def get_zapad24ru():
ignored = get_ignored_films()
ignored_cinemas = get_ignored_cinemas()
source = ImportSources.objects.get(url='http://zapad24.ru/')
sfilm_clean(source)
cities_dict = get_source_data(source, 'city', 'dict')
cinemas_dict = get_source_data(source, 'cinema', 'dict')
schedules = get_source_data(source, 'schedule', 'list')
films = {}
source_films = SourceFilms.objects.filter(source_obj=source)
for i in source_films:
films[i.source_id] = i
fdict = get_all_source_films(source, source_films)
today = datetime.datetime.now()
next_month = datetime.date.today() + datetime.timedelta(days=40)
data_nof_films = ''
data_nof_cinema = ''
data_nof_city = ''
noffilms = []
req = urllib.urlopen('%safisha/' % source.url)
if req.getcode() == 200:
data = BeautifulSoup(req.read()) #, from_encoding="utf-8"
div = data.find('div', align="left")
for ind, table in enumerate(
div.findAll('table',
border="0",
cellpadding="0",
cellspacing="0",
width="100%")):
cinema_tag = table.find('strong').string.encode('utf-8')
cinema_name = re.findall(r'\".+\"',
cinema_tag)[0].replace('"', '').strip()
cinema_slug = low(del_separator(cinema_name))
cinema_id = cinema_slug.decode('utf-8')
city_name = re.findall(r'\(.+\)', cinema_tag)[0].replace(
'(г. ', '').replace(')', '').strip()
city_slug = low(del_separator(city_name))
city_id = city_slug.decode('utf-8')
city_obj = cities_dict.get(city_id)
if not city_obj:
city = City.objects.filter(name__name=city_slug,
name__status=2).distinct('pk')
if city.count() == 1:
city_obj = SourceCities.objects.create(
source_id=city_id,
source_obj=source,
city=city[0],
name=city_name,
)
cities_dict[city_id] = city_obj
else:
if 'slug="%s"' % city_slug not in data_nof_city:
data_nof_city += '<city name="%s" slug="%s"></city>' % (
city_name, city_slug)
if city_obj:
cinema_ig_id = u'%s__%s' % (cinema_slug.decode('utf-8'),
city_obj.city.kid)
if cinema_ig_id not in ignored_cinemas:
cinema_obj = cinemas_dict.get(cinema_id)
if not cinema_obj:
filter1 = {
'name__name': cinema_slug,
'name__status': 2,
'city': city_obj.city
}
cinema_kid = cinema_identification(
cinema_slug, filter1)
if cinema_kid:
try:
cinema = Cinema.objects.get(code=cinema_kid)
cinema_obj = SourceCinemas.objects.create(
source_id=cinema_id,
source_obj=source,
city=city_obj,
cinema=cinema,
name=cinema_name,
)
cinemas_dict[cinema_id] = cinema_obj
except Cinema.DoesNotExist:
pass
else:
if 'slug="%s"' % cinema_slug not in data_nof_cinema:
data_nof_cinema += '<cinema name="%s" slug="%s" city="%s" city_kid="%s"></cinema>' % (
cinema_name, cinema_slug, city_name,
city_obj.city.kid)
if cinema_obj:
film_table = table.find('table')
date_from = None
date_to = None
for tr in film_table.findAll('tr'):
film_name, film_slug, film_id = (None, None, None)
if ind == 0:
film_name = tr.find('b').string.encode(
'utf-8').strip()
film_slug = low(del_separator(film_name))
film_id = film_slug.decode('utf-8')
else:
showdate = ''
for f in tr.findAll('b'):
if f.find('span'):
showdate = f.find(
'span').string.encode(
'utf-8').strip()
else:
film_name = f.string.encode(
'utf-8').strip()
film_name = re.findall(
r'\«.+\»', film_name)[0]
film_name = film_name.replace(
'«', '').replace('»', '').strip()
film_slug = low(
del_separator(film_name))
film_id = film_slug.decode('utf-8')
if showdate and film_name:
try:
date_from, date_to = showdate.split(
'-')
date_from_day, date_from_month = date_from.strip(
).split('.')
