Skip to content

Instantly share code, notes, and snippets.

@thefinn93
Created April 22, 2012 06:38
Show Gist options
  • Save thefinn93/2462039 to your computer and use it in GitHub Desktop.
Save thefinn93/2462039 to your computer and use it in GitHub Desktop.
Wallbase.cc Scraper
#! /usr/bin/env python
import sys
import json
import subprocess
import urllib
try:
import requests
except:
print "Install requests (try easy_install requests)"
sys.exit()
try:
from BeautifulSoup import BeautifulSoup
except:
print "Install BeautifulSoup (try easy_install beautifulsoup)"
sys.exit()
try:
from termcolor import colored, cprint
except:
print "Install termcolor (try easy_install termcolor)"
sys.exit()
username="" # Remember to clear this
password="" # before sharing :D
login = requests.post("http://wallbase.cc/user/login","username="+username+"&pass="+password+"&nopass_email=Type+in+your+e-mail+and+press+enter&nopass=0")
q = ""
if len(sys.argv) == 1:
q = raw_input("What would you like to search for? ")
else:
q = " ".join(sys.argv[1:])
cprint("For the following options, simply press enter for all","yellow")
res = raw_input("Specify resolution (WIDTHxHEIGHT): ")
if res == "":
res = "0x0"
aspect = raw_input("Specify aspect ratio (width:height): ")
if aspect == "":
aspcet = "0"
cprint("Searching for " + q, "grey")
page = 0
a = json.loads(requests.post("http://wallbase.cc/search/"+str(page),"query="+q+"&board=12&res_opt=eqeq&res=" + res + "&aspect=" + aspect + "&nsfw_sfw=1&nsfw_sketchy=1&nsfw_nsfw=1&thpp=60&orderby=reference&orderby_opt=desc",cookies=login.cookies,headers={"X-Requested-With":"XMLHttpRequest","User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.30 Safari/536.5"}).content)
while len(a) > 1:
cprint("Loading 32 images starting at " + str(page), "yellow")
a = json.loads(requests.post("http://wallbase.cc/search/"+str(page),"query="+q+"&board=12&res_opt=eqeq&res=" + res + "&aspect=" + aspect + "&nsfw_sfw=1&nsfw_sketchy=1&nsfw_nsfw=1&thpp=60&orderby=reference&orderby_opt=desc",cookies=login.cookies,headers={"X-Requested-With":"XMLHttpRequest","User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.30 Safari/536.5"}).content)
for wallpaper in a:
url = "http://wallbase.cc/wallpaper/"+str(wallpaper['id'])
colorpage = colored(str(page),"blue")
colorwidth = colored(str(wallpaper['attrs']['wall_w']), "blue")
colorheight = colored(str(wallpaper['attrs']['wall_h']), "blue")
print colorpage + ".\t" + url + "\tWidth: " + colorwidth + "\tHeight: " + colorheight
try:
soup = BeautifulSoup(requests.get(url,cookies=login.cookies).content)
img = soup.findAll("img")
urllib.urlretrieve(img[len(img)-1].get("src"),str(page) + "." + img[len(img)-1].get("src").split(".")[-1])
except:
cprint("FAILED!","red",attrs=["bold"])
page=page+1
Copy link

ghost commented Dec 13, 2012

From a little time the script doesn't work. It doesn't download wallpapers but little flag GIFs.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment