TrafilaturaWebReader

At a glance

A community member is experiencing an error when trying to use the Trafilatura Website Loader, where the loader class name is not found in the library. The issue is caused by a bug in the library.json file, which does not include the TrafilaturaWebReader loader. Another community member raised a pull request to fix the issue, which was merged. However, the updated loader is not immediately visible on the Llama Hub. After some time, the community member confirms that the issue is now resolved and the loader is working as expected.

Useful resources

LLeMoussel

When I try to use Trafilatura Website Loader, I get this error:

Plain Text

/usr/local/lib/python3.10/dist-packages/llama_index/readers/download.py in download_loader(loader_class, loader_hub_url, refresh_cache, use_gpt_index_import, custom_path)
    138         library = json.loads(library_raw_content)
    139         if loader_class not in library:
--> 140             raise ValueError("Loader class name not found in library")
    141 
    142         loader_id = library[loader_class]["id"]

ValueError: Loader class name not found in library

Python code:

Plain Text

from llama_index import download_loader

TrafilaturaWebReader = download_loader("TrafilaturaWebReader")

loader = TrafilaturaWebReader()
documents = loader.load_data(urls=['https://google.com'])

11 comments

rravitheja

Seems like TrafilaturaWebReader loader is not included in library.json here - https://github.com/run-llama/llama-hub/blob/269055628060856c3f6ac7bfa4451b31870e947f/llama_hub/library.json

rravitheja

and its causing the issue.

LLeMoussel

Bug in library.json for TrafilaturaWebReader. Should I make an issue?

rravitheja

oh I just raised a PR

rravitheja

https://github.com/run-llama/llama-hub/pull/602

LLeMoussel