{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/autocrawler-a-progressive-understanding-web","title":"AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation","arxiv_id":"2404.12753","date":"2024-04-19","proceeding":null,"authors":["Wenhao Huang","Zhouhong Gu","Chenghao Peng","Zhixu Li","Jiaqing Liang","Yanghua Xiao","Liqian Wen","Zulong Chen"],"abstract":"Web scraping is a powerful technique that extracts data from websites, enabling automated data collection, enhancing data analysis capabilities, and minimizing manual data entry efforts. Existing methods, wrappers-based methods suffer from limited adaptability and scalability when faced with a new website, while language agents, empowered by large language models (LLMs), exhibit poor reusability in diverse web environments. In this work, we introduce the paradigm of generating web scrapers with LLMs and propose AutoScraper, a two-stage framework that can handle diverse and changing web environments more efficiently. AutoScraper leverages the hierarchical structure of HTML and similarity across different web pages for generating web scrapers. Besides, we propose a new executability metric for better measuring the performance of web scraper generation tasks. We conduct comprehensive experiments with multiple LLMs and demonstrate the effectiveness of our framework. Resources of this paper can be found at \\url{https://github.com/EZ-hwh/AutoScraper}","url_abs":"https://arxiv.org/abs/2404.12753v2","url_pdf":"https://arxiv.org/pdf/2404.12753v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"autocrawler-a-progressive-understanding-web","repo_url":"https://github.com/ez-hwh/autocrawler","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"autocrawler-a-progressive-understanding-web","repo_url":"https://github.com/ez-hwh/autoscraper","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"action-generation","task_name":"Action Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.12753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12753"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/EZ-hwh/AutoScraper","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"94f6df3aa62d12ec","entry":"load_file","repo":"EZ-hwh/AutoScraper","repo_kind":"official","path":"crawler_count.py","file_url":"https://github.com/EZ-hwh/AutoScraper/blob/HEAD/crawler_count.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"94f6df3aa62d12ec"}},{"code_sha256_prefix":"93cc6e204a2d564e","entry":"load_file","repo":"EZ-hwh/AutoScraper","repo_kind":"official","path":"run_swde/evaluate.py","file_url":"https://github.com/EZ-hwh/AutoScraper/blob/HEAD/run_swde/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"93cc6e204a2d564e"}},{"code_sha256_prefix":"ceba9a05a1208ccf","entry":"normalize","repo":"EZ-hwh/AutoScraper","repo_kind":"official","path":"run_klarna/evaluate.py","file_url":"https://github.com/EZ-hwh/AutoScraper/blob/HEAD/run_klarna/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ceba9a05a1208ccf"}},{"code_sha256_prefix":"b0224a571ca6dcce","entry":"normalize_list","repo":"EZ-hwh/AutoScraper","repo_kind":"official","path":"run_swde/evaluate.py","file_url":"https://github.com/EZ-hwh/AutoScraper/blob/HEAD/run_swde/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b0224a571ca6dcce"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}