#!/usr/bin/env python

import os
import sys
import re
import urllib

def number_of_subpages(channel, page):
    html = urllib.urlopen("http://telegazeta.tvp.pl/telegazeta.php?page=%s&channel=%s" % (page, channel)).read().decode("iso8859-2")
    number = int(re.findall(r'\d+ / (\d+)', html)[0])
    return number

def subpages(channel, page):
    assert page >= 100 and page <= 999
    group = (page / 100) * 100
    for subpage in xrange(1, number_of_subpages(channel, page) + 1):
        yield (subpage, "http://www.telegazeta.tvp.pl/sync/ncexp/%s/%d/%03d_%04d.png" % (channel, group, page, subpage))

def pages(channel):
    for page in xrange(100, 999 + 1):
        for subpage in subpages(channel, page):
            yield (page,) + subpage

def download_channel(channel):
    for page, subpage, url in pages(channel):
        print channel, page, subpage
        filename, headers = urllib.urlretrieve(url, "%s-%03d-%03d.png" % (channel, page, subpage))
        if headers.type != "image/png":
            os.remove(filename)

try:
    download_channel(sys.argv[1])
except IndexError:
    print 'Usage: "tgdl <channel name>". For instance: "tgdl TG1". Available channels are: TG1, TG2, SAT, KUL, SPO'