mapping[str, Any] | None, optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
} }
} }
}, },
@@ -429,7 +429,7 @@
"kind": "function", "kind": "function",
"path": "omniread.pdf.scraper.PDFScraper.fetch", "path": "omniread.pdf.scraper.PDFScraper.fetch",
"signature": "<bound method Function.signature of Function('fetch', 48, 78)>", "signature": "<bound method Function.signature of Function('fetch', 48, 78)>",
"docstring": "Fetch a PDF document from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF source as understood by the configured PDF client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw PDF bytes, source identifier, PDF content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the PDF client." "docstring": "Fetch a PDF document from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF source as understood by the configured PDF client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw PDF bytes, source identifier, PDF content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the PDF client."
} }
} }
} }

4
docs/mcp/modules/omniread.pdf.scraper.json
View File

@@ -118,7 +118,7 @@
"kind": "function", "kind": "function",
"path": "omniread.pdf.scraper.BaseScraper.fetch", "path": "omniread.pdf.scraper.BaseScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.core.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\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Optional[Mapping[str, Any]], optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object." "docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Mapping[str, Any] | None, optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
} }
} }
}, },
@@ -150,7 +150,7 @@
"kind": "function", "kind": "function",
"path": "omniread.pdf.scraper.PDFScraper.fetch", "path": "omniread.pdf.scraper.PDFScraper.fetch",
"signature": "<bound method Function.signature of Function('fetch', 48, 78)>", "signature": "<bound method Function.signature of Function('fetch', 48, 78)>",
"docstring": "Fetch a PDF document from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF source as understood by the configured PDF client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw PDF bytes, source identifier, PDF content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the PDF client." "docstring": "Fetch a PDF document from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF source as understood by the configured PDF client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw PDF bytes, source identifier, PDF content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the PDF client."
} }
} }
} }

12
docs/mcp/modules/omniread.xlsx.json
View File

@@ -62,14 +62,14 @@
"kind": "function", "kind": "function",
"path": "omniread.xlsx.XlsxParser.parse", "path": "omniread.xlsx.XlsxParser.parse",
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.xlsx.parser.XlsxParser.parse')>", "signature": "<bound method Alias.signature of Alias('parse', 'omniread.xlsx.parser.XlsxParser.parse')>",
"docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the default (first) worksheet." "docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n list[list[str]]:\n Rows of the default (first) worksheet."
}, },
"rows": { "rows": {
"name": "rows", "name": "rows",
"kind": "function", "kind": "function",
"path": "omniread.xlsx.XlsxParser.rows", "path": "omniread.xlsx.XlsxParser.rows",
"signature": "<bound method Alias.signature of Alias('rows', 'omniread.xlsx.parser.XlsxParser.rows')>", "signature": "<bound method Alias.signature of Alias('rows', 'omniread.xlsx.parser.XlsxParser.rows')>",
"docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (Optional[Union[int, str]]):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist." "docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (int | str | None):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n list[list[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist."
} }
} }
}, },
@@ -108,7 +108,7 @@
"kind": "function", "kind": "function",
"path": "omniread.xlsx.XlsxScraper.fetch", "path": "omniread.xlsx.XlsxScraper.fetch",
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.xlsx.scraper.XlsxScraper.fetch')>", "signature": "<bound method Alias.signature of Alias('fetch', 'omniread.xlsx.scraper.XlsxScraper.fetch')>",
"docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." "docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
} }
} }
}, },
@@ -302,14 +302,14 @@
"kind": "function", "kind": "function",
"path": "omniread.xlsx.parser.XlsxParser.parse", "path": "omniread.xlsx.parser.XlsxParser.parse",
"signature": "<bound method Function.signature of Function('parse', 85, 93)>", "signature": "<bound method Function.signature of Function('parse', 85, 93)>",
"docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the default (first) worksheet." "docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n list[list[str]]:\n Rows of the default (first) worksheet."
}, },
"rows": { "rows": {
"name": "rows", "name": "rows",
"kind": "function", "kind": "function",
"path": "omniread.xlsx.parser.XlsxParser.rows", "path": "omniread.xlsx.parser.XlsxParser.rows",
"signature": "<bound method Function.signature of Function('rows', 95, 127)>", "signature": "<bound method Function.signature of Function('rows', 95, 127)>",
"docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (Optional[Union[int, str]]):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist." "docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (int | str | None):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n list[list[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist."
} }
} }
} }
@@ -600,7 +600,7 @@
"kind": "function", "kind": "function",
"path": "omniread.xlsx.scraper.XlsxScraper.fetch", "path": "omniread.xlsx.scraper.XlsxScraper.fetch",
"signature": "<bound method Function.signature of Function('fetch', 48, 80)>", "signature": "<bound method Function.signature of Function('fetch', 48, 80)>",
"docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." "docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
} }
} }
} }

