fork download
copy 
  1. #!/usr/bin/env python
  2. # Developed with pyton 2.7
  3. # Copyright 2012 Logan Ding <logan.ding@gmail.com>. All Rights Reserved.
  4. #
  5. #---------------------------------------------                             
  6. #    Coursera.org Downloader <Version 1.1>   
  7. #          by Logan Ding                                      
  8. #---------------------------------------------
  9. #
  10. # Dependent on 'mechanize'. Use 'easy_install mechanize' first if 'mechanize' not installed.
  11. # Be sure to change the email and the password in main() to yours first before running.
  12. #
  13. # Run as: 'python coursera_downloader.py' will download to CWD.
  14. # Run as: 'python coursera_downloader.py <dir>' will download to path <dir>.
  15. #
  16. # Only support single thread to download right now.
  17. # Add courses by yourself. Not all tested. You can feed back.
  18. # Download videos, subtitles, PDF and PPT(X) slides.
  19. # Has problem to resolve subtitles for 'modelthinking'. Ignored...now.
  20.  
  21. import cookielib, re, sys, os
  22. try:
  23.     import mechanize
  24. except ImportError, e:
  25.     print e
  26.     print 'You must install "mechanize" first. Can use "easy_install": easy_install mechanize'
  27.     sys.exit(1)
  28.  
  29. def split_string(source,splitlist):
  30.     if source == '':
  31.         return [source]
  32.     result = []
  33.     tmp = ''
  34.     for c in source:
  35.         if c not in splitlist:
  36.             tmp += c
  37.         else:
  38.             if tmp != '':
  39.                 result.append(tmp)
  40.             tmp = ''
  41.     if tmp != '':
  42.         result.append(tmp)
  43.     return result      
  44.  
  45. def resolve_name_with_hex(name):
  46.     r = re.finditer(r'%\w\w', name)
  47.     for m in r:
  48.         c = m.group()[1:].decode('hex') 
  49.         c = c if c not in '\/:*?"<>|' else '_'
  50.         name = re.sub(m.group(), c, name)
  51.     return name
  52.  
  53. def resolve_name_with_illegal_char(name):
  54.     return re.sub(r'[\\/:*?"<>|]', ' -', name)
  55.  
  56. def initialize_browser(course, email, password):
  57.     #Use mechanize to handle cookie
  58.     print
  59.     print 'Initialize browsering session...'
  60.     br = mechanize.Browser()
  61.     cj = cookielib.LWPCookieJar()
  62.     br.set_cookiejar(cj)
  63.     br.set_handle_equiv(True)
  64.     #br.set_handle_gzip(True)
  65.     br.set_handle_redirect(True)
  66.     br.set_handle_referer(True)
  67.     br.set_handle_robots(False)
  68.     br.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(), max_time = 0)
  69.     auth_url = 'https://c...content-available-to-author-only...a.org/****/auth/auth_redirector?type=login&subtype=normal&email'.replace('****', course)
  70.     br.open(auth_url)
  71.  
  72.     br.select_form(nr = 0)
  73.     br.form['email'] =  email
  74.     br.form['password'] = password
  75.     br.submit()
  76.     print 'It takes seconds to login and resolve resources to download...\n'
  77.  
  78.     #Check if email + password submitted correctly
  79.     if 'https://c...content-available-to-author-only...a.org/****/auth/login_receiver?data='.replace('****', course) not in br.geturl():
  80.         print 'Failed to login, exit...'
  81.         sys.exit(1)
  82.  
  83.     video_lectures = 'https://c...content-available-to-author-only...a.org/****/lecture/index'.replace('****', course)
  84.     br.open(video_lectures)
  85.     return br
  86.  
  87. def resolve_resources(br, path, course):
  88.     title       = []
  89.     pdf         = []
  90.     pptx        = []
  91.     link_txt    = []
  92.     link_srt    = []
  93.     link_video  = []
  94.  
  95.     for l in br.links():
  96.         m_title = re.search(r'text=[\'\"](.+)[\'\"], tag=\'a\', .+\'class\', \'lecture-link\'', str(l))
  97.         m_pdf = re.search(r'https*:[\S]+/([\S]+\.pdf)', str(l))
  98.         m_pptx = re.search(r'https*:[\S]+/([\S]+\.pptx*)', str(l))
  99.         m_txt = re.search(r'url=\'(https:[\S]+subtitles\?[\S]+=txt)', str(l))
  100.         m_srt = re.search(r'url=\'(https:[\S]+subtitles\?[\S]+=srt)', str(l))
  101.         m_video = re.search(r'https:[\S]+download.mp4[\S]+\'', str(l))
  102.  
  103.         if m_title:
  104.             title.append(resolve_name_with_illegal_char(m_title.group(1).strip()))
  105.         if m_pdf:
  106.             pdf.append([resolve_name_with_hex(m_pdf.group(1)), m_pdf.group()])
  107.         if m_pptx:
  108.             pptx.append([resolve_name_with_hex(m_pptx.group(1)), m_pptx.group()])
  109.         if m_txt:
  110.             link_txt.append(m_txt.group(1))
  111.         if m_srt:
  112.             link_srt.append(m_srt.group(1))
  113.         if m_video:
  114.             link_video.append(m_video.group().rstrip("'"))
  115.  
  116.     if len(title) == len(link_video):
  117.         video = zip([t+'.mp4' for t in title], link_video)
  118.     else:
  119.         print 'Video names resolving error. Ignore videos...'
  120.         video = []
  121.     # Here is a buggy way to handle different numbers of videos and subtitles for 'modelthinking' and 'saas'.
  122.     # To completely solve the problem, need to change the links resolve and match method completely.
  123.     # Will fix this if have time. Right now, this inelegant way can handle 'saas' only.
  124.     if len(title) == len(link_srt):
