Extract all Images from a 4chan thread.

4chan

#!/usr/bin/env python
# Made by 'Mirko van der Waal'
# Distributed under terms of the MIT license.


try:
    import getopt
    import urllib
    import os

    from sys import exit, argv
    from re import findall
    from HTMLParser import HTMLParser
except ImportError as e:
    print e, exit(0)

images      = []
image_links = []
home_dir    = os.getenv('HOME')

# A subclass of HTMLParser
# Moves all information about images to images.
class MyHTMLParser(HTMLParser):
    def handle_starttag(self, tag, attrs):
        if tag == "a":
            if attrs[0][1] == "fileThumb":
                images.append(attrs)

# Process links from the images array.
def getLinks():
    for image in images:
        url = image[1][1][2:]
        image_links.append("http://" + url)

img_name = ''
web_addr = ''
fol_name = ''
our_dir  = ''

try:
    opts, args = getopt.getopt(argv[1:],
        ':u:n:p:x:', 
        ['url=', 'name=', 'path=', 'prefix='])

except Exception as e:
    print e, exit(0)
        
for o, a in opts:
    if   o in ('-u', '--url'):   web_addr = a
    elif o in ('-n', '--name'):  fol_name = a
    elif o in ('-p', '--path'):  our_dir  = a                                        
    elif o in ('-x', '--prefix'):img_name = a

if img_name == '': img_name    = 'image_'
if web_addr == '': web_addr    = raw_input("Board to extract images from: ")
if fol_name == '': fol_name    = raw_input("Name of folder to extract to: ")
if our_dir  == '': our_dir     = home_dir + "/Pictures/"+ fol_name + "/"

parser = MyHTMLParser()
rc = urllib.urlopen(web_addr)
parser.feed(rc.read())
getLinks()

try: 
    os.mkdir(our_dir)
except Exception as e: 
    print e, exit(0)

for ind, image in enumerate(image_links):
    ty = findall('\.\w+', image_links[ind])
    print '%i/%s\t%s\t%s'%(ind+1,len(image_links),image_links[ind],''.join([our_dir,img_name,str(ind+1),''.join(ty[-1:])]))
    with open(our_dir+img_name+str(ind)+''.join(ty[-1:]),"wb")as output:
        output.write(urllib.urlopen(image).read())

print "\nFinished."