def get_shows(self, channel, url, params):
while True:
print "PAGE %d" % params['pagina']
real_url = "%s?%s" % (url,urllib.urlencode(params))
html = urllib.urlopen(real_url).read()
soup = BeautifulSoup(html,from_encoding='latin-1')
answer = []
found = False
for dataitem in soup('div','resBusqueda'):
found = True
name = dataitem.h1.a.text.strip()
print "%s..." % name.encode('utf8')
if channel.serie_set.filter(name=name).count() > 0:
print "EXIST"
continue
serie = Serie()
serie.channel = channel
serie.name = name
serie.thumbnail = dataitem.find('div','resBusqueda_thumb').img.get('src')
serie.description = dataitem.p.text
serie.url = urllib.basejoin(self.BASE_URL, dataitem.h1.a.get('href'))
#self.get_episodes(serie, serie_url)
serie.save()
print "OK"
if not found:
break
params['pagina'] += 1
def get_serie(self, channel, genre, url):
if Serie.objects.filter(url=url).count() > 0:
print "EXISTS"
return
html = urllib.urlopen(url).read()
soup = BeautifulSoup(html, from_encoding='utf-8')
info = soup.find('article','info')
serie_name = info.strong.text.strip()
if Serie.objects.filter(name=serie_name).count() > 0:
print "EXISTS"
return
serie = Serie(channel=channel)
serie.name = serie_name
serie.url = url
serie.thumbnail = urllib.basejoin(self.BASE_URL, info.img.get('src'))
serie.description = info.find('div','expandable').text
serie.save()
serie.genres.add(genre)