  125.         srt = zip([t+'.srt' for t in title], link_srt)
  126.     elif course == 'saas':
  127.         srt = zip([t+'.srt' for t in title[len(title)-len(link_srt) : ]], link_srt)
  128.     else:
  129.         print 'Can NOT match video names with subtitiles. Ignore...'
  130.         srt = []
  131.  
  132.     if len(title) == len(link_txt):
  133.         txt = zip([t+'.txt' for t in title], link_txt)
  134.     elif course == 'saas':
  135.         txt = zip([t+'.txt' for t in title[len(title)-len(link_txt) : ]], link_txt)
  136.     else:
  137.         print 'Can NOT match video names with subtitiles. Ignore...'
  138.         txt = []
  139.     return video, srt, txt, pdf, pptx
  140.  
  141. def downloader(video, srt, txt, pdf, pptx, br, path):
  142.     # Only single download thread supported right now.
  143.     print
  144.     print 'Videos can be downloaded:'
  145.     v = choose_download(video)
  146.     print 'srt subtitles can be downloaded:'
  147.     s = choose_download(srt)
  148.     print 'txt subtitles can be downloaded:'
  149.     t = choose_download(txt)
  150.     print 'PDF slides can be downloaded:'
  151.     f = choose_download(pdf)
  152.     print 'PPT slides can be downloaded:'
  153.     x = choose_download(pptx)
  154.  
  155.     # Combine all to be downloaded together for multiple downloading threads later
  156.     all = v + s + t + f + x 
  157.     for r in all:
  158.         filename = os.path.join(path, r[0])
  159.         print 'Downloading', r[0]
  160.         br.retrieve(r[1], filename)
  161.  
  162. def choose_course(course):
  163.     for key in sorted(course.keys()):
  164.         print key, ':', course[key]
  165.     choice = raw_input('Please choose course by number: ')
  166.     while choice not in course.keys():
  167.         choice = raw_input('Invalid choice, input again or Enter to quit: ')
  168.         if choice == '':
  169.             sys.exit(1)
  170.     return course[choice]
  171.  
  172. def parse_choice(input):
  173.     if input == '':
  174.         return input
  175.     input = split_string(input, ' ,')
  176.     # This split can handle your input as: 1,3,4-5 or 1 3 4-5 or 1, 3, 4-5. Besides, range input support 4-5 or 4:5 
  177.     choice = []
  178.     for e in input:
  179.         if e.isdigit():
  180.             if e not in choice:
  181.                 choice.append(int(e))
  182.         else:
  183.             s = split_string(e, ':-')
  184.             if len(s) != 2 or not s[0].isdigit() or not s[1].isdigit():
  185.                 print 'Ignore invalid input %s' %e
  186.             else:
  187.                 for num in range(int(s[0]), int(s[1])+1):
  188.                     if num not in choice:
  189.                         choice.append(num)
  190.     return sorted(choice)           
  191.  
  192. def choose_download(resource):
  193.     for i in range(len(resource)):
  194.         print '['+repr(i).rjust(2)+']:', resource[i][0]
  195.     print 'Enter your choice, such as: 1, 3, 5-9. Or just Enter to skip.'
  196.     choice = raw_input('>')
  197.     choice = parse_choice(choice)
  198.     print 'To be downloaded:', choice
  199.     print
  200.     download = []
  201.     for i in choice:
  202.         if i in range(len(resource)):
  203.             download.append(resource[i])
  204.     return download
  205.  
  206. def download_path():
  207.     if len(sys.argv) > 1:
  208.         if not os.path.exists(sys.argv[1]):
  209.             try:
  210.                 os.mkdir(sys.argv[1])
  211.             except Exception, error:
  212.                 print error
  213.                 sys.exit(1)
  214.         return os.path.abspath(sys.argv[1])
  215.     else:
  216.         return os.path.abspath('.')
  217.  
  218. def main():
  219.     print '----------------------------------'
  220.     print '-    Coursera.org Downloader     -'
  221.     print '-         by Logan Ding          -'
  222.     print '----------------------------------'
  223.     print
  224.     # Add courses by yourself. Not all tested. You can feed back.
  225.     course = { '1' : 'modelthinking',
  226.                '2' : 'gametheory',  
  227.                '3' : 'crypto',
  228.                '4' : 'saas',
  229.                '5' : 'pgm', 
  230.                '6' : 'algo'}
  231.  
  232.     # Your Coursera.org email and password needed here to download videos. 
  233.     email = 'youremail'
  234.     password = 'password'
  235.  
  236.     if email == 'youremail':
  237.         print 'You must change the email and the password to yours in main() first.'
  238.         sys.exit(1)
  239.  
  240.     path  = download_path()
  241.     print 'All files will be downloaded to:', path
  242.     print
  243.     course = choose_course(course)
  244.     br = initialize_browser(course, email, password)
  245.     vidoe, srt, txt, pdf, pptx = resolve_resources(br, path, course)
  246.     downloader(vidoe, srt, txt, pdf, pptx, br, path)
  247.  
  248. if __name__ == '__main__':
  249.     main()
  250.  
Runtime error #stdin #stdout 0.02s 5760KB
comments (?)
stdin
copy 
Standard input is empty
stdout
copy 
Standard output is empty
https://ideone.com/UxJHp
language:
Python 3 (python  3.12)
created:
14 years ago
visibility:
public

Share or Embed source code

Discover > Sphere Engine API

The brand new service which powers Ideone!

Discover > IDE Widget

Widget for compiling and running the source code in a web browser!