GPT Scraper
Pay $9.00 for 1,000 pages
GPT Scraper
Pay $9.00 for 1,000 pages
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 demoNot able to integrate with other actor
Closed
When trying to integrate, using a placeholder to feed urls into gpt, it's not working. Would it be possible to see an example?
Hi, thanks for opening this issue!
Can you please explain the issue more in-depth? What do you mean by "placeholder to feed urls into gpt? Where are the URLs coming from, and where do you want to pass them to?
jen_brown_done
I'm trying to follow this tutorial to send a set of scraped urls to gpt scraper, it mentions resource.defaultdatasetid, but I'm unsure of where to input that when integrating with the gpt scraper https://blog.apify.com/connecting-scrapers-apify-integration/
Right I see, yes that is the regular way to go about Actor2Actor integrations. Unfortunately we do not want to pollute the input schema of this Actor with this field and the dataset also has to be in the correct format.
A much easier solution would be to simply use the Forward Dataset to Actor or Task utility Actor. Basically you will use that one for the integration and it will call GPT scraper inside of it. Use this input to send the URLs over to this scraper:
1{ 2 "datasetFieldName": {YOUR_URL_FIELD_NAME}, 3 "datasetId": {{resource.defaultDatasetId}}, 4 "format": "requestListSources", 5 "inputOverride": { 6 {YOUR_INPUT_FOR_GPT_SCRAPER_WITHOUT_START_URLS} 7 }, 8 "targetFieldName": "startUrls", 9 "targetId": "paOtbjvyUiNsr1Qms", 10 "targetType": "ACTOR" 11}
And that's it, just input in your stuff for the placeholder variables and it should work :)
Let me know if this helps, thanks and happy scraping!
Jakub DrobníkActor Metrics
155 monthly users
-
64 stars
>99% runs succeeded
2 days response time
Created in Mar 2023
Modified 4 days ago
