Web scraping with GPT-4o: powerful but expensive • Hacker News Board

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

#71

Post by hubraumhugo » Tue, Sep 03, 2024, 4:47 AM UTC

We've been working on AI-automated web scraping at Kadoa[0] and our early experiments were similar to the those in the article. We started when only the expensive and slow GPT-3 was available, which pushed us to develop a cost-effective solution at scale.

Here is what we ended up with:

- Extraction: We use codegen to generate CSS selectors or XPath extraction code. This is more efficient than using LLMs for every data extraction. Using an LLM for every data extraction, would be expensive and slow, but using LLMs to generate the scraper code and subsequently adapt it to website modifications is highly efficient.

- Cleansing & transformation: We use small fine-tuned LLMs to clean and map data into the desired format.

- Validation: Unstructured data is a pain to validate. Among traditional data validation methods like reverse search, we use LLM-as-a-judge to evaluate the data quality.

We quickly realized that doing this for a few data sources with low complexity is one thing, doing it for thousands of websites in a reliable, scalable, and cost-efficient way is a whole different beast.

Combining traditional ETL engineering methods with small, well-evaluated LLM steps was the way to go for us

[0] https://kadoa.com

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

#72

Post by mfrye0 » Tue, Sep 03, 2024, 4:49 AM UTC

As others have mentioned, converting html to markdown works pretty well.

With that said, we've noticed that for some sites that have nested lists or tables, we get better results by reducing those elements to a simplified html instead of markdown. Essentially providing context when the structures start and stop.

It's also been helpful for chunking docs, to ensure that lists / tables aren't broken apart in different chunks.

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

#73

Post by houseplant » Tue, Sep 03, 2024, 4:51 AM UTC

bangaladore wrote: post #32

dghlsakjg wrote: post #26

Earlier quoted context omitted.

Instagram really doesn’t want you scraping. There are almost certainly terms against it in the user agreement

Companies like Instagram (Facebook/Meta/Garbage) abuse their users' data day in and day out. Who cares what their TOS says. Let them spend millions of dollars trying to block you, its a drop in the bucket.

instead, don't do it because it's disrespectful to people. A lot of people weren't made aware- or didn't have the option- to object to that TOS change. Saying "well, THOSE guys do it! why can't I!" isn't a mature stance. Don't take their images because it's the right thing to do

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

#74

Post by snthpy » Tue, Sep 03, 2024, 5:19 AM UTC

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…

Thank you for these.

I've been wanting to try the same approach and have been looking for the right tools.

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

#75

Post by tuktuktuk » Tue, Sep 03, 2024, 5:31 AM UTC

Can you share how long it took for you to parse the HTML? I recently experimented with comparing different AI models, including GPT-4o, alongside Gemini and Claude to parse raw HTML: https://serpapi.com/blog/web-scraping-with-ai-parsing-html-t.... Result is pretty interesting.

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

#76

Post by sunshadow » Tue, Sep 03, 2024, 5:39 AM UTC

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-…

I don't see any difference than browserless?

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

#77

Post by jumploops » Tue, Sep 03, 2024, 5:40 AM UTC

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-…

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

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

#78

Post by jumploops » Tue, Sep 03, 2024, 5:42 AM UTC

neeleshs wrote: post #61

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…

We did something similar -na although in a somewhat different context. Translating a complex JSON representing an execution graph to a simpler graphviz dot format first and then feeding it to an LLM. We had decent success.

Yes, just like with humans, if you simplify the context, it's often much easier to get the desired result.

Source: I have a toddler at home.

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

#79

Post by pkiv » Tue, Sep 03, 2024, 5:45 AM UTC

sunshadow wrote: post #76

pkiv wrote: post #59

Earlier quoted context omitted.

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-…

I don't see any difference than browserless?

The price and the dashboard are a great start :)

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

#80

Post by naiv » Tue, Sep 03, 2024, 6:19 AM UTC

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-…

Awesome product!

I was just a bit confused that the sign up buttons for the Hobby and Scale plans are grey, I thought that they are disabled until randomly hovering over them.