from BeautifulSoup import BeautifulSoup
from urllib import urlopen, quote_plus
import urlparse
import time
def tuplelist_to_dict(tuplelist):
    res = {}
    for t in tuplelist:
        res[t[0]] = t[1]
    return res
v01 = {}
def get_list():
    global v01
    v01 = {}
    _url = "http://www.nrk.no/nett-tv/bokstav/@/"
    v01['start'] = time.time()
    html = urlopen("http://www.w3.org/services/tidy?docAddr=%s&forceXML=on" %(quote_plus(_url))).read()
    v01['got html'] = time.time()
    html = html.replace("\n", "")

    items = BeautifulSoup(html).find("div", "nettv-category").find("ul").findChildren("li")
    res = []
    v01['starting item parsing'] = time.time()
    for item in items:
        x = tuplelist_to_dict(item.find("img").attrs)
        v_title = unicode(x['alt'])
        v_image = unicode(urlparse.urljoin(_url, x['src']))
        v_link = unicode(urlparse.urljoin(_url, tuplelist_to_dict(item.find("a").attrs)['href']))
        v_summary = unicode(item.find("div", "summary").text)
        res.append({'title': v_title, 'img': v_image, 'url': v_link, 'plot': v_summary})
        #print v_title
        #print v_image
        #print v_link
        #print v_summary
    v01["returning results"] = time.time()
    return res
    
    #print unicode(items[0])
    #print dir(items[0])
print get_list()
print "Starting".ljust(30), ":", str(v01['start'])
print "Got html".ljust(30), ":", "+" + str(v01['got html'] - v01['start'])
print "Starting item parsing".ljust(30), ":", "+" + str(v01['starting item parsing'] - v01['got html'])
print "Returning results".ljust(30), ":", "+" + str(v01['returning results'] - v01['starting item parsing'])