Source code for langchain.document_loaders.college_confidential
"""Loader that loads College Confidential."""
from typing import List
from langchain.docstore.document import Document
from langchain.document_loaders.web_base import WebBaseLoader
[docs]class CollegeConfidentialLoader(WebBaseLoader):
"""Loader that loads College Confidential webpages."""
[docs] def load(self) -> List[Document]:
"""Load webpage."""
soup = self.scrape()
text = soup.select_one("main[class='skin-handler']").text
metadata = {"source": self.web_path}
return [Document(page_content=text, metadata=metadata)]