Metadata-Version: 2.4
Name: llama-index-readers-megalania
Version: 0.1.0
Summary: LlamaIndex reader for the Megalania scraping API.
Author: Megalania
License-Expression: MIT
Project-URL: Homepage, https://megalania.io
Project-URL: Documentation, https://docs.megalania.io/integrations/llamaindex
Project-URL: Source, https://github.com/megalania/megalania-python
Classifier: Development Status :: 4 - Beta
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: megalania<0.3,>=0.2
Requires-Dist: llama-index-core<0.15,>=0.14
Dynamic: license-file

# llama-index-readers-megalania

LlamaIndex reader for the [Megalania](https://megalania.io) scraping API.

```sh
pip install llama-index-readers-megalania
export MEG_API_KEY=...
```

```python
from llama_index.readers.megalania import MegalaniaReader

docs = MegalaniaReader().load_data(["https://docs.megalania.io/"])
crawl = MegalaniaReader().load_data("https://docs.megalania.io/", crawl={"max_pages": 20})
```

The documents hold Markdown with `source`, `request_id`, `credits_charged` and `target_status` in the metadata.
A blocked page raises `MegalaniaError`; set `continue_on_failure=True` to skip it. Blocked pages and errors are free.
For agents, connect the Megalania MCP server with `llama-index-tools-mcp`.

Guide: https://docs.megalania.io/integrations/llamaindex. MIT license.
