#import xbmc, xbmcgui,urllib, re, random, string, time, os.path,Image,cookielib,urllib2
import string,getopt,sys
import cookielib,urllib2
import re
import time

# URL for all pages, ordered by number of downloads.
# Most downloaded .torrent files first.
BASE_URL = 'http://www.vuze.com/content/BucketBrowse.htm?sp=X&sp=X&sp=X&sp=$PAGENUM&sp=SPOPULAR&sp=SALL&sp=X&sp=X&sp=X&sp=X&sp=X'
#BASE_URL= 'http://www.vuze.com/content/BucketBrowse.htm?sp=X&sp=X&sp=X&sp=$PAGENUM&sp=SAZHOT&sp=SALL&sp=X&sp=X&sp=X&sp=X&sp=X'

def parse_page(page):
	torrent = {}
	#pagefile = open(page, 'r')
	#file = pagefile.read()
	#pagefile.close()
	prev_title = 'unknown'
	for line in page.split("\n"):
		title = re.search('\); return false;" title="' + r'([^\"]+)' + '" href="/details', line)
		#title = re.search(';" title="' + r'(\w+)' + '" href="', line)
		if title:
			prev_title = re.sub( r'[\/]', '_', title.group(1))
		code = re.search('span id="java_not_installed_' + r'(\w{20,})' + '" style="display: none', line)
		if code:
			url = 'http://www.vuze.com/download/' + code.group(1) + '.torrent'
			torrent[prev_title] = url
			#print url, prev_title
			#print line
	return(torrent)

	# example link : 'span id="java_not_installed_QSHDTXGQUL53HVQ2ZJGFYYLTQXUKJ5TT" style'
	# translated   : http://www.vuze.com/download/QSHDTXGQUL53HVQ2ZJGFYYLTQXUKJ5TT.torrent
	#print file

def get_page(url):
	cj = cookielib.CookieJar()
	opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
	temp = opener.open(url)
	return temp.read()
#print temp.read()

def get_url_and_write_to_file(url, name):
	#print url
	page = get_page(url)
	pagefile = open(name, 'w')
	pagefile.write(page)
	pagefile.close()
	return(page)

def get_all_on_vuze(baseurl):
	for num in range(6,55):
		print "Downloading page " + str(num)
		url = string.Template(BASE_URL).safe_substitute(dict(PAGENUM=str(num)))
		page = get_url_and_write_to_file(url,"vuze_page_" + str(num) + ".html")
		torrents = parse_page(page)
		for torrent in torrents.keys():
			print "  ", torrent, torrents[torrent]
			time.sleep(10)
			get_url_and_write_to_file(torrents[torrent], torrent + ".torrent")


CRAWL = True
try:
  opts, args = getopt.getopt(sys.argv[1:], "f", ["debug"])
except getopt.GetoptError:
       # print help information and exit:
  print "Unknown option"
  sys.exit(2)
for o, a in opts:
  if o in ("-f", "--debug"):
    CRAWL = False

if CRAWL:
	print "Crawl mode.."
	get_all_on_vuze(BASE_URL)
else:
	print "No crawl mode.."
	parse_page()