downsols.py

import os
import re
from getpass import getpass
from requests import Session
from contextlib import contextmanager

STATUS_PAGE = "http://www.spoj.com/status/{problem},{username}/"
MYACCOUNT_PAGE = "http://www.spoj.com/myaccount/"
SOLUTION_PAGE = "http://www.spoj.com/files/src/save/{sol_id}"
HOME_PAGE = "https://www.spoj.com/"

@contextmanager
def login(username, password):
    ses = Session()
    ses.post(HOME_PAGE, data={
        'login_user': username,
        'password': password
    })
    yield ses

@contextmanager
def takedir(path):
    oldloc = os.path.abspath(os.curdir)
    newloc = path
    try:
        if not os.path.exists(newloc):
            os.mkdir(newloc)
        os.chdir(newloc)
        yield newloc
    finally:
        os.chdir(oldloc)

def getSolvedProblems(doc, username):
    pattern = '/status/(.{3,8}),' + username + '/'
    return re.findall(pattern, doc)

def getSolutions(doc):
    pattern = '/files/src/([0-9]*?)/'
    return re.findall(pattern, doc)

def download():
    username = raw_input("username: ")
    password = getpass("password: ")
    with login(username, password) as session:
        for prob_id in getSolvedProblems(session.get(MYACCOUNT_PAGE).content, username):
            print 'downloading {} solutions'.format(prob_id)
            with takedir(os.path.abspath(prob_id)):
                for sol_id in getSolutions(session.get(
                        STATUS_PAGE.format(problem=prob_id, username=username)).content):
                    print '    downloading {}'.format(sol_id)
                    with open(sol_id, 'w') as solution:
                        solution.write(session.get(SOLUTION_PAGE.format(sol_id=sol_id)).content)

if __name__ == '__main__':
    download()