Yelp

Data engineers are discussing why Yelp scrapers often return incomplete datasets without throwing any errors, a problem that can silently corrupt downstream analysis. The conversation highlights a common frustration with tools that promise straightforward data extraction but fail quietly, prompting developers to share debugging approaches and caution about relying on scraping outputs without validation.

A study by 8ight found ChatGPT named local businesses with fewer than 25 reviews in 3.4% of tested cases, while Anthropic's Claude cited Yelp in 202 of 218 answers and ChatGPT leaned on BBB and licensing records. The findings raise questions about which sources AI assistants rely on when recommending local service firms like roofers and plumbers.