Source code for langchain_community.document_loaders.azlyrics

from typing import List

from langchain_core.documents import Document

from langchain_community.document_loaders.web_base import WebBaseLoader



[docs]class AZLyricsLoader(WebBaseLoader):
    """加载`AZLyrics`网页。"""


[docs]    def load(self) -> List[Document]:
        """加载网页到文档中。"""
        soup = self.scrape()
        title = soup.title.text
        lyrics = soup.find_all("div", {"class": ""})[2].text
        text = title + lyrics
        metadata = {"source": self.web_path}
        return [Document(page_content=text, metadata=metadata)]