GPT Browser

🌐 GPT Browser 💬

GPT Browser is a powerful tool that leverages OpenAI's API to modify text obtained from a browser. You can use the browser to extract content from a website and then pass that content to the OpenAI API to make the GPT magic happen.

🔍 How does GPT Browser work?

The Actor first loads the page using Playwright, then it converts the content into markdown format and asks for GPT instructions about markdown content.

The Actor first removes hidden html content and other Html tags in order to minimize your OpenAI cost. Note that if the content doesn't fit into the GPT limit, the browser will truncate the content.

💰 How much does it cost?

To let you control the cost, we ask for your OpenAI API key and only charge a small monthly fee. This way you can browse a large maount for the same price ! Free Apify account gives you $5 each month, so you can already get hundreds of answers for free.

📐 How to use GPT Browser

• Add your OpenAI API Key
• Add page URLs (or uplad a file, like CSV) that the browser will visit
• Prompt instructions on how the GTP browser should handle each page

You can configure the browser and GPT using Input configuration to set up a more complex workflow.

Instructions and prompts for GPT

Tells GPT how to handle your page content. For example, send the prompt:

• "Summarize this website in less than 10 words."
• "Find sentences that contain 'pricing' and return them as a list."
• "Find the logo URL of this website. If the page is about food, answer with 'skip this page'.".

👀 Examples

Here are some example use cases you can use for your own GPT browsing experiments.

Summarize a wiki page

• https://en.wikipedia.org/wiki/COVID-19_pandemic
• "What is this covid thing I read in the newspaper from last century ?"

Results:

🔗 URL	👨 Screenshot	📝 Answer
https://en.wikipedia.org/wiki/COVID-19_pandemic		"The COVID-19 pandemic refers to a global outbreak of coronavirus disease caused by the severe acute respiratory [...]"

Summarize reviews of movies, games, or products

• https://www.imdb.com/title/tt10366206/reviews
• "Summarize reviews for this John Wick movie"

🔗 URL	👨 Screenshot	📝 Answer
https://www.imdb.com/title/tt10366206/reviews		"John Wick 4 has received a mix of enthusiastic accolades and critical remarks from viewers, reflecting its polarized reception [...]"

Other suggested use cases

• Find typos and grammatical errors across on a page
• Analyze competing content to find keywords or ideas
• Examine code examples in content to find errors or suggest improvements

🥢 Other Actors I should use ?

I developped a couple of Actors. Take a look guillim's actors or my portfolio. My focus is Linkedin, since it is "login protected", and many users need to access its information.

Scraping LinkedIn with GPT

• If you have a few LinkedIn people url, that you want to filter out using a ChatGPT prompt: LinkedIn x GPT

Scraping LinkedIn, big amount of pages

When you need to gather data, like more 50 records per day, it's recommended to avoid using your Linkedin cookies. You will need the following actors :

• Looking for many LinkedIn company url: Mass company finder
• Looking for many LinkedIn people url: Mass people finder
• You have many LinkedIn people url, now looking for their information like job, description, skills... : Mass profile scrapper