Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/EZ-hwh/AutoCrawler
Official implement of paper "AutoCrawler: A Progressive Understanding Web Agent for Web Crawler Generation"
https://github.com/EZ-hwh/AutoCrawler
webscraping
Last synced: about 2 months ago
JSON representation
Official implement of paper "AutoCrawler: A Progressive Understanding Web Agent for Web Crawler Generation"
- Host: GitHub
- URL: https://github.com/EZ-hwh/AutoCrawler
- Owner: EZ-hwh
- License: apache-2.0
- Created: 2024-04-19T09:19:31.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2024-06-18T12:16:39.000Z (3 months ago)
- Last Synced: 2024-06-19T13:52:31.629Z (3 months ago)
- Topics: webscraping
- Language: Python
- Homepage:
- Size: 1.25 MB
- Stars: 355
- Watchers: 11
- Forks: 30
- Open Issues: 7
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# AutoCrawler
This is the official code for paper *"AutoCrawler: A Progressive Understanding Web Agent for Web
Crawler Generation"*.![](assets/Framework.png)
## Setup
```bash
# Clone the AutoCrawler repository
git clone https://github.com/EZ-hwh/AutoCrawler# Change directory into the cloned repository
cd AutoCrawler# Optional: Create a Conda environment for AutoCrawler
# conda create -n autocrawler python=3.9
# conda activate autocrawler# Install required dependencies
pip install -r requirements.txt
```## TODOs
- [x] Public the experimental code.
- [ ] Adapt AutoCrawler for real-world websites.
- [ ] Website for showing our demo and testing.## Experiments
If you want to reproduce the result we report in paper.```bash
# Generate crawler with AutoCrawler
python crawler_generation.py \
--pattern reflexion \
--dataset swde \
--model ChatGPT \
--seed_website 3 \
--save_name ChatGPT \
--overwrite False# Extract information with crawler
python crawler_extraction.py \
--pattern autocrawler \
--dataset swde \
--model GPT4# Evaluate the extraction on SWDE dataset
python run_swde/evaluate.py \
--model GPT4 \
--pattern autocrawler
```## 📝 Citation
If you find this work useful, please consider citing our work:
```
@misc{huang2024autocrawler,
title={AutoCrawler: A Progressive Understanding Web Agent for Web Crawler Generation},
author={Wenhao Huang and Chenghao Peng and Zhixu Li and Jiaqing Liang and Yanghua Xiao and Liqian Wen and Zulong Chen},
year={2024},
eprint={2404.12753},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```