1

Is there a way to extract questions and answers from Stack Overflow that share the same tag(s) into any of the following formats: .tsv, .pdf, .doc, .docx, .xlsx, containing questions and answers in sequence (for the purpose of populating a knowledge base using QnA Maker)?

I am creating a chat bot using Bot Framework, and would like to populate the knowledge base using QnA maker with question-answer pairs with the same tag from the Stack Overflow website. I was wondering if Stack Overflow had a feature hidden away somewhere that would allow me to extract said information.

Before I attempt to code something up that will extract this information manually, I want to make sure I am not completely overlooking functionality that may already exist. Since my Stack Overflow reputation is low, I am unable to post this on meta (thus the inappopriate tagging).

Vadim Kotov
  • 8,084
  • 8
  • 48
  • 62
Jung
  • 13
  • 3
  • 1
    I made it a comment since StackOverflow disapproves of answers without code examples since links aren't static. However, in this case, I think it's sufficient - it's not too difficult to Google "StackOverflow API" if the link changes. Thanks for the suggestion. – tdurnford Jul 11 '19 at 04:46

1 Answers1

2

I would recommend looking at the StackOverflow Question API. You can make a get request for issues that have certain tags and then write them to a CSV file or use the QnA Maker API to create your knowledge base from the resulting data.

tdurnford
  • 3,632
  • 2
  • 6
  • 15