def save_sms_sources(request):
'''
Парсер файла sms.txt
'''
# получаю объект для русского языка
lang = Language.objects.get(pk=1)
list_all = []
sms_file = open(rel('sources/sms.txt'), 'r')
# получаю данные из файла
for line in sms_file.read().split('\n'):
listt = []
for i, l in enumerate(line.split('\t')):
if i == 1: listt.append(capit(low(l)))
elif i == 2: listt.append(l.split(' ')[0])
elif i == 4: listt.append(l)
# складываю данные в список
list_all.append(listt)
sms_file.close()
# получаю объект для источника sms
source = ImportSources.objects.get(source='SMS')
# иду по списку с данными
for l in list_all:
try:
if l[1] != 'ЗАКРЫТ':
# очищаю название от спец.символов
slug_city = low(del_separator(l[1]))
# ищу по очищенному названию
try: city = City.objects.get(name__name=slug_city)
except City.DoesNotExist:
# если не найдено, то ищу по названию из источника
try: city = City.objects.get(name__name=l[1])
except City.DoesNotExist:
# если не найдено, то ищу по названию из источника в нижнем регистре
try: city = City.objects.get(name__name=capit(low(l[1])))
except City.DoesNotExist: city = None
if city:
# очищаю название от спец.символов
slug_cinema = low(del_separator(l[0]))
# ищу по очищенному названию
try: cinema = Cinema.objects.get(name__name=slug_cinema, city=city.id)
except Cinema.DoesNotExist:
# если не найдено, то ищу по названию из источника
try: cinema = Cinema.objects.get(name__name=l[0], city=city.id)
except Cinema.DoesNotExist: cinema = None
if cinema:
# получаю/создаю залы для этого кинотеатра в этом городе
name1 = create_hallname(1, lang, 'без указания зала')
name2 = create_hallname(2, lang, 'безуказаниязала')
hall = create_hall((name1, name2), 0, 0, cinema)
# записываю url источника в БД, для последующего получения данных о сеансах
try: HallsSources.objects.get(id_hall=hall, source=source, url_hall_sources=l[2])
except HallsSources.DoesNotExist: HallsSources(id_hall=hall, source=source, url_hall_sources=l[2]).save()
else:
# если не найден кинотеатр, то запись в лог
logger(**{'event': 2, 'code': 2, 'bad_obj': l[0], 'obj1': l[1], 'obj2': l[2], 'extra': city.id})
else:
# если не найден город, то запись в лог
logger(**{'event': 2, 'code': 1, 'bad_obj': capit(low(l[1])), 'obj2': l[2]})
except IndexError: pass
return HttpResponseRedirect(reverse("main_kai"))
def nowru_ident():
source = ImportSources.objects.get(url='http://www.now.ru/')
ignored = get_ignored_films()
data_nof_film = ''
nowru_data = Nowru.objects.filter(kid=None)
for i in nowru_data:
name_ru_slug = low(del_separator(i.name_ru.encode('utf-8')))
if name_ru_slug.decode('utf-8') not in ignored:
name_en_slug = low(del_separator(i.name_en.encode('utf-8')))
kid, info = film_identification(name_ru_slug,
name_en_slug, {}, {},
year=i.year,
source=source)
if kid:
i.kid = kid
i.save()
else:
if 'slug="%s"' % name_ru_slug not in data_nof_film:
name_ru = i.name_ru.encode('utf-8')
name_en = i.name_en.encode('utf-8')
data_nof_film += xml_noffilm(name_ru, name_ru_slug,
name_en, name_en_slug,
i.nowru_id, info, None,
source.id)
create_dump_file('%s_nof_film' % source.dump, settings.NOF_DUMP_PATH,
'<data>%s</data>' % data_nof_film)
cron_success('xml', source.dump, 'players', 'Онлайн плееры')
def person_create_func(name_ru, parental, name_en):
person_obj = AfishaPersons.objects.using('afisha').create(
birth_year = 0,
birth_mounth = 0,
birth_day = 0,
male = 0,
national = 0,
country_id = 0,
imdb = 0
)
person = Person.objects.create(kid = person_obj.id)
names_list = [
{'name': name_ru.strip(), 'status': 1, 'lang': 1},
{'name': low(del_separator(name_ru.strip().encode('utf-8'))), 'status': 2, 'lang': 1},
{'name': name_en.strip(), 'status': 1, 'lang': 2},
{'name': low(del_separator(name_en.strip().encode('utf-8'))), 'status': 2, 'lang': 2},
{'name': parental.strip(), 'status': 3, 'lang': 1},
]
for i in names_list:
if i['name']:
if i['status'] == 1:
try:
afisha_person_name_create(person_obj, i['name'], i['lang'])
except db.backend.Database._mysql.OperationalError:
i['name'] = i['name'].encode('ascii', 'xmlcharrefreplace')
afisha_person_name_create(person_obj, i['name'], i['lang'])
name, created = person_name_create(i['name'], i['lang'], i['status'])
person.name.add(name)
return person_obj
def get_imdb_film_list():
source = ImportSources.objects.get(url='http://www.imdb.com/')
url = '%scalendar/?region=us' % source.url
opener = give_me_cookie()
req = opener.open(urllib2.Request(url))
xml = ''
ids = []