date_to_day, date_to_month = date_to.strip(
).split('.')
except ValueError:
date_from, date_to = showdate.split(
' – ')
date_from_day, date_from_month = date_from.strip(
).split()
date_from_month = get_month(
date_from_month)
date_to_day, date_to_month = date_to.strip(
).split()
date_to_month = get_month(
date_to_month)
date_from = datetime.date(
today.year, int(date_from_month),
int(date_from_day))
date_to = datetime.date(
today.year, int(date_to_month),
int(date_to_day))
full_url = tr.find('a').get('href').encode('utf-8')
if film_id not in noffilms and film_id not in ignored:
obj = films.get(film_id)
next_step = checking_obj(obj)
if next_step:
if obj:
kid = obj.kid
else:
kid, info = film_identification(
film_slug,
None, {}, {},
source=source)
objt = None
if kid:
create_new, objt = unique_func(
fdict, kid, obj)
if create_new:
objt = create_sfilm(
film_id, kid, source,
film_name)
films[film_id] = objt
if not fdict.get(kid):
fdict[kid] = {
'editor_rel': [],
'script_rel': []
}
fdict[kid]['script_rel'].append(
objt)
elif not obj:
data_nof_film += xml_noffilm(
film_name, film_slug, None, None,
film_id.encode('utf-8'), info,
full_url, source.id)
noffilms.append(film_id)
if objt:
req_film = urllib.urlopen(full_url)
if req_film.getcode() == 200:
data_film = BeautifulSoup(
req_film.read()
) #, from_encoding="utf-8"
td = data_film.find(
'td', {
'class': 'news'
}).div.text.encode('utf-8')
showtime = []
if ind == 0:
showtime = re.findall(
r'\d+\:\d+\s\s?', td)
else:
if date_from and date_to:
if date_to < next_month:
showtimes = re.findall(
r'Начало сеансов:\s?[\d+\-\d+\,?\s?]+',
td)
times = []
for t in showtimes:
t = t.replace(
'Начало сеансов:',
'').split(',')
times = [
i.strip()
for i in t
if i.strip()
]
delta = date_to - date_from
for day in range(
delta.days +
1):
d = date_from + datetime.timedelta(
days=day)
for t in times:
hours, minutes = t.split(
'-')
dtime = datetime.datetime(
d.year,
d.month,
d.day,
int(hours),
int(minutes
))
showtime.append(
dtime)
for t in showtime:
if ind == 0:
hours, minutes = t.strip(
).split(':')
dtime = datetime.datetime(
today.year,
today.month, today.day,
int(hours),
int(minutes))
else:
dtime = t
sch_id = '%s%s%s%s' % (
dtime, cinema_slug,
city_slug,
film_id.encode('utf-8'))
sch_id = sch_id.replace(
' ', '').decode('utf-8')
if sch_id not in schedules:
SourceSchedules.objects.create(
source_id=sch_id,
source_obj=source,
film=objt,
cinema=cinema_obj,
dtime=dtime,
)
schedules.append(sch_id)
create_dump_file('%s_nof_city' % source.dump, settings.NOF_DUMP_PATH,
'<data>%s</data>' % data_nof_city)
create_dump_file('%s_nof_cinema' % source.dump, settings.NOF_DUMP_PATH,
'<data>%s</data>' % data_nof_cinema)
create_dump_file('%s_nof_film' % source.dump, settings.NOF_DUMP_PATH,
'<data>%s</data>' % data_nof_films)
cron_success('html', source.dump, 'schedules', 'Сеансы')
def get_premierzal_cinemas():
source = ImportSources.objects.get(url='http://www.premierzal.ru/')
cinemas = get_source_data(source, 'cinema', 'list')
cities_dict = get_source_data(source, 'city', 'dict')
cinemas_dict = {}
for i in Cinema.objects.all():
cinemas_dict[i.code] = i
ignored_cinemas = get_ignored_cinemas()
data_nof_cinema = ''
city = cities_dict.values()[0]
body = urllib.urlencode({
'city': city.name.encode('utf-8'),
})
