![Extended GPT Scraper avatar](https://images.apifyusercontent.com/yvDCOx1KzXbr3a9g6iCsA-YslD3CeAhEUP2qNFs5bN0/rs:fill:250:250/aHR0cHM6Ly9hcGlmeS1pbWFnZS11cGxvYWRzLXByb2QuczMudXMtZWFzdC0xLmFtYXpvbmF3cy5jb20vYUFhRG5HWmdOd0htNG16Y2wvcVRMaGkyeE5oMEE3Yzk1MkEtR1BUX1NjcmFwZXJfZXh0ZW5kZWRfJTI4MSUyOS5wbmc.webp)
No credit card required
![Extended GPT Scraper](https://images.apifyusercontent.com/yvDCOx1KzXbr3a9g6iCsA-YslD3CeAhEUP2qNFs5bN0/rs:fill:250:250/aHR0cHM6Ly9hcGlmeS1pbWFnZS11cGxvYWRzLXByb2QuczMudXMtZWFzdC0xLmFtYXpvbmF3cy5jb20vYUFhRG5HWmdOd0htNG16Y2wvcVRMaGkyeE5oMEE3Yzk1MkEtR1BUX1NjcmFwZXJfZXh0ZW5kZWRfJTI4MSUyOS5wbmc.webp)
Extended GPT Scraper
No credit card required
Extract data from any website and feed it into GPT via the OpenAI API. Use ChatGPT to proofread content, analyze sentiment, summarize reviews, extract contact details, and much more.
Do you want to learn more about this Actor?
Get a demo4o mini model (for cost concern)
Closed
Hi, since website scraping involved large input token and out token, any plans to add model 4o mini soon? Many thanks
![lukas.prusa avatar](https://apify-image-uploads-prod.s3.amazonaws.com/KNRBu8ZQbXJs57TCd/gMDJPyh4HJ53yis3n-rsz_1lukas_about_small.jpg)
Hi Tak, thanks opening this issue and your suggestion!
Yes, we will 100% add the 4o-mini model shortly :) We will also most likely add it to our Pay Per Result version of this Actor.
I will keep you updated here, thanks!
![lukas.prusa avatar](https://apify-image-uploads-prod.s3.amazonaws.com/KNRBu8ZQbXJs57TCd/gMDJPyh4HJ53yis3n-rsz_1lukas_about_small.jpg)
Hi again, thanks for your patience!
We've had some other issues with the scraper, so we kept in the beta for a bit too long now. The 4o-mini
model is accessible on the latest (default) version :) We've also set it as the default one for the Pay Per Result Actor version.
Try it out and let me know how it works, thanks!
tak_lai
Thanks , I will try it. Really appreciate your effort
tak_lai
Hello , I just spotted another issue, which may relate to playwright. I tried to use playwright and selenium to scrape https://www.newbalance.com/pd/made-in-usa-990v6/U990V6-45189.html I am not sure why it is failed when using playwright. Since Extended GPT Scraper use playwright so it shared same result(retrieve blank page). It works using selenium in my local but failed to use playwright in my local. I just want to share this limitation as it is not the problem on this actor. I am truly thankful of your effort on this actor
![lukas.prusa avatar](https://apify-image-uploads-prod.s3.amazonaws.com/KNRBu8ZQbXJs57TCd/gMDJPyh4HJ53yis3n-rsz_1lukas_about_small.jpg)
Hi, thanks for sharing this inside. This looks to be some issue in playwright, or at least it's getting detected and blocked by the website.
I've tried a few settings like residential proxies and waiting longer for the dynamic content to load, but I guess it's still getting blocked... This looks a bit out of our scope as this is most likely an issue somewhere else, so unfortunately we won't be fixing this. But good luck with the website and I hope you will be able to scrape it well with selenium :)
- 75 monthly users
- 26 stars
- 99.2% runs succeeded
- 7.6 days response time
- Created in Jun 2023
- Modified 24 days ago