4
docs/mcp/modules/omniread.xlsx.parser.json
View File

@@ -118,14 +118,14 @@
"kind": "function", "kind": "function",
"path": "omniread.xlsx.parser.XlsxParser.parse", "path": "omniread.xlsx.parser.XlsxParser.parse",
"signature": "<bound method Function.signature of Function('parse', 85, 93)>", "signature": "<bound method Function.signature of Function('parse', 85, 93)>",
"docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the default (first) worksheet." "docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n list[list[str]]:\n Rows of the default (first) worksheet."
}, },
"rows": { "rows": {
"name": "rows", "name": "rows",
"kind": "function", "kind": "function",
"path": "omniread.xlsx.parser.XlsxParser.rows", "path": "omniread.xlsx.parser.XlsxParser.rows",
"signature": "<bound method Function.signature of Function('rows', 95, 127)>", "signature": "<bound method Function.signature of Function('rows', 95, 127)>",
"docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (Optional[Union[int, str]]):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist." "docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (int | str | None):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n list[list[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist."
} }
} }
} }

2
docs/mcp/modules/omniread.xlsx.scraper.json
View File

@@ -134,7 +134,7 @@
"kind": "function", "kind": "function",
"path": "omniread.xlsx.scraper.XlsxScraper.fetch", "path": "omniread.xlsx.scraper.XlsxScraper.fetch",
"signature": "<bound method Function.signature of Function('fetch', 48, 80)>", "signature": "<bound method Function.signature of Function('fetch', 48, 80)>",
"docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client." "docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Mapping[str, Any] | None, optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
} }
} }
} }

