def process_candidates():
reader = codecs.open("candidates.csv", 'r', encoding='utf-8')
counter = 0
candidates_ids = []
for line in reader:
row = line.split(u',')
area_name = row[0].title().strip()
area = area_getter(area_name)
if area is None:
print u'no encontré a ' + area_name
return
kind_of = row[1].title().strip()
election_name = kind_of + u' por ' + area.name
if not Election.objects.filter(name__iexact=election_name):
print u"no pillé a " + election_name
# Candidate.objects.filter(id__in=candidates_ids).delete()
return
else:
e = Election.objects.get(name__iexact=election_name)
name = row[2].title().strip()
candidate = Candidate(name=name)
candidate.save()
candidates_ids.append(candidate.id)
e.candidates.add(candidate)
print e, candidate
try:
mail = row[6].strip().lower()
except IndexError:
mail = None
if mail:
contact = CandidacyContact.objects.create(candidate=candidate,
mail=mail)
pacto = row[3].strip().title()
sub_pacto = row[4].strip().title()
partido = row[5].strip().title()
if pacto:
PersonalData.objects.create(candidate=candidate,
label=u'Pacto',
value=pacto)
if sub_pacto:
PersonalData.objects.create(candidate=candidate,
label=u'Sub Pacto',
value=sub_pacto)
if partido:
PersonalData.objects.create(candidate=candidate,
label=u'Partido',
value=partido)
send_candidate_username_and_password(candidate)
counter += 1
if not counter % 1000:
print u'van' + str(counter)
counts = table.find_all(class_="read")
days = table.find_all(class_="date")
for tit, count, day in zip(t**s, counts, days):
title = tit.a.get_text()
link = tit.a.get('href')
read = count.get_text()
date = day.get_text()
temp_dict = {
'day': date,
'title': title,
'count': read,
'link': link
}
temp_list.append(temp_dict)
#toJson(temp_list)
return temp_list
#parsing()
if __name__ == '__main__':
parsed_data = parsing()
for i in range(len(parsed_data)):
new_candidate = Candidate(name=parsed_data[i]["day"],
introduction=parsed_data[i]["title"],
area=parsed_data[i]["count"],
party_number=parsed_data[i]["link"])
new_candidate.save()
if container.find('video'):
videotag = container.find('video')
image =videotag.get('poster')
elif container.find('img'):
imgtag = container.find('img')
image =imgtag.get('src')
else:
image = 'none'
#
read = count.get_text()
date = day.get_text()
temp_dict = {'day': date, 'title': title, 'count': read, 'link': link, 'image': image}
temp_list.append(temp_dict)
#toJson(temp_list)
return temp_list
'''
if __name__=='__main__':
parsed_data = []
parsed_data = ygosu_parsing()
#parsed_data1 = ou_parsing()
#parsed_data.extend(parsed_data1)
toJson(parsed_data)
for i in range(len(parsed_data)):
new_candidate = Candidate(date=parsed_data[i]["day"],
title=parsed_data[i]["title"],
count=parsed_data[i]["count"],
link=parsed_data[i]["link"],
image=parsed_data[i]["image"])
new_candidate.save()
