uvicorn VS requests-html

FastAPI & Uvicorn

This tells Heroku to run uvicorn, which is a web server implementation in Python.

FastAPI uses Uvicorn, an ASGI (Asynchronous Server Gateway Interface) web server implementation for Python.

Now, let’s run our FastAPI application using Uvicorn: uvicorn main:app --reload

Uvicorn + Starlette 8k requests/s

I switched to Hypercorn because Uvicorn currently supports HTTP/1.1 and WebSockets as mentioned at https://www.uvicorn.org

This will set up Chroma and run it as a server with uvicorn, making port 8000 accessible outside the net docker network. The command also mounts a persistent docker volume for Chroma's database, found at chroma/chroma from your project's root.

There's an open discussion under the Uvicorn repository and we prepared a repository for Reproduction GitHub Repo

FastAPI is a popular Python Web framework that developers use to create RESTful APIs. It is based on Pydantic and Python-type hints that assist in the serialization, deserialization, and validation of data. In this tutorial, we will use FastAPI to create a simple "Hello World" application. We test and run the application locally. FastAPI requires a ASGI server to run the application production such as Uvicorn.

- [3] https://github.com/encode/uvicorn/issues/527

requests-html

Ya, thanks for advice. When using requests_html library, I am trying to lower down the speed using response.html.render(timeout=1000), but it raise Runtime error instead on Google Colab: https://github.com/psf/requests-html/issues/517.

For dynamic js, prefer requests-html with xpath selection.

Example: requests-html which has a rather exhaustive README.md, but their dedicated page is not that helpful, if I remember correctly, and currently the domain is suspended.

When it comes to web scraping, the usual people recommend is beautifulsoup, lxml, or selenium. But I highly recommend people check out requests-html also. Its a library that is a happy medium between ease of use as in beautifulsoup and also good enough to be used for dynamic, javascript data where it would be overkill to use a browser emulator like selenium.

Quite possible. If you look at requests-html source code, it is simply one single python file that acts as a wrapper around a bunch of other packages, like requests, chromium, parse, lxml, etc., plus a couple convenience functions. So it could easily be some sort of bad dependency resolution.

What I do is try to see if I can use requests_html first before trying selenium. requests_html is usually enough if I dont need to interact with browser widgets or if the authentication isnt too difficult to reverse engineer.