Okay, this is probably one step too far. I’m almost afraid to ask, but you never know. So here we go…
I scrape concert venues. For each concert I need (i) all webpage text, and (ii) the url of the page and (iii) the url of the concert image. Would it be possible to build a scraper that would work on all music concert sites (rather than a scraper for each site individually)?
(i) and (ii) should probably be doable, but how to do (iii)?
I have built list scrapers for most important venues separately. But would be great if i would be able to scrape a concert venue site if there is just one interesting concert to scrape (scrape active tab), without having to first build a scraper for that site specifically.
This sounds like a task for AI. Did you have a chance to try our “Execute actions in the background”? It allows you to instruct an AI agent to visit a page and extract necessary information, please see:
It may take longer to process a page, but ideally you don’t have to build a website specific scraper.
oh wow that looks amazing. I’ll start playing around with it, see if i can get it to work. Thanks for pointing this out. Ill have more than one use case for this action.
–Bob
