def get_episodes(self, channel):
url = 'http://www.youtube.com/user/CanalACulturaActiva/feed'
j = 1
shows = {}
html = urllib.urlopen(url).read()
dom = lxml.html.document_fromstring(html)
for item in dom.cssselect('.feed-item-main'):
p = [x.strip() for x in item.cssselect('h4')[0].text_content().split('-')]
show_title = p[0]
episode_title = '-'.join(p[1:])
try:
serie = Serie.objects.get(name=show_title)
except Serie.DoesNotExist:
serie = Serie(name=show_title)
print ">> SERIE: %s" % show_title.encode('utf8')
serie.channel = channel
serie.save()
serie.genres.add(Genre.objects.get_or_create(code='CULTURA',defaults={'name':'Cultura'})[0])
if Episode.objects.filter(name=episode_title).count() > 0:
continue
episode = Episode(serie=serie, name=episode_title, number=0)
print "%s" % episode_title
episode.description = item.cssselect('.description')[0].text_content() + "\n" + \
item.cssselect('.video-time')[0].text_content()
episode.thumbnail = urllib.basejoin(self.BASE_URL, item.cssselect('.video-thumb img')[0].get('src'))
episode.save()
url2 = item.cssselect('a')[0].get('href')
video_id = re.findall('v=([^&]+)', url2)[0]
video_url = get_youtube_url(video_id)
media = HttpMediaFile(width=640, height=480, mimetype='video/mp4', url=video_url)
media.episode = episode
media.save()
serie.episode_set.add(episode)
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()
html = re.sub('<\?.*?\?>','',html)
soup = BeautifulSoup(html, from_encoding='utf8')
for cnt,article in enumerate(soup('td','listado-mediateca-menu')):
episode = Episode()
episode.serie = serie
episode.thumbnail = urllib.basejoin(self.base_url, article.find('div','imagen-mediateca').img.get('src'))
episode.name = article.find('h5','titulo-mediateca').a.text
print episode.name.encode('utf8')
episode.description = article.find('span','texto-mediateca').text
episode_url = urllib.basejoin(self.base_url, article.find('h5','titulo-mediateca').a.get('href'))
episode.number = cnt+1
episode.season = 1
episode.save()
self.scrap_episode(episode, episode_url)
