MWDumpLoader#

class langchain_community.document_loaders.mediawikidump.MWDumpLoader(file_path: str | Path, encoding: str | None = 'utf8', namespaces: Sequence[int] | None = None, skip_redirects: bool | None = False, stop_on_error: bool | None = True)[source]#

Load MediaWiki dump from an XML file.

Example

from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_community.document_loaders import MWDumpLoader

loader = MWDumpLoader(
    file_path="myWiki.xml",
    encoding="utf8"
)
docs = loader.load()
text_splitter = RecursiveCharacterTextSplitter(
    chunk_size=1000, chunk_overlap=0
)
texts = text_splitter.split_documents(docs)
Parameters:
  • file_path (str) – XML local file path

  • encoding (str, optional) – Charset encoding, defaults to “utf8”

  • namespaces (List[int],optional) – The namespace of pages you want to parse. See https://www.mediawiki.org/wiki/Help:Namespaces#Localisation for a list of all common namespaces

  • skip_redirects (bool, optional) – TR=rue to skip pages that redirect to other pages, False to keep them. False by default

  • stop_on_error (bool, optional) – False to skip over pages that cause parsing errors, True to stop. True by default

Methods

__init__(file_path[, encoding, namespaces, ...])

alazy_load()

A lazy loader for Documents.

aload()

Load data into Document objects.

lazy_load()

Lazy load from a file path.

load()

Load data into Document objects.

load_and_split([text_splitter])

Load Documents and split into chunks.

__init__(file_path: str | Path, encoding: str | None = 'utf8', namespaces: Sequence[int] | None = None, skip_redirects: bool | None = False, stop_on_error: bool | None = True)[source]#
Parameters:
  • file_path (str | Path)

  • encoding (str | None)

  • namespaces (Sequence[int] | None)

  • skip_redirects (bool | None)

  • stop_on_error (bool | None)

async alazy_load() AsyncIterator[Document]#

A lazy loader for Documents.

Return type:

AsyncIterator[Document]

async aload() list[Document]#

Load data into Document objects.

Return type:

list[Document]

lazy_load() Iterator[Document][source]#

Lazy load from a file path.

Return type:

Iterator[Document]

load() list[Document]#

Load data into Document objects.

Return type:

list[Document]

load_and_split(text_splitter: TextSplitter | None = None) list[Document]#

Load Documents and split into chunks. Chunks are returned as Documents.

Do not override this method. It should be considered to be deprecated!

Parameters:

text_splitter (Optional[TextSplitter]) – TextSplitter instance to use for splitting documents. Defaults to RecursiveCharacterTextSplitter.

Returns:

List of Documents.

Return type:

list[Document]

Examples using MWDumpLoader