def browse_episodes(self, skip=0):
self.ensure_authorized()
doc = self.fetch(self.BASE_URL + "/browse.php", {'o': skip})
with Timer(logger=self.log, name='Parsing episodes list'):
body = doc.find('div', {'class': 'content_body'})
series_titles = body.find('span', {'style': 'font-family:arial;.*?'}).strings
titles = body.find('span', {'class': 'torrent_title'}).strings
episode_titles, original_titles = zip(*[parse_title(t) for t in titles])
release_dates = body.find('b').strings[1::3]
release_dates = [str_to_date(d, '%d.%m.%Y %H:%M') for d in release_dates]
selected_page = body.find('span', {'class': 'd_pages_link_selected'}).text
last_page = body.find('a', {'class': 'd_pages_link'}).last.text
self.has_more = int(selected_page) < int(last_page)
icons = body.find('img', {'class': 'category_icon'}).attrs('src')
onclicks = body.find('a', {'href': 'javascript:{};'}).attrs('onClick')
series_ids, season_numbers, episode_numbers = zip(*[parse_onclick(s or "") for s in onclicks])
posters = [poster_url(i[0][18:-5], i[1]) for i in zip(icons, season_numbers)]
icons = [self.BASE_URL + url for url in icons]
images = [url.replace('/icons/cat_', '/posters/poster_') for url in icons]
data = zip(series_ids, series_titles, season_numbers,
episode_numbers, episode_titles, original_titles, release_dates, icons, posters, images)
episodes = [Episode(*e) for e in data if e[0]]
self.log.info("Got %d episode(s) successfully" % (len(episodes)))
self.log.debug(repr(episodes).decode("unicode-escape"))
return episodes
def get_series_episodes(self, series_id):
doc = self._get_series_doc(series_id)
episodes = []
with Timer(logger=self.log, name='Parsing episodes of series with ID %d' % series_id):
body = doc.find('div', {'class': 'mid'})
series_title, original_title = parse_title(body.find('h1').first.text)
image = self.BASE_URL + body.find('img').attr('src')
icon = image.replace('/posters/poster_', '/icons/cat_')
episode_divs = body.find('div', {'class': 't_row.*?'})
series_poster = None
for ep in episode_divs:
title_td = ep.find('td', {'class': 't_episode_title'})
episode_title, orig_title = parse_title(title_td.text)
onclick = title_td.attr('onClick')
release_date = ep.find('span', {'class': 'micro'}).find('span')[0].text
release_date = str_to_date(release_date, '%d.%m.%Y %H:%M') if release_date else None
_, season_number, episode_number = parse_onclick(onclick)
poster = poster_url(original_title, season_number)
if not series_poster:
series_poster = poster
episode = Episode(series_id, series_title, season_number, episode_number, episode_title,
orig_title, release_date, icon, poster, image)
episodes.append(episode)
self.log.info("Got %d episode(s) successfully" % (len(episodes)))
self.log.debug(repr(episodes).decode("unicode-escape"))
return episodes
def browse_episodes(self, skip=0):
self.ensure_authorized()
self.check_for_new_series()
page = (skip or 0) / 10 + 1
only_favorites = plugin.get_setting('check_only_favorites', bool)
doc = self._get_new_episodes_doc(page, only_favorites)
with Timer(logger=self.log, name="Parsing episodes list"):
body = doc.find('div', {'class': 'content history'})
series_titles = body.find('div', {'class': 'name-ru'}).strings
episode_titles = body.find('div', {'class': 'alpha'}).strings[::2]
original_episode_titles = body.find('div', {'class': 'beta'}).strings[::2]
release_dates = body.find('div', {'class': 'alpha'}).strings[1::2]
release_dates = [str_to_date(r_d.split(' ')[-1], '%d.%m.%Y') for r_d in release_dates]
paging = doc.find('div', {'class': 'pagging-pane'})
selected_page = paging.find('a', {'class': 'item active'}).text
last_page = paging.find('a', {'class': 'item'}).last.text
self.has_more = int(selected_page) < int(last_page)
data_codes = body.find('div', {'class': 'haveseen-btn.*?'}).attrs('data-code')
