Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Web scraping with GPT-4o: powerful but expensive

blancas.io

Post reply on HN
Print view View original

51–60 of 177 posts

Re: Web scraping with GPT-4o: powerful but expensive

#51

Post by 7thpower »

edublancas wrote: post #35
parhamn wrote: post #31

Is there a "html reducer" out there? I've been considering writing one. If you take a page's source it's going to be 90% garbage tokens -- random JS, ads, unnecessary properties, aggressive nesting for layout rendering, etc. I feel like if you used a dom parser to walk and only keep nodes with text, the html structure and the necessary tag properties (class/id only maybe?) you'd have significant savings. Perhaps the…

author here: I'm working on a follow-up post. Turns out, removing all HTML tags works great and reduces the cost by a huge margin.

What do you mean? What do you use as reference points?

Re: Web scraping with GPT-4o: powerful but expensive

#53

Post by mjrbds »

We've had lots of success with this at Rastro.sh - but the biggest unlock came when we used this as benchmark data to build scraping code. Sonnet 3.5 is able to do this. It reduced our cost and improved accuracy for our use case (extracting e-commerce products), as some of these models are not reliable to extract lists of 50+ items.

Re: Web scraping with GPT-4o: powerful but expensive

#56

Post by asaddhamani »

Tostino wrote: post #30
tom1337 wrote: post #11

OpenAI recently announced a Batch API [1] which allows you to prepare all prompts and then run them as a batch. This reduces costs as its just 50% the price. Used it a lot with GPT-4o mini in the past and was able to prompt 3000 Items in less than 5min. Could be great for non-realtime applications. [1] https://platform.openai.com/docs/guides/batch

I hope some of the opensource inference servers start supporting that endpoint soon. I know vLLM has added some "offline batch mode" support with the same format, they just haven't gotten around to implementing it on the OpenAI endpoint yet.

Do note it can take up to 24 hours or drop requests altogether. But if that’s not an issue for your use case it’s a great cost saving.

Re: Web scraping with GPT-4o: powerful but expensive

#57

Post by edublancas »

7thpower wrote: post #51
edublancas wrote: post #35

Earlier quoted context omitted.

author here: I'm working on a follow-up post. Turns out, removing all HTML tags works great and reduces the cost by a huge margin.

What do you mean? What do you use as reference points?

nothing, I strip out all the HTML tags and pass raw text

Re: Web scraping with GPT-4o: powerful but expensive

#58

Post by jumploops »

asaddhamani wrote: post #56
Tostino wrote: post #30

Earlier quoted context omitted.

I hope some of the opensource inference servers start supporting that endpoint soon. I know vLLM has added some "offline batch mode" support with the same format, they just haven't gotten around to implementing it on the OpenAI endpoint yet.

Do note it can take up to 24 hours or drop requests altogether. But if that’s not an issue for your use case it’s a great cost saving.

This is neat, I’ve been looking for a way to run our analytics (LLM-based) without affecting the rate limits of our prod app.

May need to give this a try!

Re: Web scraping with GPT-4o: powerful but expensive

#59

Post by pkiv »

jumploops wrote: post #41

We've had the best success by first converting the HTML to a simpler format (i.e. markdown) before passing it to the LLM. There are a few ways to do this that we've tried, namely Extractus[0] and dom-to-semantic-markdown[1]. Internally we use Apify[2] and Firecrawl[3] for Magic Loops[4] that run in the cloud, both of which have options for simplifying pages built-in, but for our Chrome Extension we use dom-to-semanti…

If you're open to it, I'd love to hear what you think of what we're building at https://browserbase.com/ - you can run a chrome extension on a headless browser so you can do the semantic markdown within the browser, before pulling anything off.

We even have an iFrame-able live view of the browser, so your users can get real-time feedback on the XPaths they're generating: https://docs.browserbase.com/features/session-live-view#give...

Happy to answer any questions!

Re: Web scraping with GPT-4o: powerful but expensive

#60

Post by danpalmer »

fvdessen wrote: post #28

This looks super useful, but from what i've heard, if you try to do this at any meaningful scale your scrapers will be blocked by Cloudflare and the likes

I used to do a lot of web scraping. Cloudflare is an issue, as are a few Cloudflare competitors, but scraping can still be useful. We had contracts with companies we scraped that allowed us to scrape their sites, specifically so that they didn't need to do any integration work to partner with us. The most anyone had to do on the company side was allowlist us with Cloudflare.

Would recommend web scraping as a "growth hack" in that way, we got a lot of partnerships that we wouldn't otherwise have got.

Post reply on HN