if req.getcode() == 200:
data = BeautifulSoup(req.read(), from_encoding="utf-8")
div = data.find('div', id="main")
old_date = ''
for h4 in div.findAll('h4'):
release = h4.string.encode('utf-8')
day, month, year = release.split()
month = get_month_en(low(month))
rel_date = '%s-%s-%s' % (year, month, day)
xml += '<date v="%s">' % rel_date
ul = h4.find_next('ul')
for li in ul.findAll('li'):
year = li.find('span', {'class': "year_type"}).string.encode('utf-8')
if 'documentary' not in low(year):
year = re.findall(r'\d+', year)
if year:
details = li.find('i')
if details:
details = str(details).encode('utf-8').replace('<i>','').replace('</i>','')
details = details.replace('(','').replace(')','')
else:
details = ''
if 'limited' not in low(details) and 'fest' not in low(details) or 'tv premiere' not in low(details):
film_name = li.a.string.encode('utf-8').replace('"', '"').replace('&','&')
film_slug = low(del_separator(film_name))
full_url = li.a.get('href').encode('utf-8')
imdb_id = full_url.replace('/title/tt', '').replace('/', '')
xml += '<film n="%s" s="%s" y="%s" id="%s" d="%s" r="%s"></film>' % (film_name, film_slug, year[0], imdb_id, details, rel_date)
ids.append(imdb_id)
xml += '</date>'
ids = ';'.join(set(ids))
xml = '<data><ids value="%s">%s</ids></data>' % (ids, xml)time
create_dump_file('%s_film_list' % source.dump, settings.API_DUMP_PATH, xml)
cron_success('html', source.dump, 'films_list', 'Список релизов')
def raspishi_relations():
source = ImportSources.objects.get(url='http://распиши.рф/')
ignored = get_ignored_films()
data_nof_film = ''
domain = u'распиши.рф'
url = 'http://%s/getfilmxml.php' % domain.encode('idna')
req = urllib.urlopen(url)
if req.getcode() == 200:
films_rid = list(
RaspishiRelations.objects.exclude(kid=0).values_list('rid',
flat=True))
xml_data = BeautifulSoup(req.read(), from_encoding="utf-8")
for i in xml_data.findAll('movie'):
id = int(i['id'])
if id not in films_rid:
name_ru = i.find('name').text.encode('utf-8')
name_en = i.find('nameeng').text.encode('utf-8')
name_ru = re.sub(r'\(.*?\)', '', name_ru).strip()
name_en = re.sub(r'\(.*?\)', '', name_en).strip()
name_slug = low(del_separator(del_screen_type(name_ru)))
name_en_slug = low(del_separator(del_screen_type(name_en)))
if name_slug.decode('utf-8') not in ignored:
try:
kid, info = film_identification(name_slug,
None, {}, {},
source=source)
if kid:
created = RaspishiRelations.objects.create(
rid=id,
kid=kid,
name_ru=name_ru,
name_en=name_en,
)
else:
data_nof_film += xml_noffilm(
name_ru, name_slug, name_en, name_en_slug, id,
info, None, source.id)
except db.backend.Database._mysql.OperationalError:
pass
create_dump_file('%s_nof_film' % source.dump, settings.NOF_DUMP_PATH,
'<data>%s</data>' % data_nof_film)
cron_success('xml', source.dump, 'films', 'Укр. сеансы')
def get_cinemate_cc_film(data, source, ignored, noffilms):
flist = []
for div in data.findAll('div', {'class': "movie-brief"}):
h3 = div.find('h3')
a = h3.find('a')
film_url = a.get('href')
film_id = int(film_url.replace('/movie/', '').replace('/', ''))
film_name = a.text.encode('utf-8')
film_slug = low(del_separator(film_name))
if film_slug.decode(
'utf-8') not in ignored and film_id not in noffilms:
full_url = '%s%s' % (source.url, film_url.lstrip('/'))
film_year = int(
h3.find('small').text.encode('utf-8').replace('(', '').replace(
')', ''))
next = False
ul = div.find('ul')
for link in ul.findAll('a'):
a_txt = link.text.encode('utf-8').strip()
if a_txt == 'Скачать':
next = True
if next:
flist.append({
'id': film_id,
'name': film_name,
'slug': film_slug,
'year': film_year,
'url': full_url,
})
return flist
def imdb_film_ident():
source = ImportSources.objects.get(url='http://www.imdb.com/')
films = Films.objects.filter(kid=None)
films_ids = [i.imdb_id for i in films]
exist_films = Film.objects.using('afisha').filter(idalldvd__in=films_ids)
exist_ids = {}
for i in exist_films:
exist_ids[i.idalldvd] = i.id
data_nof_film = ''
for i in films:
name = None
for j in i.name.filter(status=1, language__id=2):
name = j.name.encode('utf-8')
slug = low(del_separator(name))
kid = exist_ids.get(long(i.imdb_id))
if kid:
i.kid = kid
i.save()
else:
full_url = '%stitle/tt%s/' % (source.url, i.imdb_id)
data_nof_film += xml_noffilm(name, slug, None, None, i.imdb_id, 'Фильм не найден', full_url.encode('utf-8'), source.id)
create_dump_file('%s_nof_film' % source.dump, settings.NOF_DUMP_PATH, '<data>%s</data>' % data_nof_film)
