Hi everyone,
I want to build a straightforward n8n flow that updates values in an Excel template using data from a PDF financial statement and a CSV. The plan is:
-
Read a CSV with the target rows (the template “skeleton”).
-
Extract tables from a PDF financial statement (about 240 pages, varies by company).
-
Use AI for fuzzy matching between the PDF rows and the template wording (the wording is ~99% identical).
-
Merge results and export to a new CSV.
This needs to run quarterly for 18 companies. PDFs contain both tables and text.
Excel sample
Index Company Year Quarter Place Place2 To fill Segment Sub_Segment Variable Value
15 Clal 2025 Q1 מאזן מאוחד Yes ראשי סך הכל נכסים בלתי מוחשיים ומוניטין
20 Clal 2025 Q1 מאזן מאוחד Yes ראשי סך הכל סה’'כ נכסים
40 Clal 2025 Q1 מאזן מאוחד Yes ראשי סך הכל סך הכל הון המיוחס לבעלי המניות של החברה
Can someone write me how the flow should be created ?
i have created few flows without success so i would like to start from scratch
Thank you for your help
