Source code for langchain_community.document_loaders.tomarkdown

from __future__ import annotations

from typing import Iterator

import requests
from langchain_core.documents import Document

from langchain_community.document_loaders.base import BaseLoader



[docs]
class ToMarkdownLoader(BaseLoader):
    """Load `HTML` using `2markdown API`."""


[docs]
    def __init__(self, url: str, api_key: str):
        """Initialize with url and api key."""
        self.url = url
        self.api_key = api_key



[docs]
    def lazy_load(
        self,
    ) -> Iterator[Document]:
        """Lazily load the file."""
        response = requests.post(
            "https://api.2markdown.com/v1/url2md",
            headers={"X-Api-Key": self.api_key},
            json={"url": self.url},
        )
        text = response.json()["article"]
        metadata = {"source": self.url}
        yield Document(page_content=text, metadata=metadata)