Python script to download Lecture notes for machine learning from http://cs229.stanford.edu/materials.html

ml_notes.py

"""
Description:
Get Lecture notes for machine learning
from http://cs229.stanford.edu/materials.html

Usage:
python ml_notes.py
"""
import urllib2
import os
def getfile(url):
    file_name = url.split('/')[-1]
    u = urllib2.urlopen(url)
    f = open(file_name, 'wb')
    meta = u.info()
    file_size = int(meta.getheaders("Content-Length")[0])
    print "Downloading: %s Bytes: %s" % (file_name, file_size)
    
    file_size_dl = 0
    block_sz = 8192
    while True:
        buffer = u.read(block_sz)
        if not buffer:
            break

        file_size_dl += len(buffer)
        f.write(buffer)
        status = r"%10d  [%3.2f%%]" % (file_size_dl, file_size_dl * 100. / file_size)
        status = status + chr(8)*(len(status)+1)
        print status,
        
    f.close()
    print "\n"

if __name__ == '__main__':
    initurl = 'http://cs229.stanford.edu/notes/cs229-notes1.pdf'
    temp = initurl.split("1")
    urls = []
    for i in range(1, 13):
        if i == 7:
            urls.append(temp[0] + "7a" + temp[1])
            urls.append(temp[0] + "7b" + temp[1])
            continue
        urls.append(temp[0] + str(i) + temp[1])
    if not os.path.isdir("lecture_notes"):
        print "Creating directory lecture_notes."
        os.mkdir("lecture_notes")
    else:
        print "lecture_notes directory already exists."
    print "Going to directory lecture_notes."
    os.chdir("lecture_notes")
    for url in urls:
        fname = url.split("/")[-1]
        if not os.path.isfile(fname):
            print "Get file => " + fname
            getfile(url)
    print "\nDownload finished."