Get the table of content for a Coursera course

course_table_of_content.py

import requests
from bs4 import BeautifulSoup


if __name__ == '__main__':
    req = requests.get("https://www.coursera.org/learn/dsp4?specialization=digital-signal-processing")
    bs = BeautifulSoup(req.text)
    tags = bs.find_all(lambda tag: tag.name == 'h3' or (tag.has_attr('data-test-id') and tag['data-test-id'] == 'item-view'))
    for t in tags:
        try:
            print(t.findAll(string=True, recursive=False)[0])
        except Exception:
            pass