1
import requests
2
import re
3
import os
4
from subprocess import call
5

6

7
def urls_iter(origin_url='http://v.163.com/special/opencourse/algorithms.html', begin_from=1):
8
    """
9
    *origin_url* is the origin download page of 163 OpenCourse, the default value is 'algorithms course from MIT'.
10
    *begin_from* can make the function jump to the No.*begin_from* item to start download.
11
    """
12
    download_request = requests.get(origin_url)
13

14
    course_list_pattern = re.compile(r'<table class="m-clist" id="list2".*?>(.*?)</table>', flags=re.DOTALL)
15
    course_pattern = re.compile(r'<tr class="(?:u-odd|u-even)">.*?</tr>', flags=re.DOTALL)
16
    course_text = course_list_pattern.search(download_request.text).group(1)
17
    course_list = course_pattern.findall(course_text)
18

19
    course_name_pattern = re.compile(r'<a href=.*?>(.*?)</a>', flags=re.DOTALL)
20
    course_video_pattern = re.compile(r'<a class="downbtn" href=[\'""](.*?)[\'""].*?>.*?</a>', flags=re.DOTALL)
21

22
    for index, course in enumerate(course_list, 1):
23
        if index < begin_from:
24
            continue
25

26
        index = '{:0>2}_'.format(index)
27
        video_title = index + course_name_pattern.search(course).group(1) + '.mp4'
28
        video_address = course_video_pattern.search(course).group(1)
29
        yield (video_title, video_address)
30

31

32
def download_course(download_list, download_dir='/Users/zealot/Downloads/algorithms'):
33
    """
34
    *download_list* is a collection contains a list of tuple whose 1st element is the filename of the video,
35
        and 2nd element is the download url of the video.
36
    *download_dir* defines the directory where the files should be stored in.
37

38
    function using common download tool `wget` to fetch videos one at a time.
39
    raise error if `wget` not found.
40
    """
41
    with open('/dev/null') as black_hole:
42
        if call(['which', 'wget'], stdout=black_hole):
43
            raise OSError('command not found: wget')
44

45
    if not os.path.exists(download_dir):
46
        os.makedirs(download_dir)
47

48
    for video_title, video_address in download_list:
49
        call(['wget', '-c', video_address, '-O', os.path.join(download_dir, video_title)])
50

51
if __name__ == '__main__':
52
    download_course(urls_iter())

1
if __name__ == '__main__':
2
    download_course(urls_iter('http://v.163.com/special/opencourse/fouriertransforms.html'),
3
                    '/Users/zealot/downloads/fouriertransforms')