> For the complete documentation index, see [llms.txt](https://doc.thordata.com/doc/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://doc.thordata.com/doc/faq/product-problem/scraping/web-scraping-api/what-format-does-a-web-scraper-api-return-can-it-feed-straight-into-an-llm-pipeline.md).

# What format does a Web Scraper API return — can it feed straight into an LLM pipeline?

Structured JSON (HTML optional). Clean fields with no parser to maintain can go directly into LLM summarization, classification, or pre-training cleanup; it is not the right fit for deeply custom schemas or labeling — turn to the [custom dataset service](https://www.thordata.com/?ls=community\&lk=proxyip) instead.