cron_success('html', source.dump, 'films_ident', 'Идентификация')
def imdb_search2(imdb_id, name, year, kid):
film_name = name
slug = low(del_separator(film_name.encode('utf-8')))
film_name = film_name.encode('ascii', 'xmlcharrefreplace')
xml = '<film n="%s" s="%s" y="%s" id="%s" d="" r=""></film>' % (film_name, slug, str(year).encode('utf-8'), str(imdb_id).encode('utf-8'))
data = exp_film_data(imdb_id)
if data:
if data.get('double'):
return simplejson.dumps(data)
else:
if not data['kid']:
pass
elif int(data['kid']) != int(kid):
return simplejson.dumps({'status': True, 'redirect': True, 'kid': data['kid']})
data_nof_persons, distr_nof_data, dump, good = get_imdb_data(xml, False, 1, [int(imdb_id),], True, kid)
if good:
data = exp_film_data(imdb_id)
if not data:
data = {'status': False}
else:
data = {'status': False}
if kid:
cache.delete_many(['get_film__%s' % kid, 'film__%s__fdata' % kid])
return simplejson.dumps(data)
def part_search(model, var, name, extra):
'''
Поиск по частичному совпадению
'''
res_list = []
# очищаю от формата изображения (3D, 2D ...), привожу в нижний регистр
clear_name = low(del_screen_type(name.encode('utf-8')))
# заменяю некоторые символы на символ пробела
clear_name = clear_name.replace('(', ' ').replace(')', ' ').replace(',', ' ').replace('.', ' ').replace(':', ' ')
# для городов/фильмов минимальное кол-во символов в с строке поиска должно быть не менее 3,
# а для кинотеатров 2, иначе выведу сообщение об ошибке
max_char = 3 if var == 1 or var == 2 else 2
# разбиваю название по пробелу и произвожу поиск по каждой части названия
for cn in clear_name.split(' '):
if len(cn.decode('utf-8')) >= max_char:
#result = model.objects.filter(name__name__contains=cn).distinct() # для новой БД
# для старой БД ----
#if var == 1:
# result = model.objects.filter(name__contains=cn)
#else: result = model.objects.filter(name__name__contains=cn).distinct()
result = search(model, var, cn, extra)
# ------------------
# результаты складываю в список и возвращаю
for i in result:
res_list.append(i)
return res_list
def person_name_detect(request, ru, en):
try:
film_editor = is_film_editor(request)
if film_editor:
name = escape(strip_tags(ru)).encode('utf-8').strip()
en = escape(strip_tags(en)).encode('utf-8').strip()
slug_ru = low(del_separator(name))
slug_en = low(del_separator(en))
queries = []
if name:
queries.append(Q(name__icontains=slug_ru, status=1))
if en:
queries.append(Q(name__icontains=en, status=1))
query = queries.pop()
for item in queries:
query |= item
data = list(NamePerson.objects.filter(query, language__id__in=(1,2), person__kid__gt=0).values('language', 'person__kid', 'name'))
names = {}
for i in data:
if not names.get(i['person__kid']):
names[i['person__kid']] = {'ru': '', 'en': '', 'id': i['person__kid']}
if i['language'] == 1:
names[i['person__kid']]['ru'] = i['name']
elif i['language'] == 2:
names[i['person__kid']]['en'] = i['name']
names = sorted(names.values(), key=operator.itemgetter('ru'))
txt = ''
for i in names:
txt += u'<div style="border-bottom:1px solid #CCC; padding:5px; background:#EBEBEB; min-width: 300px;"><a href="http://kinoinfo.ru/person/%s/" target="_blank">%s / %s</a></div>' % (i['id'], i['ru'], i['en'])
if txt:
txt = u'В базе есть похожие персоны:<br />%s' % txt
return simplejson.dumps({
'status': True,
'content': txt,
})
except Exception as e:
open('errors.txt','a').write('%s * (%s)' % (dir(e), e.args))
def organization_uni_temp(request):
orgs = Organization.objects.all().order_by('name')
for i in orgs:
result = unidecode(i.name)
result = re.findall(ur'[a-z0-9]+', low(result))
result = '-'.join(result) if result else ''
i.uni_slug = '%s-%s' % (result, i.id)
i.save()
return HttpResponse(str())
def get_rutracker_topics_closed():
REG_SIZE = re.compile(r'\[\d+\.?\d+?\s?\w+\]')
REG_SLUG = re.compile(ur'[a-zа-я0-9]+')
source = ImportSources.objects.get(url='http://rutracker.org/')
films = SourceFilms.objects.filter(source_obj=source)
films_dict = {}
for i in films:
films_dict[i.name_alter] = i
url = 'http://rutracker.org/forum/index.php?closed=1'
req = urllib.urlopen(url)
for_del = []
if req.getcode() == 200:
data = BeautifulSoup(req.read(), from_encoding="windows-1251")
nav = data.find('ul')
if nav:
for i in nav.findAll('li'):
title = i.b.text.strip().encode('utf-8')
if ' / ' in title:
name_alt = re.findall(REG_SLUG, low(title).decode('utf-8'))
name_alt = ''.join(name_alt)
obj = films_dict.get(name_alt)
