jina-ai / reader

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

Home Page:https://jina.ai/reader

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Not pulling image links correctly

AndyMik90 opened this issue · comments

commented

Testing jina on our norwegian websites, we see that the images are not pulled correctly:

example URL: https://mikalsenutvikling.no/
Jina URL: https://r.jina.ai/https://mikalsenutvikling.no

First image on the website by Jina is given as ![Image 1: Daglig Leder - André mikalsen](data:image/svg+xml,%3Csvg%20xmlns='http://www.w3.org/2000/svg'%20viewBox='0%200%201200%201307'%3E%3C/svg%3E)

But in the HTML you can clearly see there is a src image with .png that should be the URL given in the Jina reader version:

src="https://mikalsenutvikling.no/wp-content/uploads/2022/11/Andre-Mikalsen-optimalisert.png

This has been the same on all sites we have tested.

having the same exact problem,
any solution?