https://github.com/scrapfly/llm-scraping-demo

Demo notebooks for LLM based web scraping with Scrapfly
https://github.com/scrapfly/llm-scraping-demo

Last synced: about 1 year ago
JSON representation

Demo notebooks for LLM based web scraping with Scrapfly

• Host: GitHub
• URL: https://github.com/scrapfly/llm-scraping-demo
• Owner: scrapfly
• License: mit
• Created: 2024-06-28T06:12:20.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2024-07-11T15:06:57.000Z (almost 2 years ago)
• Last Synced: 2025-04-14T17:49:19.992Z (about 1 year ago)
• Language: Jupyter Notebook
• Size: 9.77 KB
• Stars: 2
• Watchers: 1
• Forks: 3
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# llm-scraping-demo

Demo notebooks for LLM based web scraping with Scrapfly used in intro video:

[![Watch the video](https://img.youtube.com/vi/muo6I9XY8K4/hqdefault.jpg)](https://www.youtube.com/watch?v=muo6I9XY8K4)

## Setup

To use this notebook you'll need:

- [Jupyter notebook server](https://jupyter.org/)

- `httpx`

All of which can be installed using the provided `pyproject.toml` using [poetry](https://python-poetry.org/) (or any other moder python package manager):

```

$ poetry install

$ poetry run jupyter notebook

[I 2024-07-09 21:54:57.134 ServerApp] Serving notebooks from local directory: /home/scrapfly/llm-scraping-demo

[I 2024-07-09 21:54:57.134 ServerApp] Jupyter Server 2.14.1 is running at:

[I 2024-07-09 21:54:57.134 ServerApp] http://localhost:8888/tree?token=7a960bcb9

[I 2024-07-09 21:54:57.134 ServerApp]     http://127.0.0.1:8888/tree?token=7a960b

#                                         ^^^^^^^^^^ open this in your browser.

```