if obj:
for_del.append(obj.id)
SourceFilms.objects.filter(pk__in=set(for_del)).delete()
'''
if req.getcode() == 200:
data = BeautifulSoup(req.read(), from_encoding="utf-8")
return HttpResponse(str(data))
nav = data.find('div', {'class': 'cl-pg'})
for a in nav.findAll('a'):
link = a.get('href').encode('utf-8')
if 'start' in link:
new_url = '%sforum/%s' % (source.url, link)
links.append(new_url)
for url in links:
req = urllib.urlopen(url)
if req.getcode() == 200:
data = BeautifulSoup(req.read(), from_encoding="utf-8")
for i in data.findAll('b'):
title = i.text.encode('utf-8').strip()
if ' / ' in title:
name_alt = re.findall(REG_SLUG, low(title).decode('utf-8'))
name_alt = ''.join(name_alt)
obj = films_dict.get(name_alt)
if obj:
obj.delete()
'''
cron_success('xml', source.dump, 'films_closed', 'Закрытые фильмы')
def addfile(request, m=None):
if m and m != 'm':
raise Http404
if request.POST:
from user_registration.func import md5_string_generate
from api.func import resize_image
next = request.POST.get('fnext')
new = request.POST.get('new_msg_id')
f = request.FILES.get('file')
# если есть файл
if f and f.size < 5000000:
file_format = low(f.name.encode('utf-8'))
img_format = re.findall(r'\.(jpg|png|jpeg|bmp|gif)$', file_format)
# если подходит формат
if img_format:
img_path = '%s/%s' % (settings.WF_PATH, 'women')
try: os.makedirs(img_path)
except OSError: pass
# если существует сообщение для файла
try:
obj = WFOpinion.objects.using('afisha').get(pk=new)
except WFOpinion.DoesNotExist:
pass
else:
# если юзер загружающий файл является автором сообщения
if obj.user_id == request.profile.kid:
img_obj = f.read()
img_name = '%s.%s' % (new, img_format[0])
img_path_tmp = '%s/%s' % (img_path, img_name)
with open(img_path_tmp, 'wb') as f:
f.write(img_obj)
resized = resize_image(1000, None, img_obj, 1500)
if resized:
resized.save(img_path_tmp)
if next:
if m:
return HttpResponseRedirect(reverse('women_forum', kwargs={'m': m, 'topic': next}))
else:
return HttpResponseRedirect(reverse('women_forum', kwargs={'topic': next}))
if m:
return HttpResponseRedirect(reverse('women_forum', kwargs={'m': m}))
else:
return HttpResponseRedirect(reverse('women_forum'))
else:
raise Http404
def org_slufy_names(request):
orgs = Organization.objects.all()
for i in orgs:
lo = low(i.name.encode('utf-8'))
name_slug = re.findall(ur'[a-zа-я0-9]', lo.decode('utf-8'))
name_slug = ''.join(name_slug) if name_slug else ''
i.slug = name_slug
i.save()
return HttpResponse(str())
def get_name_film_obj(film):
'''
Получение объекта названия фильма
'''
# очищаю названия от формата изображения (3D, 2D ...)
f = del_screen_type(film)
# очищаю названия от спец.символов и привожу в нижний регистр
f = low(del_separator(f))
# ищу по очищенному названию
try: name = NameProduct.objects.filter(name=f)[0]
except IndexError:
# если не найден, ищу по названию источника
try: name = NameProduct.objects.filter(name=film)[0]
except IndexError:
# если не найден, ищу по названию источника в нижнем регистре
try: name = NameProduct.objects.filter(name=low(film))[0]
except IndexError:
# если не найден, ищу по названию источника в нижнем регистре с заглавной буквы
try: name = NameProduct.objects.filter(name=capit(film))[0]
except IndexError: name = None
return name
def create_news(request, tags, name, text, reader_type, nick=0, extra=None, visible=None):
profile = request.profile
current_site = request.current_site
subdomain = request.subdomain if request.subdomain else 0
if current_site.domain in ('kinoinfo.ru', 'kinoafisha.ru'):
subdomain = 0
language = None
if current_site.domain == 'imiagroup.com.au':
try: language = Language.objects.get(code=request.current_language)
except Language.DoesNotExist: pass
tags_list = []
for i in tags:
tag = i.strip()
t_list = (tag, capit(tag), low(tag))
tag_obj = None
for t in t_list:
try:
tag_obj = NewsTags.objects.get(name=t)
break
except NewsTags.DoesNotExist: pass
if not tag_obj:
tag_obj = NewsTags.objects.create(name=t_list[0])
tags_list.append(tag_obj)
if visible is None:
visible = True if text else False
news = News.objects.create(
title = name,
autor = profile,
site = current_site,
subdomain = subdomain,
language = language,
text = text,
visible = visible,
reader_type = reader_type,
autor_nick = nick,
extra = extra,
)
for i in set(tags_list):
news.tags.add(i)
NewsTags.objects.filter(news=None).delete()
return news
def get_news_tags(request, id, arr):
#try:
news = News.objects.get(pk=id)
if arr:
profile = RequestContext(request).get('profile')
is_editor = False
try:
org = OrganizationNews.objects.select_related('organization').get(
news=news)
if profile in org.organization.editors.all():
is_editor = True
except OrganizationNews.DoesNotExist:
pass
if request.user.is_superuser or is_editor or request.is_admin:
arr = set(arr)
tags_error = False
tags_objs = {}
tags_list = []
tags = NewsTags.objects.all()
for i in tags:
tags_objs[i.name] = i
for i in arr:
t_list = (i, capit(i).decode('utf-8'), low(i).decode('utf-8'))
tag_obj = None
for t in t_list:
tag_obj = tags_objs.get(t)
if tag_obj:
break
if not tag_obj:
tag_obj = NewsTags.objects.create(name=t_list[0])
tags_list.append(tag_obj)
org_tags = [i for i in news.tags.all()]
for i in org_tags:
news.tags.remove(i)
for i in tags_list:
news.tags.add(i)
return simplejson.dumps({
'status': True,
'err': False,
'content': sorted(arr)
})
return simplejson.dumps({'status': False})
def imdb_person_data(id):
url = 'http://www.imdb.com/name/nm%s/bio' % id
resp, content = httplib2.Http(disable_ssl_certificate_validation=True).request(url)
result = {'bio': '', 'birth': '', 'place': '', 'country': '', 'poster': ''}
if resp['status'] == '200':
data = BeautifulSoup(content, "html5lib", from_encoding="utf-8")
table = data.find('table', id="overviewTable")
birth_day = 0
birth_month = 0
birth_year = 0
if table:
trs = table.findAll('tr')
for a in trs[0].findAll('a'):
href = a.get('href').encode('utf-8')
if '?birth_monthday' in href:
birth_day, birth_month = a.text.strip().split()
birth_month = get_month_en(low(birth_month))
elif '?birth_year' in href:
birth_year = a.text.encode('utf-8')
elif '?birth_place' in href:
result['place'] = a.text.encode('utf-8')
result['country'] = a.text.split(',')[-1].split('[')[0].strip()
if birth_day and birth_month and birth_year:
result['birth'] = datetime.date(int(birth_year), int(birth_month), int(birth_day))
bio_block = data.find('a', {'name': 'mini_bio'}).find_next('p')
if bio_block:
result['bio'] = bio_block.text.strip().encode('utf-8')
poster = data.find('img', {'class': 'poster'})
if poster:
poster = poster.get('src').split('._V1_')[0]
poster += '._V1_SX640_SY720_.jpg'
result['poster'] = poster
return result
def imdb_person_search(request, pid, name, exist):
try:
from person.views import person_name_create
from release_parser.imdb import imdb_person_searching
if request.user.is_superuser:
name = escape(strip_tags(name)).encode('utf-8').strip()
slug = low(del_separator(name))
person = Person.objects.get(pk=pid)
# если не было имени (en), то создаю
if not exist:
if name:
exist = True
person_names = person.name.all()
names = [
{'name': name, 'status': 1},
{'name': slug, 'status': 2},
]
for i in names:
name_obj, created = person_name_create(i['name'], i['status'], 2)
if name_obj not in person_names:
person.name.add(name_obj)
if exist:
result = imdb_person_searching(name)
txt = ''
for i in result:
txt += '<div style="border-bottom:1px solid #CCC; padding:5px; background:#EBEBEB; min-width: 300px;"><a href="http://www.imdb.com%s" target="_blank">%s</a> <i>%s</i><br /> <input type="button" value="Выбрать" id="%s" class="imdb_person_list_select" /></div>' % (i['link'].encode('utf-8'), i['title'], i['details'], i['id'])
txt += '<br /><div>Или укажите ссылку на страницу персоны IMDb:<br /><input type="text" value="" size="40" class="imdb_person_url" /> <input type="button" value="Искать" class="imdb_person_list_select" /><input type="hidden" value="%s" id="pid" /></div>' % person.id
return simplejson.dumps({
'status': True,
'content': txt,
'query': name,
})
return simplejson.dumps({})
except Exception as e:
open('errors.txt','a').write('%s * (%s)' % (dir(e), e.args))
def get_okinoua_cities():
"""
Парсинг городов Украины
"""
source = ImportSources.objects.get(url='http://www.okino.ua/')
# Получаем список городов с таблицы SourceCities в виде списка
cities_ids = get_source_data(source, 'city', 'list')
data_nof_city = ''
# Открываем страницу с городами
url = '%skinoafisha-kiev/' % source.url
req = urllib.urlopen(url)
if req.getcode() == 200:
page = BeautifulSoup(req.read(), from_encoding="utf-8")
# Находим все теги с городами и считываем из них id и названия городов
for ul in page.findAll('ul', {'class': 'blist'}):
for li in ul.findAll('li'):
id = li.a.get('href').replace('/', '')
name = li.a.string.encode('utf-8').strip()
name_slug = low(del_separator(name))
