# Web scraping node - Return HTML

**URL:** <https://forum.gumloop.com/t/web-scraping-node-return-html/1554>\
**Category:** General Question\
**Tags:** Website-Scraper\
**Created:** [March 1, 2025, 4:20am UTC](https://forum.gumloop.com/t/web-scraping-node-return-html/1554 "2025-03-01T04:20:41Z")\
**Posts on this page:** 1\
**Showing post:** 7

<div class="post-metadata">

**Author:** ![Shrikar](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.gumloop.com/shrikar/32/300_2.png) [@Shrikar](https://forum.gumloop.com/u/Shrikar)\
**Post date:** [March 1, 2025, 8:23am UTC](https://forum.gumloop.com/t/web-scraping-node-return-html/1554/7 "2025-03-01T08:23:23Z")

</div>

I am able to do it in python but I don’t understand why we can’t do it in the scrape source [https://www.gumloop.com/pipeline?workbook\_id=wj9uLit6jYjgPYwK8XaAU4](https://www.gumloop.com/pipeline?workbook_id=wj9uLit6jYjgPYwK8XaAU4). Ideally we should be able to traverse a dom elements without spending anything on the llm credits. I also think this might be a feature worth adding don’t run the LLM content on the whole page source specially when we have a lot of page with heavy html elements(wasting tokens). Let the end user define the scope of the html element and then run llm on top of those for extracting data

---

_[View the full topic](https://forum.gumloop.com/t/web-scraping-node-return-html/1554)._