mirror of
https://github.com/run-llama/llama-hub.git
synced 2025-08-15 04:01:32 +00:00
17 lines
415 B
Markdown
17 lines
415 B
Markdown
|
# Async Website Loader
|
||
|
|
|
||
|
|
This loader is an asynchronous web scraper that fetches the text from static websites by converting the HTML to text.
|
||
|
|
|
||
|
|
## Usage
|
||
|
|
|
||
|
|
To use this loader, you need to pass in an array of URLs.
|
||
|
|
|
||
|
|
```python
|
||
|
|
from llama_index import download_loader
|
||
|
|
|
||
|
|
AsyncWebPageReader = download_loader("AsyncWebPageReader")
|
||
|
|
|
||
|
|
loader = AsyncWebPageReader()
|
||
|
|
documents = loader.load_data(urls=['https://google.com'])
|
||
|
|
```
|