# Сравниваем полученные города с городами в нашей БД и, если НЕТ совпадений, то
if id not in cities_ids:
# идентифицируем новый город
city = City.objects.filter(name__name=name_slug,
name__status=2).distinct('pk')
# если идентифицировали, то записываем в таблицу SourceCities
if city.count() == 1:
SourceCities.objects.create(
source_id=id,
source_obj=source,
city=city[0],
name=name,
)
# в противном случаем записываем ненайденые города в xml для дальнейших действий над ними
else:
if 'slug="%s"' % name_slug not in data_nof_city:
data_nof_city += '<city name="%s" slug="%s"></city>' % (
name, name_slug)
create_dump_file('okinoua_nof_city', settings.NOF_DUMP_PATH,
'<data>%s</data>' % data_nof_city)
cron_success('html', 'okinoua', 'cities', 'Укр. города')
def get_rambler_cities():
source = ImportSources.objects.get(url='http://www.rambler.ru/')
cities_ids = get_source_data(source, 'city', 'list')
data_nof_city = ''
'''
# LOCALHOST
f = open('%s/dump_rambler_city.xml' % settings.API_DUMP_PATH, 'r')
xml = BeautifulSoup(f.read(), from_encoding="utf-8")
f.close()
if xml: # --- end localhost
'''
# SERVER
url = 'http://api.kassa.rambler.ru/v2/%s/xml/cities/' % RAMBLER_API_KEY # dump_rambler_city.xml
req = urllib.urlopen(url)
if req.getcode() == 200:
xml = BeautifulSoup(req.read(),
from_encoding="utf-8") # --- end server
for i in xml.findAll('city'):
id = i.cityid.string
name = i.find('name').string.encode('utf-8')
name_slug = low(del_separator(name))
if id not in cities_ids:
city = City.objects.filter(name__name=name_slug,
name__status=2).distinct('pk')
if city.count() == 1:
SourceCities.objects.create(
source_id=id,
source_obj=source,
city=city[0],
name=name,
)
else:
if 'slug="%s"' % name_slug not in data_nof_city:
data_nof_city += '<city name="%s" slug="%s"></city>' % (
name, name_slug)
create_dump_file('%s_nof_city' % source.dump, settings.NOF_DUMP_PATH,
'<data>%s</data>' % data_nof_city)
cron_success('xml', source.dump, 'cities', 'Города')
def check_tag(tag, id):
tags = capit(tag).decode('utf-8')
tags = low(tag).decode('utf-8')
obj=""
try:
obj = OrganizationTags.objects.get(name=tags)
#obj = Organization.objects.get(tags__name=tags)
debug_logs("already exists: %s " % (obj))
except MultipleObjectsReturned:
debug_logs("MultipleObjectsReturned: %s " % (obj))
except ObjectDoesNotExist:
debug_logs("ObjectDoesNotExist %s" % tags.encode('utf-8'))
created = OrganizationTags.objects.create(name=tags, group_flag="org_name_tag")
tag = OrganizationTags.objects.get(name=tags)
org = Organization.objects.get(pk=id)
org.tags.add(tag)
debug_logs("tag %s, created %s " % (tag, created))
def get_premierzal_cities():
source = ImportSources.objects.get(url='http://www.premierzal.ru/')
cities = get_source_data(source, 'city', 'list')
data_nof_city = ''
req = urllib.urlopen(source.url)
if req.getcode() == 200:
data = BeautifulSoup(req.read())
block = data.find('div', {'class': 'drop'})
for i in block.findAll('a'):
city_name = i.text.encode('utf-8').strip()
city_id = low(del_separator(city_name))
if city_id.decode('utf-8') not in cities:
city = City.objects.filter(name__name=city_id,
name__status=2).distinct('pk')
if city.count() == 1:
SourceCities.objects.create(
source_id=city_id,
source_obj=source,
city=city[0],
name=city_name,
)
else:
data_nof_city += '<city name="%s" slug="%s"></city>' % (
city_name, city_id)
cities.append(city_id.decode('utf-8'))
create_dump_file('%s_nof_city' % source.dump, settings.NOF_DUMP_PATH,
'<data>%s</data>' % data_nof_city)
cron_success('html', source.dump, 'cities', 'Города')
def parse_address(data):
num, name, atype = ('', '', '')
if data:
num = re.findall(ur'^\d+\-?\d*\w?\s', data)
num = num[0].strip() if num else ''
data = re.sub(ur'^\d+\-?\d*\w?\s', '', data)
types = {
'st': 70,
'street': 70,
'rd': 71,
'road': 71,
'rds': 71,
'ave': 72,
'avenue': 72,
'hwy': 73,
'dr': 74,
'crt': 75,
'pde': 76
}
low_data = low(data)
for k, v in types.iteritems():
tmp = '%s.' % k
if k in low_data or tmp in low_data:
atype = v
if not atype:
atype = 70
name = re.sub(
r'(Avenue|avenue|Ave|ave|Street|street|Road|road|Rds|Hwy|hwy|Crt|crt|Pde|pde|St|st|Rd|rd|Dr)\.?$',
'', data)
return num, name.strip(), atype
def organizations_doubles(request):
orgs = Organization.objects.all().order_by('name')
unique = {}
double = []
txt = ''
for i in orgs:
result = unidecode(i.name)
result = re.findall(ur'[a-z0-9]+', low(result))
result = '-'.join(result) if result else ''
