maxgif.com image download script (via firefox bookmarks)

gistfile1.py

#! /usr/bin/env python
'''
Created on 05.05.2013

@author: christoph gerneth

ugly, short hack!
read in firefox bookmarks and
download images from maxgif.com
'''

import sys
import json
import urllib2
import re
import HTMLParser
from subprocess import call

with open(sys.argv[1], "r") as f:
    x = f.read()

jout = json.loads(x)

root = jout["children"][1]["children"][10]["children"]

#pprint(root)
#pattern : (?<=url\()(((f|ht){1}tp[s]?://)[-a-zA-Z0-9@:%_\+.~#?&//=;\\]+)

maxgif_pattern = r'(?<=url\()(((f|ht){1}tp[s]?://)[-a-zA-Z0-9@:%_\+.~#?&//=;\\]+)'

_htmlparser = HTMLParser.HTMLParser()
unescape = _htmlparser.unescape

img_list = []
for entry in root:
    entry_uri =  entry["uri"]
    if "maxgif" in entry_uri:
        #this is a maxif uri
        sitedata = unescape(urllib2.urlopen(entry_uri, timeout=100).read())
        found = re.findall(maxgif_pattern, sitedata)
        print "found %s on site %s" % (found[0][0], entry_uri)
        try:
            img_list.append(found[0][0])
        except:
            pass

# ok - now, download everything
call("wget %s" % " ".join(img_list), shell=True)