url = '%stheatres?%s' % (source.url, body)
req = urllib.urlopen(url)
if req.getcode() == 200:
data = BeautifulSoup(req.read())
blocks = []
block1 = data.find('div', {'class': 'this_city_theatres'})
block2 = data.find('div', {'class': 'other_city_theatres'})
if block1:
blocks.append(block1)
if block2:
blocks.append(block2)
for ind, block in enumerate(blocks):
for a in block.findAll('a'):
cinema_name = a.text.encode('utf-8').strip().replace('"', '')
cinema_id = a.get('href').replace('/theatres/',
'').replace('/', '')
if ind == 0:
city_obj = city
else:
city_name, cinema_name = cinema_name.split(',')
cinema_name = cinema_name.strip()
city_slug = low(del_separator(city_name.strip()))
city_obj = cities_dict.get(city_slug.decode('utf-8'))
cinema_slug = low(del_separator(cinema_name))
if city_obj:
cinema_ig_id = u'%s__%s' % (cinema_slug.decode('utf-8'),
city_obj.city.kid)
if cinema_id.decode(
'utf-8'
) not in cinemas and cinema_ig_id not in ignored_cinemas:
filter1 = {
'name__name': cinema_slug,
'name__status': 2,
'city__id': city_obj.city_id
}
cinema = cinema_identification(cinema_slug, filter1)
cin_obj = cinemas_dict.get(cinema)
if cin_obj:
SourceCinemas.objects.create(
source_id=cinema_id,
source_obj=source,
city=city_obj,
cinema=cin_obj,
name=cinema_name,
)
cinemas.append(cinema_id.decode('utf-8'))
else:
data_nof_cinema += '<cinema name="%s" slug="%s" city="%s" city_kid="%s"></cinema>' % (
cinema_name, cinema_slug,
city_obj.name.encode('utf-8'),
city_obj.city.kid)
create_dump_file('%s_nof_cinema' % source.dump, settings.NOF_DUMP_PATH,
'<data>%s</data>' % data_nof_cinema)
cron_success('html', source.dump, 'cinemas', 'Кинотеатры')
def get_megamag():
'''
Получение urls фильмов
'''
import cookielib
def give_me_cookie():
cookie = cookielib.CookieJar()
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie),
urllib2.HTTPHandler())
return opener
ignored = get_ignored_films()
ignored_cinemas = get_ignored_cinemas()
source = ImportSources.objects.get(url='http://megamag.by/')
sfilm_clean(source)
megamag_cities_dict = get_source_data(source, 'city', 'dict')
megamag_cinemas_dict = get_source_data(source, 'cinema', 'dict')
films = {}
source_films = SourceFilms.objects.filter(source_obj=source)
for i in source_films:
films[i.source_id] = i
fdict = get_all_source_films(source, source_films)
cities_data = {}
data_nof_films = ''
data_nof_cinema = ''
data_nof_city = ''
noffilms = []
schedules_data = []
opener = give_me_cookie()
req = opener.open(urllib2.Request('http://kinoteatr.megamag.by/index.php'))
event_dict = {}
if req.getcode() == 200:
data = BeautifulSoup(req.read(), from_encoding="utf-8")
cities = data.find('div', id="box-region")
for i in cities.findAll('a'):
city_name = i.text.encode('utf-8')
city_slug = low(del_separator(city_name))
city_id = i.get('href').replace(
'http://kinoteatr.megamag.by/index.php?region_id=', '')
mcity = megamag_cities_dict.get(city_id)
if not mcity:
city = City.objects.filter(name__name=city_slug,
name__status=2).distinct('pk')
if city.count() == 1:
mcity = SourceCities.objects.create(
source_id=city_id,
source_obj=source,
city=city[0],
name=city_name,
)
else:
if 'slug="%s"' % city_slug not in data_nof_city:
data_nof_city += '<city name="%s" slug="%s"></city>' % (
city_name, city_slug)
if mcity:
cities_data[city_name] = mcity
try:
cinemas_tag = data.findAll('td',
{'class': 'Cinema_new_box_1_BoxText'},
limit=1)[0]
except IndexError:
cinemas_tag = None
if cinemas_tag:
for i in cinemas_tag.findAll('a'):
cinema_url = i.get('href')
cinema_id = cinema_url.replace(
'http://kinoteatr.megamag.by/index.php?cPath=', '')
cinema_obj = megamag_cinemas_dict.get(cinema_id)
opener = give_me_cookie()
try:
req2 = opener.open(urllib2.Request(cinema_url))
if req2.getcode() == 200:
schedules_page = BeautifulSoup(req2.read(),
from_encoding="utf-8")
city_name = schedules_page.findAll(
'div', {'class': 'object_param_value'},
limit=1)[0].text.encode('utf-8')
city_obj = cities_data.get(city_name)
if city_obj:
cinema_name = schedules_page.find(
'div', {
'class': 'object_title'
}).text.encode('utf-8')
cinema_name = cinema_name.replace('"', '').replace(
'Кинотеатр', '')
cinema_slug = low(del_separator(cinema_name))
cinema_ig_id = u'%s__%s' % (
cinema_slug.decode('utf-8'), city_obj.city.kid)
if cinema_ig_id not in ignored_cinemas:
if not cinema_obj:
filter1 = {
'name__name': cinema_slug,
'name__status': 2,
'city': city_obj.city
}
cinema_kid = cinema_identification(
cinema_slug, filter1)
if cinema_kid:
try:
cinema = Cinema.objects.get(
code=cinema_kid)
cinema_obj = SourceCinemas.objects.create(
source_id=cinema_id,
source_obj=source,
city=city_obj,
cinema=cinema,
name=cinema_name,
)
except Cinema.DoesNotExist:
pass
else:
cinema_kid = cinema_obj.cinema.code
if cinema_kid:
for event in schedules_page.findAll(
'td', {'class': 'eventsHeading'}):
if event.a.get('name'):
ev = event.a['name'].split('_')[1]
fname = event.a.text.encode(
'utf-8')
fid = event.a.get('href').replace(
'http://kinoteatr.megamag.by/newsdesk_info.php?newsdesk_id=',
'')
event_dict[int(ev)] = {
'name': fname,
'id': int(fid)
}
links = []
for td in schedules_page.findAll(
'td', {'class': 'main'}):
for link in td.findAll('a'):
l = link.get('href')
if l and 'cPath' in l:
links.append(l)
schedules_data.append({
'mcity':
city_obj,
'city':
city_obj.city,
'mcinema':
cinema_obj,
'cinema':
cinema_kid,
'schedules':
set(links)
})
else:
if 'slug="%s"' % cinema_slug not in data_nof_cinema:
data_nof_cinema += '<cinema name="%s" slug="%s" city="%s" city_kid="%s"></cinema>' % (
cinema_name, cinema_slug,
city_name, city_obj.city.kid)
except httplib.HTTPException:
pass
create_dump_file('%s_nof_city' % source.dump, settings.NOF_DUMP_PATH,
'<data>%s</data>' % data_nof_city)
create_dump_file('%s_nof_cinema' % source.dump, settings.NOF_DUMP_PATH,
'<data>%s</data>' % data_nof_cinema)
megamag = get_source_data(source, 'schedule', 'list')
for obj in schedules_data:
cinema_object = obj['mcinema']
for index, i in enumerate(obj['schedules']):
opener = give_me_cookie()
try:
req3 = opener.open(urllib2.Request(i))
if req3.getcode() == 200:
id_schedule = i.replace(
'http://kinoteatr.megamag.by/index.php?cPath=',
'').encode('utf-8')
if id_schedule not in megamag:
sch_page = BeautifulSoup(req3.read(),
from_encoding="utf-8")
tables = sch_page.findAll('table', {
'class':
'Cinema_new_box_2_TemplateCenterPart'
},
limit=1)[0]
main_table = tables.findAll('table',
cellpadding='4',
limit=1)[0]
tr = main_table.findAll('tr')[1]
td = tr.findAll('strong')
event_id = id_schedule.split('_')[2]
film_data = event_dict.get(int(event_id))
if film_data:
film_name = film_data['name']
film_name_slug = low(
del_separator(del_screen_type(film_name)))
film_id = film_data['id']
if film_id not in noffilms and film_name_slug.decode(
'utf-8') not in ignored:
obj = films.get(
str(film_id).decode('utf-8'))
next_step = checking_obj(obj)
if next_step:
if obj:
kid = obj.kid
else:
kid, info = film_identification(
film_name_slug,
None, {}, {},
source=source)
objt = None
if kid:
create_new, objt = unique_func(
fdict, kid, obj)
if create_new:
objt = create_sfilm(
film_id, kid, source,
film_name)
films[str(film_id).decode(
'utf-8')] = objt
if not fdict.get(kid):
fdict[kid] = {
'editor_rel': [],
'script_rel': []
}
fdict[kid][
'script_rel'].append(objt)
elif not obj:
data_nof_films += xml_noffilm(
film_name, film_name_slug,
None, None, film_id, info,
None, source.id)
noffilms.append(film_id)
if objt:
dtime_info = td[1].text.encode(
'utf-8').split()
year_info = datetime.datetime.now(
).year
day_info = int(dtime_info[0])
month_low = low(
dtime_info[1].replace(',', ''))
month_info = int(
get_month(month_low))
time_info = dtime_info[-1].replace(
'(', '').replace(')',
'').split(':')
dtime = datetime.datetime(
year_info, month_info,
day_info, int(time_info[0]),
int(time_info[1]), 0)
SourceSchedules.objects.create(
source_id=id_schedule,
source_obj=source,
cinema=cinema_object,
film=objt,
dtime=dtime,
)
except httplib.HTTPException:
open('%s/httplib_errors.txt' % settings.API_DUMP_PATH,
'a').write('%s\n' % i)
# на каждом 60 обращении к источнику делаю паузу в 2 секунды
if (index + 1) % 60 == 0:
time.sleep(2.0)
create_dump_file('%s_nof_film' % source.dump, settings.NOF_DUMP_PATH,
'<data>%s</data>' % data_nof_films)
cron_success('html', source.dump, 'schedules', 'Сеансы')
def get_rambler_cinemas():
data_nof_cinema = ''
source = ImportSources.objects.get(url='http://www.rambler.ru/')
cinemas_ids = get_source_data(source, 'cinema', 'list')
rambler_cities_dict = get_source_data(source, 'city', 'dict')
cinemass = Cinema.objects.all()
cinemass_dict = {}
for i in cinemass:
cinemass_dict[i.code] = i
ignored_cinemas = get_ignored_cinemas()
'''
# LOCALHOST
f = open('%s/dump_rambler_cinema.xml' % settings.API_DUMP_PATH, 'r')
xml = BeautifulSoup(f.read(), from_encoding="utf-8")
f.close()
if xml:
if xml: # --- end localhost
'''
# SERVER
f = open('%s/dump_rambler_index.xml' % settings.API_DUMP_PATH, 'r')
xml_index = BeautifulSoup(f.read(), from_encoding="utf-8")
f.close()
places = xml_index.find('places')
filenames = []
for i in places.findAll('file'):
filename = i.get('filename')
if filename:
filenames.append(filename)
for i in filenames:
url = 'http://api.kassa.rambler.ru/v2/%s/xml/Movie/export/sale/%s' % (
RAMBLER_API_KEY, i)
req = urllib.urlopen(url)
if req.getcode() == 200:
xml = BeautifulSoup(req.read(),
from_encoding="utf-8") # --- end server
for i in xml.findAll('place'):
id = i.objectid.string
name = i.find('name').string.encode('utf-8')
name_slug = low(del_separator(name))
address = i.address.string.encode(
'utf-8') if i.address.string else None
latitude = i.latitude.string
longitude = i.longitude.string
city_id = i.cityid.string
city_obj = rambler_cities_dict.get(city_id)
if city_obj:
cinema_ig_id = u'%s__%s' % (name_slug.decode('utf-8'),
city_obj.city.kid)
