This is an AI project and is set out briefly as follows:
I am wanting someone who could help me extract (mining/scraping) case law decisions from publicly available UK sources/websites (up to 5 websites). The data that I am looking is usually stored in the backend of websites and require the user to enter search criteria and parameters like name, date and keywords.
I need someone who can build a web scraping solutions, including for websites that require navigating search parameters (name, date, keywords etc), handling session tokens, bypassing specific input criteria and interacting with JavaScript-heavy interfaces.
I don’t need the personal data of any individuals referred to in the data, I only want the decisions and reasons for the decisions.
In the near future my chosen LLM will be trained on this data, and a web based AI solution will be offered to the public.
The ideal candidate should have a proven track record in web scraper development and be able to navigate complex web structures to accurately output the required data in a structured format. Attention to detail and strong problem-solving skills are essential.
This is a very specialised piece of work so please do not offer your services if you are not an expert.
IN YOUR RESPONSE PLEASE PROVIDE EXAMPLES OF YOUR WORK AND SET OUT HOW YOU WOULD ACHIEVE THE PROJECT GOALS. IF YOU CANNOT PROVIDE THIS INFORMATION YOUR PROPOSAL WILL BE DECLINED.
