[Subtask]: Remove PII / Anonymize Email

[lnovitz]

Is there a pain point in the app driving this feature request?

The content being parsed by LLM should be anonymized, no PII (no first last name, no email addresses, no LinkedIn urls) to protect users and also increase the reliability of model responses

Desired Behavior

Given a response from the Gmail API for a specific message ID, create a function to be able to anonymize the message

Add unit test(s)

Criteria for Completion

• Create a Python function that takes in email text and returns the anonymized version
• Apply this function to the email text before the LLM call
• Add unit test(s)

[lnovitz]

https://github.com/lnovitz/jobseeker-analytics/pull/323/files#diff-f879557b2b3aa1f4dda4142f5013226bad4f19149a05e13eba641e473430621e for starter code - it's a bit messy can be cleaned up. basically just want to remove HTML tags and remove personal info

[lnovitz]

#323 can push to this branch csc301-2025-s:email-status-extraction

[lnovitz]

🎥 https://discord.com/channels/1330717169335406756/1343326958997471364/1357002789540331681