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

171–177 of 177 posts

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

#171

Post by sebstefan »

is_true wrote: post #124
sebstefan wrote: post #119

Earlier quoted context omitted.

The LLM is resistant to website updates that would break normal scraping If you do like the author did and ask it to generate xPaths, you can use it once, use the xPaths it generated for regular scraping, then once it breaks fall back to the LLM to update the xPaths and fall back one more time to alerting a human if the data doesn't start flowing again, or if something breaks further down the pipeline because the dat…

Xpath can be based on content, not only positions

I normally use query selectors for scraping, I'm not sure if that'd work better.

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

#172

Post by iudqnolq »

zulko wrote: post #106

Same experience here. Been building a classical music database [1] where historical and composer life events are scraped off wikipedia by asking ChatGPT to extract lists of `[{event, year, location}, ...]` from biographies. - Using chatgpt-mini was the only cheap option, worked well (although I have a feeling it's dumbing down these days) and made it virtually free. - Just extracting the webpage text from HTML, with…

This doesn't directly address your issue but since this caused me some pain I'll share that if you want to parse structured information from Wikipedia infoboxes the npm module wtf_wikipedia works.

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

#173

Post by sharpshadow »

peab wrote: post #151
jumploops wrote: post #77

Earlier quoted context omitted.

This is super neat and I think I've seen your site before :) Do you handle authentication? We have lots of users that want to automate some part of their daily workflow but the pages are often behind a login and/or require a few clicks to reach the desired content. Happy to chat: username@gmail.com

I'm also curious about this! I've been learning about scraping, but I've had a hard time finding good info about how to deal with user auth effectively.

You login and grab the session and save it. Then you mount the session to the requests.

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

#174

Post by nickpsecurity »

defgeneric wrote: post #157
nickpsecurity wrote: post #150

Earlier quoted context omitted.

That’s what I’ve done for quite a few [non-LLM] applications. The remaining problem is that HTML is verbose vs other formats. That has a higher, per-token cost. So, maybe stripping followed by substituting HTML tags with a compressed notation.

I've tried this and found it doesn't make much difference. The idea was to somehow preserve the document structure while reducing the token count, so you do things like strip all styles, etc. until you have something like a structure of divs, then reduce that. But I found no performance gain in terms of output. It seems whatever structure of the document is left over after doing the reduction has little semantic mean…

That’s interesting that it didn’t change the performance. It might still reduce cost (CPU vs GPU’s) when pages have a lot of formatting.

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

#175

Post by natpalmer1776 »

retrofuturism wrote: post #142
spyder wrote: post #113

Earlier quoted context omitted.

That's not literally his e-mail :D. He means that you have to replace it with his HN username. It would have been better to write it like this: [HN username]@gmail.com

Hahaha okay I feel dumb now.

Well if you're dumb then we're dumb.

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

#176

Post by maeil »

pkiv wrote: post #59
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-…

Am I correct that the use case of doing this is 1. Scale and 2. Defeating Cloudflare et. al?

I do scraping, but I struggle to see what these tools are offering, but maybe I'm just not the target audience. If the websites don't have much anti-scraping protection to speak of, and I only do a few pages per day, is there still something I can get out of using a tool like Browserbase? I wonder because of this talk about semantic markdown and LLMs, what's the benefit between writing (or even having an AI write) standard fetching and parsing code using playwright/beautifulsoup/cheerio?

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

#177

Post by Opocio »

axg11 wrote: post #39
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…

I wrote an in-house one for Ribbon. If there’s interest, will open source this. It’s amazing how much better our LLM outputs are with the reducer.

+1
Post reply on HN