obj = unique.get(result)
if obj:
if obj not in double:
txt += '%s <a href="http://kinoinfo.ru/organizations/show/%s" target="_blank">(ID %s)</a><br />' % (obj.name.encode('utf-8'), obj.id, obj.id)
double.append(obj)
double.append(i)
txt += '%s <a href="http://kinoinfo.ru/organizations/show/%s" target="_blank">(ID %s)</a><br />' % (i.name.encode('utf-8'), i.id, i.id)
else:
unique[result] = i
count = len(double)
txt = '<b>Всего %s</b><br /><br />%s' % (count, txt)
return HttpResponse(str(txt))
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_premierzal_schedules():
data_nof_film = ''
noffilms = []
ignored = get_ignored_films()
source = ImportSources.objects.get(url='http://www.premierzal.ru/')
sfilm_clean(source)
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)
schedules = get_source_data(source, 'schedule', 'list')
cities_cinemas = {}
for i in SourceCinemas.objects.select_related('city').filter(
source_obj=source):
if not cities_cinemas.get(i.city.source_id):
cities_cinemas[i.city.source_id] = {'city': i.city, 'cinemas': []}
cities_cinemas[i.city.source_id]['cinemas'].append(i)
for k, v in cities_cinemas.iteritems():
city_url_encode = urllib.quote(v['city'].name.encode('utf-8'))
for i in v['cinemas']:
main_url = '%s?theatre=%s&city=%s' % (source.url, i.source_id,
city_url_encode)
main_req = urllib.urlopen(main_url)
if main_req.getcode() == 200:
data = BeautifulSoup(main_req.read())
data = data.find('div', id="films-list")
if data:
dates = []
for calendar in data.findAll('table',
{'class': 'calendar'}):
for a in calendar.findAll('a'):
href = a.get('href', '')
href_dict = dict(cgi.parse_qsl(href))
calendar_date = href_dict.get(
u'?date', href_dict.get(u'date'))
if calendar_date:
dates.append({
'date': calendar_date,
'href': href
})
for ind, d in enumerate(dates):
films_blocks = []
if ind == 0:
films_blocks = data.findAll(
'div', {'class': 'film-item-wrapper'})
else:
url = '%s?date=%s&city=%s&theatre=%s' % (
source.url, d['date'], city_url_encode,
i.source_id)
req = urllib.urlopen(url)
if req.getcode() == 200:
data = BeautifulSoup(req.read())
data = data.find('div', id="films-list")
films_blocks = data.findAll(
'div', {'class': 'film-item-wrapper'})
time.sleep(random.uniform(0.8, 2.2))
for block in films_blocks:
title = block.find('div', {
'class': 'title'
}).find('a')
film_name = title.text.encode('utf-8').strip()
film_slug = low(
del_separator(del_screen_type(film_name)))
film_id = film_slug
if film_id not in noffilms and film_slug.decode(
'utf-8') not in ignored:
obj = films.get(film_id.decode('utf-8'))
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.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_film += xml_noffilm(
film_name, film_slug, None, None,
film_id, info, None, source.id)
noffilms.append(film_id)
if objt:
year, month, day = d['date'].split(
u'-')
for tm in block.findAll(
'div',
{'class': 'seanse-item'}):
for t in tm.text.encode(
'utf-8').split('|'):
t = re.findall(
r'\d{2}\:\d{2}', t)
if t:
hours, minutes = t[
0].strip().split(':')
dtime = datetime.datetime(
int(year), int(month),
int(day), int(hours),
int(minutes))
sch_id = '%s%s%s' % (
dtime,
i.source_id.encode(
'utf-8'), film_id)
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=i,
dtime=dtime,
)
schedules.append(
sch_id)
time.sleep(random.uniform(1.1, 1.8))
create_dump_file('%s_nof_film' % source.dump, settings.NOF_DUMP_PATH,
'<data>%s</data>' % data_nof_film)
cron_success('html', source.dump, 'schedules', 'Сеансы')
def get_yovideo():
source = ImportSources.objects.get(url='http://www.yo-video.net/')
sfilm_clean(source)
today = datetime.datetime.now()
french_month = {
'1': 'janvier',
'2': 'fevrier',
'3': 'mars',
'4': 'avril',
'5': 'mai',
'6': 'juin',
'7': 'juillet',
'8': 'aout',
'9': 'septembre',
'10': 'octobre',
'11': 'novembre',
'12': 'decembre',
}
data_nof_film = ''
noffilms = []
ignored = get_ignored_films()
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)
main_urls = []
for i in range(today.month, 13):
m = french_month.get(str(i))
url = '%sfr/sorties/cinema/%s/%s/' % (source.url, today.year, m)
req = urllib.urlopen(url)
if req.getcode() == 200:
data = BeautifulSoup(req.read(), from_encoding="utf-8")
for h2 in data.findAll('h2'):
day = h2.findAll('span', limit=1)[0].string.encode('utf-8')
time.sleep(1)
req2 = urllib.urlopen('%s%s' % (url, day))
if req2.getcode() == 200:
data2 = BeautifulSoup(req2.read(), from_encoding="utf-8")
