A project to create a valid area code database and library. Focused not on using regex but actual data that can be updated periodically.
Currently United States of America Only
Using serenium and having gpt-3.5-turbo parse the website's html, create a JSON that would have the needed valid area code information. This included if it is in use, the location and the country.
Area Code search is defined by range of the North American Numbering Plan and is done through NANPA
LLM is not really required as could just parse through the website date but was done as an experiment. If the website layout from NANPA were to change, the build_areacodes.py wouldn't break if not tied to a certain layout but parsed by an LLM. Will try to add an LLM free option.
The way serenium is being used now might not work on other sites with more security. The NANPA search seems like an old JSP application that doesn't mind it.
Coming Soon