#!/usr/bin/env python

import sys
import os
from PIL import Image
from StringIO import StringIO
from urlparse import urlparse

"""
Author  : flo
date    : 2016.07.27
Purpose : example of parsing url from html and image download
Comments: python webparserms.py website
        : works only on a few website without a html file in the url
          http://www.blab.com/blab/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():
    sess = requests.Session()
    url = sys.argv[1]
    data = sess.get(url, verify=True)
    sess.close()
    mdir = ""
    o = urlparse(url)
    paths = o.path.split('/')
    
    for p in paths:
        if p != "":
            mdir = p

    if data.ok:
        if sys.platform == "win32":
            tmplist = parsedata(data.text, url)
            os.mkdir(mdir)
            os.chdir(mdir)
            download(tmplist)
        else:
            tmplist = parsedata(data.text, url)
            os.mkdir(mdir)
            os.chdir(mdir)
            download(tmplist)

    else:
        print "Something wrong with the website: " + url + "\n"
        print "Run this again, maybe."
        exit(1)


def parsedata(data, url):
    listIMG , links = [], []
    soup = BeautifulSoup(data, "lxml")
    for a in soup.find_all('a'):
        listIMG.append(a.get('href'))

    for a in listIMG:
        if 'jpg' in a:
            links.append(url+a)
    return links


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():
    getdata()


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