def scrap_episode(self, serie, url, thumbnail):
if Episode.objects.filter(url=url).count() > 0:
print "EXISTS"
return
print url
html = urllib.urlopen(url).read()
soup = BeautifulSoup(html, from_encoding='utf-8')
info = soup.find('article','info')
p = soup.find('div','description').text
season,number,duration = re.findall('Temporada ([0-9]+) \| Ep. ([0-9]+) \(([0-9:]+)\)', p)[0]
if Episode.objects.filter(serie=serie, season=int(season), number=int(number)).count() > 0:
print "EXISTS"
return
episode = Episode()
episode.serie = serie
episode.season = int(season)
episode.number = int(number)
episode.duration = time(0,*map(int,duration.split(':')))
episode.description = soup.find('div','description').p.children.next()
episode.thumbnail = thumbnail
episode.save()
media = MundoFoxMediaFile()
smil_url = re.findall('player.releaseUrl = "([^"]+)"', html)[0]
smil_url += "&manifest=m3u&format=SMIL&Tracking=true&Embedd=true"
media._url = smil_url
media.episode = episode
media.save()
def scrap_serie(self, serie):
html = urllib.urlopen(serie.url).read()
soup = BeautifulSoup(html, from_encoding='utf8')
for cnt,article in enumerate(soup.find('div','primary-pane').ol('li')):
episode = Episode()
episode.thumbnail = article.img.get('src')
episode.name = article.find('span','video-overview').span.text
print episode.name.encode('utf8')
dur = article.find('span','video-time').text.split(':')
episode.duration = time(0, int(dur[0]), int(dur[1]))
episode.serie = serie
episode.number = cnt+1
episode.season = 1
episode.save()
video_id = re.findall('v=([^&]+)', article.a.get('href'))[0]
media = HttpMediaFile()
media.url = self.get_real_url(video_id)
media.episode = episode
media.save()
