{"id":15228093,"url":"https://github.com/EZ-hwh/AutoScraper","last_synced_at":"2025-10-04T07:30:50.725Z","repository":{"id":235179450,"uuid":"788883686","full_name":"EZ-hwh/AutoScraper","owner":"EZ-hwh","description":"Official implement of paper \"AutoCrawler: A Progressive Understanding Web Agent for Web Crawler Generation\"","archived":false,"fork":false,"pushed_at":"2025-01-03T03:10:45.000Z","size":1315,"stargazers_count":441,"open_issues_count":6,"forks_count":36,"subscribers_count":12,"default_branch":"main","last_synced_at":"2025-01-03T04:20:42.884Z","etag":null,"topics":["webscraping"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/EZ-hwh.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-04-19T09:19:31.000Z","updated_at":"2025-01-03T03:10:49.000Z","dependencies_parsed_at":"2024-04-24T05:32:02.488Z","dependency_job_id":"b7517005-1c0f-49a7-9899-f352f8ba6733","html_url":"https://github.com/EZ-hwh/AutoScraper","commit_stats":null,"previous_names":["ez-hwh/autocrawler","ez-hwh/autoscraper"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EZ-hwh%2FAutoScraper","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EZ-hwh%2FAutoScraper/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EZ-hwh%2FAutoScraper/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EZ-hwh%2FAutoScraper/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/EZ-hwh","download_url":"https://codeload.github.com/EZ-hwh/AutoScraper/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":235227462,"owners_count":18956137,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["webscraping"],"created_at":"2024-09-29T00:00:45.611Z","updated_at":"2025-10-04T07:30:45.416Z","avatar_url":"https://github.com/EZ-hwh.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# AutoScraper\n\n\u003cdiv align=\"center\"\u003e\n    \u003ca href=\"https://arxiv.org/pdf/2404.12753.pdf\"\u003e\u003cimg src=\"assets/Paper-Arxiv-orange.svg\" \u003e\u003c/a\u003e\n    \u003ca href=\"https://hits.seeyoufarm.com\"\u003e\u003cimg src=\"https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https%3A%2F%2Fgithub.com%2FEZ-hwh%2FAutoCrawler\u0026count_bg=%2379C83D\u0026title_bg=%23555555\u0026icon=\u0026icon_color=%23E7E7E7\u0026title=hits\u0026edge_flat=false\"/\u003e\u003c/a\u003e\n    \u003c!-- \u003ca href=\"https://twitter.com/xuhaiya2483846/status/1654640739010351106\"\u003e\u003cimg src='assets/-twitter-blue.svg'\u003e\u003c/a\u003e --\u003e\n\u003c/div\u003e\n\n\nThis is the official code for paper *\"AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation\"*.\n\n\n![](assets/Framework.png)\n## Setup \n```bash\n# Clone the AutoScraper repository\ngit clone https://github.com/EZ-hwh/AutoCrawler\n\n# Change directory into the cloned repository\ncd AutoCrawler\n\n# Optional: Create a Conda environment for AutoScraper\n# conda create -n autocrawler python=3.9\n# conda activate autocrawler\n\n# Install required dependencies\npip install -r requirements.txt\n```\n\n## TODOs\n\n- [x] Public the experimental code.\n- [ ] Adapt AutoScraper for real-world websites.\n- [ ] Website for showing our demo and testing.\n\n## Experiments\nIf you want to reproduce the result we report in paper.\n\n```bash\n# Generate scraper with AutoScraper\npython crawler_generation.py \\\n    --pattern reflexion \\\n    --dataset swde \\\n    --model ChatGPT \\\n    --seed_website 3 \\\n    --save_name ChatGPT \\\n    --overwrite False\n\n# Extract information with scraper\npython crawler_extraction.py \\\n    --pattern autocrawler \\\n    --dataset swde \\\n    --model GPT4\n\n# Evaluate the extraction on SWDE dataset\npython run_swde/evaluate.py \\\n    --model GPT4 \\\n    --pattern autocrawler\n```\n\n## 📝 Citation\nIf you find this work useful, please consider citing our work:\n```\n@misc{huang2024autoscraperprogressiveunderstandingweb,\n      title={AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation}, \n      author={Wenhao Huang and Zhouhong Gu and Chenghao Peng and Zhixu Li and Jiaqing Liang and Yanghua Xiao and Liqian Wen and Zulong Chen},\n      year={2024},\n      eprint={2404.12753},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2404.12753}, \n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FEZ-hwh%2FAutoScraper","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FEZ-hwh%2FAutoScraper","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FEZ-hwh%2FAutoScraper/lists"}