# web_scraping_images.py

# web_scraping_images.py
import urllib, os, re

def download_image(urls_list):
    base_folder = r'c:\Z-DL-TEMP\\'
    if not os.path.exists(base_folder):
        os.makedirs(base_folder)
    print
    print
    for url in urls_list:
        path_components = re.sub('^https?://', '', url).split('/')
        file_name = path_components.pop()
        folder_name = '..'.join(path_components)
        full_path = base_folder + folder_name
        if not os.path.exists(full_path):
            os.makedirs(full_path)
            print 'Made a new folder:', folder_name
        print 'saving ->', url
        urllib.urlretrieve(url, os.path.join(base_folder,
                                             folder_name,
                                             file_name[:4])) # ***
        os.rename(full_path+'\\'+file_name[:4],full_path+'\\'+file_name) ### for os.rename() demo ref

def all_links(in_page):
    links = re.findall(r'href="([^"]+)"',in_page)
    if '.jpg' not in links:
        links = re.findall(r'src="([^"]+)"',in_page)
    links = [links[i].replace('.jpeg','.jpg') for i in xrange(0,len(links)) if ('http:' or 'https:') and '.jpg' in links[i].lower()]
    return list(set(links))

def from_page(u):
    return urllib.urlopen(u).read()

download_image(all_links(from_page("http://pizzot.com/en/for-android")))
print 'Done'