Re:I'm Betting on HTML
by kennyloginz on Wednesday August 02, 2023 @02:21AM
(#36967620)
You don’t need a good old Python script using Beautiful soup, you can use an LLM with the added benefit of not dealing with that cruft.
[ Parent
| on HN ]
Re:I'm Betting on HTML
by selfhoster11 on Wednesday August 02, 2023 @02:50AM
(#36967814)
An LLM is much slower and requires more resources at runtime than Beautiful Soup (if you are hosting yourself), and could fail to retrieve data. It's a worse solution unless your HTML parser/scraper is broken by website changes.
This is only the case for now, however. I expect this to change in favour of LLMs as time goes on and they become easier to deploy and better at their job.