Webscraper: Leverage Multimodal Large Language Models for Index-Content Web Scraping

Computer Science > Artificial Intelligence [Submitted on 31 Mar 2026] Webscraper: Leverage Multimodal Large Language Models for Index-Content Web Scraping Guan-Lun Huang, Yuh-Jzer Joung Modern web scraping struggles with dynamic, interactive websites that require more than static HTML parsing. Current methods are often brittle and require manual customization for each site. To address this, we introduce Webscraper, a framework designed to handle the challenges of modern, dynamic web applications. It leverages a Multimodal Large Language Model (MLLM) to autonomously navigate interactive interfaces, invoke specialized tools, and perform structured data extraction in environments where traditional scrapers are ineffective. Webscraper utilizes a structured five-stage prompting procedure and a set of custom-built tools to navigate and extract data from websites following the common ``index-and-content'' architecture. Our experiments, conducted on six news websites, demonstrate that the full Webscraper framework, equipped with both our guiding prompt and specialized tools, achieves a significant improvement in extraction accuracy over the baseline agent Anthropic's Computer Use. We also applied the framework to e-commerce platforms to validate its generalizability. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2603.29161 [cs.AI]   (or arXiv:2603.29161v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2603.29161 Focus to learn more Submission history From: Yuh-Jzer Joung [view email] [v1] Tue, 31 Mar 2026 02:20:27 UTC (962 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-03 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)