
Feb 11th, 2025
How a Gen Z Fashion Startup Extracted 350,000+ E-Commerce Products with Reworkd

Co-founder at Reworkd
About Lookbk
The Challenge
“As an early-stage startup, building and maintaining scrapers in-house consumed too much time. With plans to scale up considerably in the coming months, our manual approach to data collection just wasn’t sustainable.” — Caelin Sutch, Co-founder of Lookbk
Lookbk needed to gather extensive product data from many curated e-commerce sites, all mapped to its own internal schema. They initially used a headless browser service to avoid managing headless browsers themselves while still writing Playwright code for each site manually. However, this approach still had several key issues:
- Scraper Maintenance: E-commerce sites frequently changed layouts, breaking scrapers and forcing their engineers to drop everything to fix it - diverting attention from the core platform.
- Scalability Concerns: With plans to increase scraper coverage by 10×, the current process simply wouldn’t work.
- Bot Detection: Standard residential proxies weren’t enough to bypass anti-bot measures on many sites.
Why Reworkd
Recognizing that ongoing scraper maintenance would hamper long-term growth, Lookbk began searching for a platform that could resolve these challenges.
Reworkd solves Lookbk’s immediate scraping maintenance issues and can easily enable them to scale to 10× more sites in the future by using LLMs to dynamically generate and maintain Playwright scraping code. Combined with Reworkd’s fully managed solution, Lookbk no longer has to spend any time on data extraction and can simply let Reworkd keep the pipeline running smoothly—no matter how often websites change.
"Before Reworkd, we spent countless frustrating hours fixing scrapers every time a site changed—now it’s automated. Their advanced captcha solving also unlocks data from sites we couldn’t access before. Scaling our data pipeline is suddenly no longer an issue."

Caelin Sutch
Co-founder of Lookbk
The Result
Zero Maintenance Overhead
- Reduced 40 hours/month of engineering time to 0, resulting in a 30% reduction in data extraction costs.
Access to More Sites
- 20% more sites are now accessible (previously blocked by bot detection), giving customers access to a broader range of sources.
- Expanded data coverage without the need to hire additional engineers or manage proxies.
Rapid Implementation
- Timeline to scrape new sites reduced to days - not weeks.
- Scraped 350K products and over 1M product images.
Dedicated Slack Support
- Larger issues are resolved in hours, not days—minimizing disruption to data flows.
Book a call with us if you are interested in using Reworkd to automate your data scraping pipeline.