# Does anyone know how to extract tables from pdf for llms?

**URL:** <https://free-pdf-to-word.net/forum/t/does-anyone-know-how-to-extract-tables-from-pdf-for-llms/123>\
**Category:** Merge, Split & Compress\
**Created:** [November 13, 2026, 10:57pm UTC](https://free-pdf-to-word.net/forum/t/does-anyone-know-how-to-extract-tables-from-pdf-for-llms/123 "2026-11-13T22:57:32Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![OliviaRussell](https://free-pdf-to-word.net/forum/letter_avatar_proxy/v4/letter/o/fbc32d/32.png) [@OliviaRussell](https://free-pdf-to-word.net/forum/u/OliviaRussell)\
**Post date:** [November 13, 2026, 10:57pm UTC](https://free-pdf-to-word.net/forum/t/does-anyone-know-how-to-extract-tables-from-pdf-for-llms/123/1 "2026-11-13T22:57:32Z")

</div>

I’m feeding a bunch of PDF reports into an LLM for a side project, but the tables come out as garbled text with all the columns merged together. Has anyone found a reliable way to extract them cleanly?

---

<div class="post-metadata">

**Author:** ![ashley.cardiff](https://free-pdf-to-word.net/forum/user_avatar/free-pdf-to-word.net/ashley.cardiff/32/31_2.png) [@ashley.cardiff](https://free-pdf-to-word.net/forum/u/ashley.cardiff)\
**Post date:** [November 13, 2026, 10:58pm UTC](https://free-pdf-to-word.net/forum/t/does-anyone-know-how-to-extract-tables-from-pdf-for-llms/123/2 "2026-11-13T22:58:17Z")

</div>

I agree, that is annoying. Honestly, I try selecting the table in the PDF reader, copying it, and pasting it into Excel or Sheets. If it lands in one column, I use Text to Columns with fixed width or tab delimiter, then save as CSV. To be fair, scanned pages or image tables usually will not copy cleanly, and then I am not sure there is a quick fix.