series_ids, season_numbers, episode_numbers = zip(*[parse_data_code(s or "") for s in data_codes])
posters = [img_url(i, y, z) for i, y, z in zip(series_ids, season_numbers, episode_numbers)]
images = [img_url(series_id) for series_id in series_ids]
icons = [img_url(series_id).replace('/poster.jpg', '/image.jpg') for series_id in series_ids]
data = zip(series_ids, series_titles, season_numbers, episode_numbers, episode_titles, original_episode_titles, release_dates, icons, posters, images)
episodes = [Episode(*e) for e in data if e[0]]
self.log.info("Got %d episode(s) successfully" % (len(episodes)))
self.log.debug(repr(episodes).decode("unicode-escape"))
return episodes
def get_series_episodes(self, series_id, series_alias=None):
if not series_alias:
series_alias = self.shows_ids_dict[int(series_id)]
doc = self._get_episodes_doc(series_alias)
episodes = []
with Timer(logger=self.log, name='Parsing episodes of series with ID %s' % series_alias):
title = doc.find('div', {'class': 'header'})
series_title = title.find('h2', {'class': 'title-en'}).text
image = img_url(series_id)
icon = image.replace('/poster.jpg', '/image.jpg')
episodes_data = doc.find('div', {'class': 'series-block'})
seasons = episodes_data.find('div', {'class': 'serie-block'})
year = seasons.last.find('div', {'class': 'details'}).text
year = re.search('Год: (\d{4})', year)
year = year.group(1) if year else None
if year:
series_title += " (%s)" % year
for s in seasons:
fullseason = s.find('div', {'class': 'movie-details-block'})
inactive = fullseason.find('div', {'class': 'external-btn inactive'})
if not inactive:
button = fullseason.find('div', {'class': 'haveseen-btn.*?'}).attr('data-code')
if button:
series_id, season_number, episode_number = parse_data_code(button)
episode_title = lang(40424) % season_number
orig_title = ""
release_date=str_to_date("17.09.1989", "%d.%m.%Y")
poster = img_url(series_id, season_number, episode_number)
episode = Episode(series_id, series_title, season_number, episode_number, episode_title, orig_title, release_date, icon, poster, image)
episodes.append(episode)
episodes_table = s.find('table', {'class': 'movie-parts-list'})
if not episodes_table.attrs('id')[0]:
self.log.warning("No ID for table. New season of {0}".format(series_title))
continue
if episodes_table.attrs('id')[0][-6:] == u'999999':
pass
# IS SPECIAL SEASON
titles = episodes_table.find('td', {'class': 'gamma.*?'})
orig_titles = titles.find('span').strings
episode_titles = [t.split('\n')[0].strip().replace(u"й", u"й").replace(u"И", u"Й") for t in titles.strings]
#episode_dates = [str(d.split(':')[-1])[1:] for d in episodes_table.find('td', {'class': 'delta'}).strings]
episode_dates = []
for d in episodes_table.find('td', {'class': 'delta'}).strings:
d = d.split(':')
d = d[-1]
d = d[1:]
d = d.replace('янв ', '01.01.').replace('фев ', '01.02.').replace('мар ', '01.03').replace('апр','01.04')\
.replace('май','01.05').replace('июн','01.06').replace('июл','01.07').replace('авг','01.08').replace('сен','01.09')\
.replace('окт','01.10').replace('ноя','01.11').replace('дек','01.12')
it = str(d)
episode_dates.append(it)
onclick = episodes_table.find('div', {'class': 'haveseen-btn.*?'}).attrs('data-code')
for e in range(len(onclick)):
data_code = onclick[e]
if not data_code:
continue
_, season_number, episode_number = parse_data_code(onclick[e])
episode_title = episode_titles[e]
orig_title = orig_titles[e]
release_date = str_to_date(episode_dates[e], "%d.%m.%Y")
poster = img_url(series_id, season_number, episode_number)
episode = Episode(series_id, series_title, season_number, episode_number, episode_title, orig_title, release_date, icon, poster, image)
episodes.append(episode)
self.log.info("Got %d episode(s) successfully" % (len(episodes)))
self.log.debug(repr(episodes).decode("unicode-escape"))
return episodes