release_date = datetime.date(today.year, int(i), int(day))
for film_block in data2.findAll('div', {'class': 'sfilm'}):
film_id = film_block.find('a').get('href').encode('utf-8')
full_url = '%s%s' % (source.url, film_id.lstrip('/'))
name = film_block.find('img').get('alt').encode('utf-8').replace('Film ', '')
slug = low(del_separator(name))
if slug.decode('utf-8') not in ignored and film_id not in noffilms:
obj = films.get(film_id)
next_step = checking_obj(obj)
if next_step:
kid = None
if obj:
kid = obj.kid
if not kid:
req3 = urllib.urlopen(full_url)
if req3.getcode() == 200:
data3 = BeautifulSoup(req3.read(), from_encoding="utf-8")
h3 = data3.find('h3')
alter_name = None
alter_name_slug = None
if h3:
alter_name = h3.string.encode('utf-8')
alter_name_slug = low(del_separator(alter_name))
kid, info = film_identification(slug, alter_name_slug, {}, {}, source=source)
txt = None
if not kid:
div = data3.find('div', {'class': "filmLeft"})
img_url = div.find('img').get('src').encode('utf-8')
details = data3.find('div', {'class': "details"})
director = details.find('span', itemprop="name")
if director:
director = director.string.encode('utf-8').strip()
year = re.findall(ur'Année\s?\: \d+', details.text)
if year:
year = year[0].encode('utf-8').replace('Année','').replace(':','').strip()
txt = '%s;%s;%s;%s' % (full_url.encode('utf-8'), img_url, director, year)
kid = None
objt = None
if kid:
create_new, objt = unique_func(fdict, kid, obj)
if create_new:
new = create_sfilm(film_id, kid, source, name, name_alt=alter_name, txt=txt, extra=release_date)
films[film_id] = new
if not fdict.get(kid):
fdict[kid] = {'editor_rel': [], 'script_rel': []}
fdict[kid]['script_rel'].append(new)
else:
if not obj:
new = create_sfilm(film_id, kid, source, name, name_alt=alter_name, txt=txt, extra=release_date)
films[film_id] = new
if not fdict.get(kid):
fdict[kid] = {'editor_rel': [], 'script_rel': []}
fdict[kid]['script_rel'].append(new)
create_dump_file('%s_nof_film' % source.dump, settings.NOF_DUMP_PATH, '<data>%s</data>' % data_nof_film)
cron_success('html', source.dump, 'releases', 'Франц.релизы')
def parse_data_ident(request, selected):
"""Функция для идентификации полученных записей
"""
#try:
debug_logs("start ident %s " % selected)
# Начинаем отчет времени выполнения фукнции
start = time.time()
data_nof_film = ''
noffilms = []
ignored = get_ignored_films()
# Задаем тип идентификации, для передачи в качестве параметра в функцию идентификации
ident_type = 'movie_online'
# Делаем выборку всех фильмов из базы с пометкой (afisha_id=None),
# так помечаются все фильмы при парсинге,
# это фильмы, которые не разу не проходифшие идентификацию киноафиши
data = MovieMegogo.objects.filter(afisha_id__in=(0, None))
# Получаем необходимые для идентификации параметры,
# проходим итерациями в цикле для каждого отдельного фильма
for i in data:
year = i.year
name_ru = i.title
name_en = i.title_en
country = i.country
# Отчищаем названия ru en для идентификации фильма
name_ru_slug = del_separator(low(name_ru))
name_en_slug = del_separator(low(name_en))
# Задаем диапазон лет для идентификации фильма
new_year = year + 2
old_year = year - 2
filter_year = {'year__gte': old_year, 'year__lte': new_year}
try:
# Передаем фильм в функцию на идентификацию
kid, info = film_identification(name_ru_slug, name_en_slug, {}, {},
filter_year, ident_type, country)
if kid:
# Записываем результат в модель
i.afisha_id = kid
i.save()
else:
if i.megogo_id not in noffilms and name_ru_slug.decode(
'utf-8') not in ignored:
data_nof_film += xml_noffilm(name_ru.encode('utf-8'),
name_ru_slug, None, None,
i.megogo_id, info,
i.page.encode('utf-8'))
noffilms.append(i.megogo_id)
except db.backend.Database._mysql.OperationalError:
if i.megogo_id not in noffilms and name_ru_slug.decode(
'utf-8') not in ignored:
data_nof_film += xml_noffilm(name_ru.encode('utf-8'),
name_ru_slug, None, None,
i.megogo_id, None,
i.page.encode('utf-8'))
noffilms.append(i.megogo_id)
# Время выполнения функции
finish = time.time()
timer = "%.2f мин" % ((float(finish - start)) / 60)
debug_logs("finish")
debug_logs("timer: %s " % timer)
debug_logs("Идентификация: название %s / инфо %s %s" %
(name_ru_slug, kid, info))
source = ImportSources.objects.get(url='http://megogo.net/')
create_dump_file('%s_nof_film' % source.dump, settings.NOF_DUMP_PATH,
'<data>%s</data>' % data_nof_film)
# Возвращаемся в интерфейс
return simplejson.dumps({
'request_type': 1,
'timer': timer,
})