next »

[nop_90]

uses libxml2dom
http://www.boddie.org.uk/python/libxml2dom.html
basically you supply it the url of the gallery
the complete url of all the thumbs will be returned as a list.

Code:

def get_thumbs(url):
    tree = libxml2dom.parseURI(url,1)
    anchors = tree.getElementsByTagName("a")
    #(g_proto,g_netloc,g_path,g_params,g_query) = urlparse.urlsplit(url)
    result = []
    thumb_exts = [".jpg",".gif",".avi",".mpg",".wmv"]
    for anchor in anchors :
        href = anchor.getAttribute("href")
        #print urlparse.urlsplit(href)
        (proto,netloc,path,params,query) = urlparse.urlsplit(href)
        (root,ext) = os.path.splitext(path.lower())
        if thumb_exts.count(ext)>0 :
            imgs = anchor.getElementsByTagName("img")
            if len(imgs)>0 :
                img_src = imgs[0].getAttribute("src")
                result.append(urlparse.urljoin(url,img_src))
    if len(result)<=0 :
        print url
        raise "Error"
    return result