Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bhardwaj, Arth, Diwan, Nirav, Wang, Gang
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2601.06301
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914244791894016
author Bhardwaj, Arth
Diwan, Nirav
Wang, Gang
author_facet Bhardwaj, Arth
Diwan, Nirav
Wang, Gang
contents Web scraping has historically required technical expertise in HTML parsing, session management, and authentication circumvention, which limited large-scale data extraction to skilled developers. We argue that large language models (LLMs) have democratized web scraping, enabling low-skill users to execute sophisticated operations through simple natural language prompts. While extensive benchmarks evaluate these tools under optimal expert conditions, we show that without extensive manual effort, current LLM-based workflows allow novice users to scrape complex websites that would otherwise be inaccessible. We systematically benchmark what everyday users can do with off-the-shelf LLM tools across 35 sites spanning five security tiers, including authentication, anti-bot, and CAPTCHA controls. We devise and evaluate two distinct workflows: (a) LLM-assisted scripting, where users prompt LLMs to generate traditional scraping code but maintain manual execution control, and (b) end-to-end LLM agents, which autonomously navigate and extract data through integrated tool use. Our results demonstrate that end-to-end agents have made complex scraping accessible - requiring as little as a single prompt with minimal refinement (less than 5 changes) to complete workflows. We also highlight scenarios where LLM-assisted scripting may be simpler and faster for static sites. In light of these findings, we provide simple procedures for novices to use these workflows and gauge what adversaries could achieve using these.
format Preprint
id arxiv_https___arxiv_org_abs_2601_06301
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond BeautifulSoup: Benchmarking LLM-Powered Web Scraping for Everyday Users
Bhardwaj, Arth
Diwan, Nirav
Wang, Gang
Cryptography and Security
Artificial Intelligence
Software Engineering
Web scraping has historically required technical expertise in HTML parsing, session management, and authentication circumvention, which limited large-scale data extraction to skilled developers. We argue that large language models (LLMs) have democratized web scraping, enabling low-skill users to execute sophisticated operations through simple natural language prompts. While extensive benchmarks evaluate these tools under optimal expert conditions, we show that without extensive manual effort, current LLM-based workflows allow novice users to scrape complex websites that would otherwise be inaccessible. We systematically benchmark what everyday users can do with off-the-shelf LLM tools across 35 sites spanning five security tiers, including authentication, anti-bot, and CAPTCHA controls. We devise and evaluate two distinct workflows: (a) LLM-assisted scripting, where users prompt LLMs to generate traditional scraping code but maintain manual execution control, and (b) end-to-end LLM agents, which autonomously navigate and extract data through integrated tool use. Our results demonstrate that end-to-end agents have made complex scraping accessible - requiring as little as a single prompt with minimal refinement (less than 5 changes) to complete workflows. We also highlight scenarios where LLM-assisted scripting may be simpler and faster for static sites. In light of these findings, we provide simple procedures for novices to use these workflows and gauge what adversaries could achieve using these.
title Beyond BeautifulSoup: Benchmarking LLM-Powered Web Scraping for Everyday Users
topic Cryptography and Security
Artificial Intelligence
Software Engineering
url https://arxiv.org/abs/2601.06301