Created
March 8, 2012 05:54
-
-
Save scturtle/1999012 to your computer and use it in GitHub Desktop.
get subtitles of coursera classes
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os, urllib2 | |
game_cookie = 'csrf_token=XXXX; session=XXXX;' | |
class Sub_downloader: | |
def __init__(self, cookie): | |
self.cookie = cookie # 'csrf_token=XXXX; session=XXXX;' | |
def getname(self, response): | |
content_type = response.headers['content-type'] | |
if 'download' not in content_type: | |
return None # 404 | |
disposition = response.headers['content-disposition'] | |
st,ed = disposition.index('"'), disposition.rindex('"') | |
return disposition[st+1:ed] | |
def getsub(self, class_name, lecture_id, lang='en'): | |
req = urllib2.Request( | |
'https://www.coursera.org/%s/lecture/subtitles?q=%d_%s' | |
% (class_name, lecture_id, lang), | |
headers={'Cookie':self.cookie}) | |
response = urllib2.urlopen(req) | |
name = self.getname(response) | |
if not name: | |
return None # 404 | |
if not os.path.exists(name): | |
with file(name,'w') as f: | |
f.write(response.read()) | |
return name | |
if __name__ == '__main__': | |
sd = Sub_downloader(game_cookie) | |
game_lst = [49,12,50,8,9,10,11] | |
for i in game_lst: | |
s='%d\t%s' %(i, sd.getsub('gametheory',i)) | |
print s |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment