get_courses.py

import requests

# max_records is there so you can get back partial result sets, if you want. Useful for testing.
def get_all_course_data(max_records=None): 
    page_number = 1
    page_size = 100
    more_records_exist = True
    all_courses = []

    while more_records_exist:
        api_response = get_courses(page_number, page_size)
        results = process_response(api_response)

        # add the new results to our aggregate set
        all_courses += results
    
        # if we get back fewer records than we asked for, we know we reached the end.
        # terminate the loop if we're at the end, or have hit our max.
        if len(results) < page_size or (max_records and len(all_courses) >= max_records):
            more_records_exist = False
        else:
            page_number += 1

    return all_courses

def get_courses(page_number, page_size): 
    courses_url = "https://www.udemy.com/api-2.0/courses/"

    query_params = {
        "page_size": page_size, 
        "page": page_number 
    }

    credentials = ('username', 'password')

    return requests.get(url=courses_url, auth=credentials, params=query_params).json()

def process_response(api_response):
    # api_response is a dictionary object which is a representation of the json structure.  
    courses = []

    # The json structure places all of the courses inside the results array
    for course in api_response['results']:
        # we add to the courses list tuples containing id, price, and headline.
        courses.append((course['id'], course['price'], course['headline']))

    return courses