python3 https://www.python.org

从官网下载安装或者用brew

$ brew linkapps python3
$ brew linkapps python3

pipenv https://github.com/pypa/pipenv

$ pip install pipenv

.zshrc

eval "$(pipenv --completion)"

request-html http://html.python-requests.org/en/latest/

$ git clone https://github.com/iOSDevLog/Machine-Learning-Crash-Course
$ cd Machine-Learning-Crash-Course
$ pipenv --python 3.6
$ pipenv install requests-html
$ pipenv shell     # To activate this project's virtualenv

fetch_course.py

#!/usr/bin/env python
import os
import ssl
import time

from requests_html import HTMLSession

ssl._create_default_https_context = ssl._create_unverified_context

base_url = 'https://developers.google.com/machine-learning/crash-course/'

def course_info(course_url):
    session = HTMLSession()
    request = session.get(course_url)

    data_video_url = ''
    data_captions_url = ''
    # video_info = request.html.find('.devsite-vplus', first=True)
    # data_video_url = video_info.attrs['data-video-url']
    # data_captions_url = video_info.attrs['data-captions-url']

    next_url_info = request.html.find('div.devsite-steps-next > a.devsite-steps-link', first=True)
    next_url = next_url_info.attrs['href']

    return (data_video_url, data_video_url, next_url)

import urllib.request

def getHtml(url):
    html = urllib.request.urlopen(url).read()
    return html

def saveHtml(file_name, file_content):
    dir = 'course_html/'
    file_name = file_name.replace('/','_')+'.html'
    path = os.path.join(dir, file_name)
    with open (path, 'wb') as f:
        f.write(file_content)

if __name__ == '__main__':
    next_url = 'https://developers.google.com/machine-learning/crash-course/framing/check-your-understanding'
    while next_url:
        try:
            (_, _, next_url) = course_info(next_url)
            filename = os.path.basename(next_url)
            html = getHtml(next_url)
            saveHtml(filename, html)
            print(next_url)
        except:
            time.sleep(5)
            print("Was a nice sleep, now let me continue...")
            continue

data_video_url 为mp4视频相对地址
data_captions_url 为字幕相对地址

通过 base_url 可得到绝对地址，后面再写吧。