gistfile1.py

import sys, getpass, os, glob

try:
    import argparse
except ImportError:
    print "argparse required but missing"
    sys.exit(1)

try:
    from mechanize import Browser
except ImportError:
    print "mechanize is required but missing"
    sys.exit(1)
    

def getSolutions (path_prefix):
    global br
    br = Browser()
    br.set_proxies({"http":"iit2006069:hukunQk007@172.31.1.4:8080"})
    
    # make me a browser that makes ass of robots.txt
    br.addheaders = [('User-agent', 'Mozilla/5.0 (X11; U; Linux i686; en-US; \
              rv:1.9.0.1) Gecko/2008071615 Fedora/3.0.1-1.fc9 Firefox/3.0.1')]
    br.set_handle_robots(False)

    print "Enter yout SPOJ username :",
    username = raw_input()
    password = getpass.getpass()

    # Authenticate the user
    print "Authenticating " + username
    br.open ("http://spoj.pl")
    br.select_form (name="login")
    br["login_user"] = username
    br["password"] = password
    # sign in for a day for avoiding timeouts
    br.find_control(name="autologin").items[0].selected = True
    br.form.action = "http://www.spoj.pl"
    response = br.submit()

    verify = response.read()
    if (verify.find("Authentication failed!") != -1):
        print "Error authenticating - " + username
        exit(0)

    # grab the signed list of submissions
    print "Grabbing siglist for " + username
    siglist = br.open("http://www.spoj.pl/status/" + username + "/signedlist")

    # dump first 9 lines
    for i in xrange(9):
        siglist.readline()

    # make a list of all AC's and challenges
    print "Filtering siglist for AC/Challenge solutions..."
    mysublist = list()

    while True: 
        temp = siglist.readline()
        
        if temp=='\------------------------------------------------------------------------------/\n':
            # reached end of siglist
            break

        if not len(temp) :
            print "Reached EOF, siglist format has probably changed," + \
                    " contact author."
            exit(1)
            
        entry = [x.strip() for x in temp.split('|')]
        
        if entry[4] == 'AC' or entry[4].isdigit():
            mysublist.append (entry)

    #totalsubmissions = len(mysublist)
    print "Done !!!"
    return mysublist

def downloadSolutions(mysublist):
    
    totalsubmissions = len(mysublist)
    
    print "Fetching sources into " + path_prefix
    progress = 0
    
    for entry in mysublist:
        existing_files = glob.glob(os.path.join(path_prefix, "%s-%s*" % \
                                                           (entry[3],entry[1])))

        progress += 1
        if len(existing_files) == 1:
            print "%d/%d - %s skipped." % (progress, totalsubmissions, entry[3])
        else:
            source_code = br.open("http://www.spoj.pl/files/src/save/" + \
                                                                       entry[1])
            header = dict(source_code.info())
            filename = ""
            try:
                filename = header['content-disposition'].split('=')[1]
                filename = entry[3] + "-" + filename
            except:
                filename = entry[3] + "-" + entry[1]
                
            fp = open( os.path.join(path_prefix, filename), "w")
            fp.write (source_code.read())
            fp.close
            print "%d/%d - %s done." % (progress, totalsubmissions, filename)

    print "Created a backup of %d submission for %s" % \
                                                    (totalsubmissions, username)


if __name__=="__main__":
    parser = argparse.ArgumentParser(prog="spojbackup",
            description = "Creates a backup of all your Submissions on SPOJ " +\
            "(Sphere Online Judge) http://spoj.pl in a desired place")

    parser.add_argument("-o", "--outputpath",default="./", type=str,
                              help="Directory to store all fetched solutions")

    args = parser.parse_args()
    path_prefix = args.outputpath
    print downloadSolutions (getSolutions (path_prefix) )