The webpage URL
Workbook link : https://www.gumloop.com/pipeline?workbook_id=ajAVgEdDqaT2xX3ThHWpA4
- Mention that you’ve tried:
- Error Shields on both nodes
- Advanced scraping enabled
- Comprehensive schema
- Detailed additional context
- Note that it’s only capturing a few conferences instead of the full list
Hey @Garbanzo - For large list extractions like this I’d recommend using the Extract Data node and then connecting the output to a Google Sheet Writer node.
The Extract Data node allows you to switch between models and add specific data descriptions which is more reliable for large extractions.
Remember to enable Extract List in the node.
Let me know if this works for you.
Thanks for your reply but as a newbie I don’t know where to connect it. Do I replace the webscrapper and also how do I get the data into the table. Can you give me Gummie like instructions. Thanks for your help
Yeah for sure. Here’s a guided tutorial that explains the data extraction flow using the Extract Data & Google Sheet writer nodes.
https://www.gumloop.com/pipeline?workbook_id=dthCiSMZQ4XSfKe5CtHNBX&tutorial=true&guided_tutorial_id=web_scraping
Let me know if anything is confusing at all.