44
docs/mcp/nav.json
View File

@@ -1,90 +1,90 @@
[ [
{ {
"module": "omniread", "module": "omniread",
"resource": "doc://modules/omniread" "resource": "docs://modules/omniread"
}, },
{ {
"module": "omniread.core", "module": "omniread.core",
"resource": "doc://modules/omniread.core" "resource": "docs://modules/omniread.core"
}, },
{ {
"module": "omniread.core.content", "module": "omniread.core.content",
"resource": "doc://modules/omniread.core.content" "resource": "docs://modules/omniread.core.content"
}, },
{ {
"module": "omniread.core.parser", "module": "omniread.core.parser",
"resource": "doc://modules/omniread.core.parser" "resource": "docs://modules/omniread.core.parser"
}, },
{ {
"module": "omniread.core.scraper", "module": "omniread.core.scraper",
"resource": "doc://modules/omniread.core.scraper" "resource": "docs://modules/omniread.core.scraper"
}, },
{ {
"module": "omniread.csv", "module": "omniread.csv",
"resource": "doc://modules/omniread.csv" "resource": "docs://modules/omniread.csv"
}, },
{ {
"module": "omniread.csv.client", "module": "omniread.csv.client",
"resource": "doc://modules/omniread.csv.client" "resource": "docs://modules/omniread.csv.client"
}, },
{ {
"module": "omniread.csv.parser", "module": "omniread.csv.parser",
"resource": "doc://modules/omniread.csv.parser" "resource": "docs://modules/omniread.csv.parser"
}, },
{ {
"module": "omniread.csv.parser_base", "module": "omniread.csv.parser_base",
"resource": "doc://modules/omniread.csv.parser_base" "resource": "docs://modules/omniread.csv.parser_base"
}, },
{ {
"module": "omniread.csv.scraper", "module": "omniread.csv.scraper",
"resource": "doc://modules/omniread.csv.scraper" "resource": "docs://modules/omniread.csv.scraper"
}, },
{ {
"module": "omniread.html", "module": "omniread.html",
"resource": "doc://modules/omniread.html" "resource": "docs://modules/omniread.html"
}, },
{ {
"module": "omniread.html.parser", "module": "omniread.html.parser",
"resource": "doc://modules/omniread.html.parser" "resource": "docs://modules/omniread.html.parser"
}, },
{ {
"module": "omniread.html.scraper", "module": "omniread.html.scraper",
"resource": "doc://modules/omniread.html.scraper" "resource": "docs://modules/omniread.html.scraper"
}, },
{ {
"module": "omniread.pdf", "module": "omniread.pdf",
"resource": "doc://modules/omniread.pdf" "resource": "docs://modules/omniread.pdf"
}, },
{ {
"module": "omniread.pdf.client", "module": "omniread.pdf.client",
"resource": "doc://modules/omniread.pdf.client" "resource": "docs://modules/omniread.pdf.client"
}, },
{ {
"module": "omniread.pdf.parser", "module": "omniread.pdf.parser",
"resource": "doc://modules/omniread.pdf.parser" "resource": "docs://modules/omniread.pdf.parser"
}, },
{ {
"module": "omniread.pdf.scraper", "module": "omniread.pdf.scraper",
"resource": "doc://modules/omniread.pdf.scraper" "resource": "docs://modules/omniread.pdf.scraper"
}, },
{ {
"module": "omniread.xlsx", "module": "omniread.xlsx",
"resource": "doc://modules/omniread.xlsx" "resource": "docs://modules/omniread.xlsx"
}, },
{ {
"module": "omniread.xlsx.client", "module": "omniread.xlsx.client",
"resource": "doc://modules/omniread.xlsx.client" "resource": "docs://modules/omniread.xlsx.client"
}, },
{ {
"module": "omniread.xlsx.parser", "module": "omniread.xlsx.parser",
"resource": "doc://modules/omniread.xlsx.parser" "resource": "docs://modules/omniread.xlsx.parser"
}, },
{ {
"module": "omniread.xlsx.parser_base", "module": "omniread.xlsx.parser_base",
"resource": "doc://modules/omniread.xlsx.parser_base" "resource": "docs://modules/omniread.xlsx.parser_base"
}, },
{ {
"module": "omniread.xlsx.scraper", "module": "omniread.xlsx.scraper",
"resource": "doc://modules/omniread.xlsx.scraper" "resource": "docs://modules/omniread.xlsx.scraper"
} }
] ]

2
omniread/core/scraper.py
View File

@@ -63,7 +63,7 @@ class BaseScraper(ABC):
source (str): source (str):
Location identifier (URL, file path, S3 URI, etc.). Location identifier (URL, file path, S3 URI, etc.).
metadata (Optional[Mapping[str, Any]], optional): metadata (Mapping[str, Any] | None, optional):
Optional hints for the scraper (headers, auth, etc.). Optional hints for the scraper (headers, auth, etc.).
Returns: Returns:

4
omniread/csv/parser.py
View File

@@ -59,7 +59,7 @@ class CsvParser(CsvParserBase[list[list[str]]]):
Parse the document into normalized string rows. Parse the document into normalized string rows.
Returns: Returns:
List[List[str]]: list[list[str]]:
Rows of the document. Rows of the document.
""" """
return self.rows() return self.rows()
@@ -74,7 +74,7 @@ class CsvParser(CsvParserBase[list[list[str]]]):
omitted. omitted.
Returns: Returns:
List[List[str]]: list[list[str]]:
Normalized rows; trailing blank cells are trimmed per row. Normalized rows; trailing blank cells are trimmed per row.
""" """
text = self._decode(self.content.raw) text = self._decode(self.content.raw)

