#!/usr/bin/env python

import sys
import os
import urllib
from PIL import Image
from StringIO import StringIO

"""
Author  : flo
date    : 2016.07.18
Purpose : example of parsing url from html and image download
Comments: python webparserww.txt website 
        : http://www.blab.com/blab/blab/blab
"""


try:
    import requests
except ImportError as err:
    print "yoyoyo, Missing Plugin, download requests dude."
    exit(1)


try:
    from bs4 import BeautifulSoup
except ImportError as err:
    print "yoyoyo, Missing Plugin, download BeautifulSoup version 4 dude."
    exit(1)


def getdata(argv):
    url = sys.argv[1]
    fname = url.split('/')[-1]
    a , b = urllib.urlretrieve(url, fname)
    fp = os.getcwd()
    fp = fp+'/'+fname

    if os.path.isfile(fp):
        if sys.platform == "win32":
            f = open(fp, 'r')
            data = f.read()
            tmplist = parsedata(data)
            f.close()
            os.remove(fp)
            os.mkdir(fname)
            os.chdir(fname)
            download(tmplist)
        else:
            f = open(fp, 'r')
            data = f.read()
            tmplist = parsedata(data)
            f.close()
            os.remove(fp)
            os.mkdir(fname)
            os.chdir(fname)
            download(tmplist)

    else:
        print "Something wrong with your internet or their website, file not downloaded: " + url + "\n"
        print "Run this again, maybe."
        exit(1)


def parsedata(d):
    listimg, links, flinks = [], [], []
    soup = BeautifulSoup(d, "lxml")
    for a in soup.find_all('a'):
        listimg.append(a.get('href'))

    for a in listimg:
        if 'jpg' in a:
            links.append(a)

    # splitting the ? from url
    for a in links:
        mess = a.split('?')
        flinks.append(mess[0])

    return flinks


def download(ilist):
    for img in ilist:
        iname = img.split('/')[-1]
        r = requests.get(img)
        sys.stdout.write('.')
        i = Image.open(StringIO(r.content))
        i.save(iname)
        sys.stdout.flush()
    print "\nDone"


def main():
    argv = ""
    getdata(argv)


# added proper main function
if __name__ == "__main__":
    main()