from bs4 import BeautifulSoup
import sys,os
import httplib2, urllib,time

http = httplib2.Http()

count = int(sys.argv[1])

retries = 0
max_retries = int(sys.argv[2])

images_path = "/var/www/4chanbanners/images/"

if len(sys.argv) == 3:
    while count > 0 and retries <= 20:
        time.sleep(3)
        status, response = http.request('http://boards.4chan.org/b/')
        soup = BeautifulSoup(response).img["src"]
        filename = soup.split('/')[-1].split('#')[0].split('?')[0]

        if os.path.exists(images_path+filename):
            retries+= 1
            print "File " + filename + " already exists!"
        else:
            urllib.urlretrieve("http:"+soup,images_path+filename)
            print "Got " + filename
            retries = 0
            count -= 1
else:
    print "Usage: parse.py IMAGE_COUNT MAX_RETRIES"