if id not in cinemas_ids and cinema_ig_id not in ignored_cinemas:
filter1 = {
'name__name': name_slug,
'name__status': 2,
'city__id': city_obj.city_id
}
cinema = cinema_identification(name_slug, filter1)
cin_obj = cinemass_dict.get(cinema)
if cin_obj:
SourceCinemas.objects.create(
source_id=id,
source_obj=source,
city=city_obj,
cinema=cin_obj,
name=name,
address=address,
latitude=latitude,
longitude=longitude,
)
else:
if 'slug="%s"' % name_slug not in data_nof_cinema:
name_city = city_obj.name
data_nof_cinema += '<cinema name="%s" slug="%s" city="%s" city_kid="%s"></cinema>' % (
name, name_slug, name_city.encode('utf-8'),
city_obj.city.kid)
create_dump_file('%s_nof_cinema' % source.dump, settings.NOF_DUMP_PATH,
'<data>%s</data>' % data_nof_cinema)
cron_success('xml', source.dump, 'cinemas', 'Кинотеатры')
def get_luxor_cinemas():
query = 'QueryCode=GetHalls'
data = get_luxor_data_by_socket(query)
source = ImportSources.objects.get(url='http://luxor.ru/')
#create_dump_file('%s_cinemas' % source.dump, settings.API_DUMP_PATH, data)
data_nof_cinema = ''
data_nof_city = ''
data_nof_hall = ''
nofcities = []
nofcinemas = []
cinemas = get_source_data(source, 'cinema', 'dict')
cities = get_source_data(source, 'city', 'dict')
ignored_cinemas = get_ignored_cinemas()
halls = get_source_data(source, 'hall', 'dict')
'''
xml = open('%s/dump_%s_cinemas.xml' % (settings.API_DUMP_PATH, source.dump), 'r')# temp
data = xml.read()# temp
xml.close()# temp
'''
xml_data = BeautifulSoup(data, from_encoding="utf-8")
for cinema in xml_data.findAll('theatre'):
cinema_id = cinema['id'].encode('utf-8')
cinema_name = cinema.find('name').text.encode('utf-8')
cinema_name = cinema_name.replace('[CDATA[', '').replace(']]',
'').strip()
cinema_slug = low(del_separator(cinema_name))
cinema_alt_name = 'Люксор'
cinema_alt_slug = 'люксор'
address = cinema.find('address').text.encode('utf-8')
address = address.replace('[CDATA[',
'').replace(']]', '').replace('"',
"'").strip()
city_obj = cities.get(cinema_slug.decode('utf-8'))
if not city_obj and cinema_slug not in nofcities:
city = City.objects.filter(name__name=cinema_slug,
name__status=2).distinct('pk')
if city.count() == 1:
city_obj = SourceCities.objects.create(
source_id=cinema_slug,
source_obj=source,
city=city[0],
name=cinema_name,
)
cities[cinema_slug] = city_obj
else:
data_nof_city += '<city name="%s" slug="%s" info="%s"></city>' % (
cinema_name, cinema_slug, address)
nofcities.append(cinema_slug)
if city_obj:
cinema_obj = cinemas.get(cinema_id)
city_kid = city_obj.city.kid
cinema_ig_id = u'%s__%s' % (cinema_slug.decode('utf-8'), city_kid)
if cinema_ig_id not in ignored_cinemas:
if not cinema_obj:
filter1 = {
'name__name': cinema_slug,
'name__status': 2,
'city__kid': city_kid
}
cinema_kid = cinema_identification(cinema_slug, filter1,
{}, city_kid)
if cinema_kid:
cin_obj = Cinema.objects.get(code=cinema_kid)
cinema_obj = SourceCinemas.objects.create(
source_id=cinema_id,
source_obj=source,
city=city_obj,
cinema=cin_obj,
name=cinema_name,
)
cinemas[cinema_id] = cinema_obj
else:
city_name = ''
for i in city_obj.city.name.all():
if i.status == 1:
city_name = i.name.encode('utf-8')
data_nof_cinema += '<cinema name="Люксор %s" slug="%s" city="%s" city_kid="%s"></cinema>' % (
cinema_name, cinema_slug, city_name, city_kid)
if cinema_obj:
