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):
    """使用`2markdown API`加载`HTML`。"""

[docs]    def __init__(self, url: str, api_key: str):
        """使用URL和API密钥进行初始化。"""
        self.url = url
        self.api_key = api_key

[docs]    def lazy_load(
        self,
    ) -> Iterator[Document]:
        """懒加载文件。"""
        response = requests.post(
            "https://2markdown.com/api/2md",
            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)

Source code for langchain_community.document_loaders.tomarkdown