Add parsers and blogs

[ccstan99]

To handle suggestions from agisf:

Add to scrape entire blog:

• epochai.org/blog,
• ai-risk-discussions.org,
• aiscc.org

Implement parsers for special_docs/indices:

• 80000hours,
• givewell.org,
• twitter.com,
• csis.org,
• blog.heim.xyz,
• astralcodexten.substack.com
• rethinkpriorities.org

[ccstan99]

Would it help to use LangChain's WebBaseLoader as a default until the unimplemented parsers get implemented?
https://python.langchain.com/docs/integrations/document_loaders/web_base

from langchain.document_loaders import WebBaseLoader
loader = WebBaseLoader("https://epochai.org/blog/")
docs = loader.load()