def parse_watchlist_page(self, data):
"""
Return a generator of parsed movies from watchlist
"""
items = data.xpath('//*[@id="itemList"]/li[@class="item"]')
id_pattern = re.compile(r'(?P<id>\d+)')
year_pattern = re.compile(ur'\((?P<year>\d{4})')
for item in items:
info = item.find('.//div[@class="info"]')
if info is not None:
link = info.find('.//a[@class="name"]')
id_match = id_pattern.findall(link.get('href'))
title_rus = link.text
info_span = info.find('.//span[1]')
title = info_span.text
year_match = year_pattern.findall(title)
if title.index('('):
title = title[0:title.index('(')-1]
else:
title = ''
movie = {
'id': id_match[0],
'title': title,
'title_rus': title_rus,
'link': link.get('href'),
'year': year_match[0],
}
movie.update({'slug': slugify(movie['title'])})
yield movie
def __init__(self, provider, pid, name, slug=None, person_type=ACTOR_TYPE,
name_rus=None, poster=None):
parser = ParserFactory.get_parser(provider)
if isinstance(parser, IMDBParser):
self.imdb_id = pid
elif isinstance(parser, KinopoiskParser):
self.kp_id = pid
else:
raise TypeError('Parser %s does not supported' % type(parser))
self.name = name
if slug is None:
self.slug = slugify(self.name)
else:
self.slug = slug
if not name_rus is None:
self.name_rus = name_rus
self.person_type = person_type
self.status = Person.ACTIVE_STATUS
if not person_type is None:
self.poster = poster
def parse_voted_movies(self, data):
"""
Return a generator of parsed movies from voted list
"""
items = data.xpath('//div[@class="profileFilmsList"]/div')
id_pattern = re.compile(r'(?P<id>\d+)')
year_pattern = re.compile(ur'(?P<year>\d{4})')
serial_pattern = re.compile(ur'сериал')
rating_pattern = re.compile(r'rating: \'(?P<id>\d+)\'')
for item in items:
if 'item' in item.get('class'):
link = item.find('.//div[@class="nameRus"]/a').get('href')
id_match = id_pattern.findall(link)
text = item.find('.//div[@class="nameRus"]/a').text
year_match = year_pattern.findall(text)
serial_match = serial_pattern.findall(text)
rating = rating_pattern.findall(item.find('.//script').text)
movie = {
'id': id_match[0],
'title': item.find('.//div[@class="nameEng"]').text,
'title_rus': text[:text.index(' (')],
'link': link,
'year': year_match[0],
'vote': int(rating[0]),
}
movie.update({'slug': slugify(movie['title'])})
if serial_match:
movie.update({'serial': True})
yield movie
def __init__(self, title, title_rus=None, slug=None):
self.title = title
if not title_rus is None:
self.title_rus = title_rus
if slug is None:
self.slug = slugify(self.title)
else:
self.slug = slug
def __init__(self, provider, mid, title, year, rating=0.0, title_rus=None,
slug=None, poster=None, is_series=False, status=ACTIVE_STATUS,
world_premiere=None, rus_premiere=None, dvd_premiere=None):
if not isinstance(provider, (IMDBParser, KinopoiskParser)):
parser = ParserFactory.get_parser(provider)
else:
parser = provider
if isinstance(parser, IMDBParser):
self.imdb_id = mid
self.imdb_rating = rating
elif isinstance(parser, KinopoiskParser):
self.kp_id = mid
self.kp_rating = rating
else:
raise TypeError('Parser %s does not supported' % type(parser))
self.title = title
self.year = year
self.status = status
if not title_rus is None:
self.title_rus = title_rus
if slug is None:
self.slug = slugify(self.title)
if poster:
self.poster = poster
if is_series:
self.is_series = is_series
if world_premiere:
self.world_premiere_date = world_premiere
if rus_premiere:
self.rus_premiere_date = rus_premiere
if dvd_premiere:
self.dvd_premiere_date = dvd_premiere