for i in cinema.findAll('hall'):
hall_id = i['id'].encode('utf-8')
hall_name = i.find('name').string.encode('utf-8')
hall_name = hall_name.replace('[CDATA[',
'').replace(']]',
'').strip()
hall_slug = low(del_separator(hall_name))
hall_obj = halls.get(hall_id)
if not hall_obj:
hall_obj = Hall.objects.filter(
name__name=hall_slug,
cinema=cinema_obj.cinema).distinct('pk')
if hall_obj.count() == 1:
hall_kid = hall_obj[0].kid
SourceHalls.objects.create(
source_id=hall_id,
source_obj=source,
cinema=cinema_obj,
name=hall_name,
kid=hall_kid,
)
else:
city_name = ''
for i in city_obj.city.name.all():
if i.status == 1:
city_name = i.name.encode('utf-8')
cinema_kid = cinema_obj.cinema.code
id = '%s%s%s%s' % (city_kid, cinema_kid,
hall_name, hall_slug)
id = id.replace(' ', '')
data_nof_hall += '<hall city="%s" city_kid="%s" cinema="Люксор %s" cinema_kid="%s" name="%s" slug="%s" id="%s"></hall>' % (
city_name, city_kid, cinema_name,
cinema_kid, hall_name, hall_slug, id)
create_dump_file('%s_nof_city' % source.dump, settings.NOF_DUMP_PATH,
'<data>%s</data>' % data_nof_city)
create_dump_file('%s_nof_cinema' % source.dump, settings.NOF_DUMP_PATH,
'<data>%s</data>' % data_nof_cinema)
create_dump_file('%s_nof_hall' % source.dump, settings.NOF_DUMP_PATH,
'<data>%s</data>' % data_nof_hall)
cron_success('xml', source.dump, 'cities_and_cinemas',
'Города и кинотеатры')
def get_surkino_cinemas():
data_nof_cinema = ''
source = ImportSources.objects.get(url='http://surkino.ru/')
city_name = 'Сургут'
city_slug = low(del_separator(city_name))
city = City.objects.get(name__name=city_name, name__status=1)
city_obj, city_created = SourceCities.objects.get_or_create(
source_id=city_slug,
source_obj=source,
defaults={
'source_id': city_slug,
'source_obj': source,
'city': city,
'name': city_name,
})
cinemas = get_source_data(source, 'cinema', 'list')
ignored_cinemas = get_ignored_cinemas()
req = urllib.urlopen(source.url)
if req.getcode() == 200:
data = BeautifulSoup(req.read(), from_encoding="windows-1251")
div = data.find('div', {'class': 'cinemas'})
div_classes = ['ciname', 'ciname last']
for cl in div_classes:
for cinema_tag in div.findAll('div', {'class': cl}):
cinema_name = cinema_tag.a.get('title').encode(
'utf-8').replace('Кинотеатр ', '')
cinema_slug = low(del_separator(cinema_name))
cinema_id = cinema_tag.a.get('href').replace('?cinema=', '')
cinema_ig_id = u'%s__%s' % (cinema_slug.decode('utf-8'),
city_obj.city.kid)
if cinema_id not in cinemas and cinema_ig_id not in ignored_cinemas:
filter1 = {
'name__name': cinema_slug,
'name__status': 2,
'city__id': city_obj.city_id
}
cinema_kid = cinema_identification(cinema_slug, filter1)
if cinema_kid:
try:
cinema = Cinema.objects.get(code=cinema_kid)
cinema_obj = SourceCinemas.objects.create(
source_id=cinema_id,
source_obj=source,
city=city_obj,
cinema=cinema,
name=cinema_name,
)
except Cinema.DoesNotExist:
pass
else:
if 'slug="%s"' % cinema_slug not in data_nof_cinema:
data_nof_cinema += '<cinema name="%s" slug="%s" city="%s" city_kid="%s"></cinema>' % (
cinema_name, cinema_slug,
city_obj.name.encode('utf-8'),
city_obj.city.kid)
create_dump_file('%s_nof_cinema' % source.dump, settings.NOF_DUMP_PATH,
'<data>%s</data>' % data_nof_cinema)
cron_success('html', source.dump, 'cinemas', 'Кинотеатры')