DL gifs from senorgif..

dl.py

# imageDownloader.py
# Finds and downloads all images from any given URL recursively.
# FB - 201009094
import urllib2
from os.path import basename
import urlparse
from BeautifulSoup import BeautifulSoup # for HTML parsing
global page
page = 1
print page
global urlList
urlList = []

# recursively download images starting from the root URL
def downloadImages(url, level, minFileSize): # the root URL is level 0
    global page
    # do not go to other websites
    global website
    netloc = urlparse.urlsplit(url).netloc.split('.')
    if netloc[-2] + netloc[-1] != website:
        return

    global urlList
    if url in urlList: # prevent using the same URL again
        return

    try:
        urlContent = urllib2.urlopen(url).read()
        urlList.append(url)
        print url
    except:
        return

    soup = BeautifulSoup(''.join(urlContent))
    # find and download all images
    imgTags = soup.findAll('img')
    for imgTag in imgTags:
        imgUrl = imgTag['src']
        # download only the proper image files
        if imgUrl.lower().endswith('.gif'):
            try:
                imgData = urllib2.urlopen(imgUrl).read()
                if len(imgData) >= minFileSize:
                    print "    " + imgUrl + " size :" + str(len(imgData)/1024)
                    fileName = basename(urlsplit(imgUrl)[2])
                    output = open(fileName,'wb')
                    output.write(imgData)
                    output.close()
            except:
                pass
    print
    print

    # if there are links on the webpage then recursively repeat
    page += 1
    linkUrl = rootUrl 
    downloadImages(linkUrl +str(page), level - 1, 2093056)

# main
rootUrl = 'http://memebase.cheezburger.com/senorgif/page/'
netloc = urlparse.urlsplit(rootUrl + str(page)).netloc.split('.')
global website
website = netloc[-2] + netloc[-1]
downloadImages(rootUrl, 1, 2093056)