forked from Archives/langchain
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
19 lines
584 B
Python
19 lines
584 B
Python
"""Loader that loads AZLyrics."""
|
|
from typing import List
|
|
|
|
from langchain.docstore.document import Document
|
|
from langchain.document_loaders.web_base import WebBaseLoader
|
|
|
|
|
|
class AZLyricsLoader(WebBaseLoader):
|
|
"""Loader that loads AZLyrics webpages."""
|
|
|
|
def load(self) -> List[Document]:
|
|
"""Load webpage."""
|
|
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)]
|