2
omniread/csv/scraper.py
View File

@@ -59,7 +59,7 @@ class CsvScraper:
source (Any): source (Any):
Identifier of the csv source as understood by the Identifier of the csv source as understood by the
configured client. configured client.
metadata (Optional[Mapping[str, Any]], optional): metadata (Mapping[str, Any] | None, optional):
Optional metadata to attach to the returned content. Optional metadata to attach to the returned content.
Returns: Returns:

2
omniread/html/parser.py
View File

@@ -126,7 +126,7 @@ class HTMLParser(BaseParser[T], Generic[T]):
BeautifulSoup tag representing an anchor. BeautifulSoup tag representing an anchor.
Returns: Returns:
Optional[str]: str | None:
The value of the `href` attribute, or None if absent. The value of the `href` attribute, or None if absent.
""" """
return a.get("href") return a.get("href")

4
omniread/html/scraper.py
View File

@@ -64,7 +64,7 @@ class HTMLScraper(BaseScraper):
Optional pre-configured `httpx.Client`. If omitted, a client is created internally. Optional pre-configured `httpx.Client`. If omitted, a client is created internally.
timeout (float, optional): timeout (float, optional):
Request timeout in seconds. Request timeout in seconds.
headers (Optional[Mapping[str, str]], optional): headers (Mapping[str, str] | None, optional):
Optional default HTTP headers. Optional default HTTP headers.
follow_redirects (bool, optional): follow_redirects (bool, optional):
Whether to follow HTTP redirects. Whether to follow HTTP redirects.
@@ -113,7 +113,7 @@ class HTMLScraper(BaseScraper):
Args: Args:
source (str): source (str):
URL of the HTML document. URL of the HTML document.
metadata (Optional[Mapping[str, Any]], optional): metadata (Mapping[str, Any] | None, optional):
Optional metadata to be merged into the returned content. Optional metadata to be merged into the returned content.
Returns: Returns:

2
omniread/pdf/scraper.py
View File

@@ -57,7 +57,7 @@ class PDFScraper(BaseScraper):
Args: Args:
source (Any): source (Any):
Identifier of the PDF source as understood by the configured PDF client. Identifier of the PDF source as understood by the configured PDF client.
metadata (Optional[Mapping[str, Any]], optional): metadata (Mapping[str, Any] | None, optional):
Optional metadata to attach to the returned content. Optional metadata to attach to the returned content.
Returns: Returns:

6
omniread/xlsx/parser.py
View File

@@ -87,7 +87,7 @@ class XlsxParser(XlsxParserBase[list[list[str]]]):
Parse the first worksheet into normalized string rows. Parse the first worksheet into normalized string rows.
Returns: Returns:
List[List[str]]: list[list[str]]:
Rows of the default (first) worksheet. Rows of the default (first) worksheet.
""" """
return self.rows() return self.rows()
@@ -102,13 +102,13 @@ class XlsxParser(XlsxParserBase[list[list[str]]]):
Extract normalized string rows from a worksheet. Extract normalized string rows from a worksheet.
Args: Args:
sheet (Optional[Union[int, str]]): sheet (int | str | None):
Worksheet index or title; defaults to the first worksheet. Worksheet index or title; defaults to the first worksheet.
skip_empty (bool): skip_empty (bool):
When True (default), rows whose cells are all blank are omitted. When True (default), rows whose cells are all blank are omitted.
Returns: Returns:
List[List[str]]: list[list[str]]:
Normalized rows; trailing blank cells are trimmed per row. Normalized rows; trailing blank cells are trimmed per row.
Raises: Raises:

2
omniread/xlsx/scraper.py
View File

@@ -58,7 +58,7 @@ class XlsxScraper:
source (Any): source (Any):
Identifier of the spreadsheet source as understood by the Identifier of the spreadsheet source as understood by the
configured client. configured client.
metadata (Optional[Mapping[str, Any]], optional): metadata (Mapping[str, Any] | None, optional):
Optional metadata to attach to the returned content. Optional metadata to attach to the returned content.
Returns: Returns: