This project provides a set of tools to help load and process various types of web content, including HTML pages, PDFs, and YouTube transcripts. It supports different methods for loading content, such as using httpx
, cloudscraper
, and singlefile
.
- Load HTML content using
httpx
orcloudscraper
. - Load PDF content.
- Load YouTube transcripts.
- Replace domains in URLs for specific services.
- Summarize Hacker News articles.
- Summarize Hugging Face papers.
- Handle text and image messages from LINE Bot.
- Push LINE message to LINE users.
This project is licensed under the MIT License.