def load_cantidates_from_url(url, election):
i = 1
while True:
soup = get_soup(url+"&number="+str(i))
i += 1
table = soup.find(id="test")
if not table:
logger.info('Нет таблицы кандидатов для %s' % election.name)
break
trs = table.find_all("tr")
if len(trs) == 0:
logger.info('Таблица кандидатов пустая %s' % election.name)
break
for tr in trs:
data = tr.find_all("td")
name = data[1].contents[0].contents[0].text.strip() # in nobr tag
logger.info('Загружен кандидат %s, выборы %s' % (name, election.name))
link = fix_link(data[1].contents[0].contents[0]['href'])
date = datetime.strptime(data[2].text, '%d.%m.%Y')
party = data[3].text.strip()
district = data[4].text.strip()
try:
person = Person.objects.get(name=name, birthdate=date)
except Person.DoesNotExist:
person = Person(name=name, birthdate=date)
person.save()
try:
info = Info.objects.get(person=person, election=election)
except Info.DoesNotExist:
info = Info(person=person, election=election)
info.save()
load_info(link, party, district, info)
def load_from_json(json_file):
data = json.loads(json_file.read().decode('utf-8'))
for d in data:
name = d[0]
date = datetime.strptime(d[1], '%d.%m.%Y')
url = d[2]
try:
election = Election.objects.get(name=name, date=date)
if election.url != url:
election.url = url
election.save()
except Election.DoesNotExist:
election = Election(name=name, date=date, url=url)
election.save()
candidates = d[3]
for c in candidates:
try:
person = Person.objects.get(name=c[0], birthdate=datetime.strptime(c[2], '%d.%m.%Y'))
except Person.DoesNotExist:
person = Person(name=c[0], birthdate=datetime.strptime(c[2], '%d.%m.%Y'))
person.save()
try:
info = Info.objects.get(person=person, election=election)
except Info.DoesNotExist:
info = Info(person=person, election=election)
info.save()
info.url = c[1]
info.party = c[3]
info.address = c[4]
info.edu = c[5]
info.firm = c[6]
info.job = c[7]
info.dep = c[8]
info.criminal = c[9]
info.status = c[10]
info.district = c[11]
info.save()