ulozto_scrape

#!/usr/bin/env python
# coding=utf-8
import argparse

from selenium import webdriver

BROWSERS = dict(phantom=webdriver.PhantomJS,
                opera=webdriver.Opera,
                firefox=webdriver.Firefox,
                chrome=webdriver.Chrome
)

PAYLOAD = '''
links = [];
$(".fileReset").each(function(i, el){
    if(!/^přihlásit|zaregistruj se$/.test($(el).text())){
        url = 'http://uloz.to' + ad.decrypt(kn[$(el).attr('data-icon')]);
        if(links.indexOf(url) == -1) links.push(url);
    }
});
return links;
'''

parser = argparse.ArgumentParser(description='Scrapes links from Uloz.to search page')
parser.add_argument('url', nargs='+')
parser.add_argument('-b', '--browser', dest='browser', choices=BROWSERS.keys(),
                    default='phantom', help='browser backend to use')

args = parser.parse_args()
browser = BROWSERS[args.browser]()
browser.get(args.url)
links = browser.execute_script(PAYLOAD)

for one in links:
    print one

browser.close()