def load(source_slug, name_slug, chunk_len=200, debug=False):
print source_slug
print name_slug
i = 0
bulk = Bulk(source_slug, name_slug, chunk_len)
slug = "%s_%s" % (source_slug, name_slug)
parts = get_parts(slug, '\n\n')
for part in parts:
# print part
# print
if not part:
continue
try:
num, word, desc = part.split('\n', 2)
except ValueError:
num, word = part.split('\n', 1)
desc = ''
if num[:3] != 'id=':
print '### WRONG_NUM ###', num, part
num = num[3:]
# if num[-2:] == '.d':
# num = num[:-2]
# # todo: write bool, downloaded or not
word = word.decode('utf8').strip()
desc = desc.decode('utf8').strip()
if (source_slug, name_slug) == ('academic', 'efremova'):
# print word
word, desc = desc.split('\n', 1)
# print word
word = word.replace(u'́', '')
# print word
if (source_slug, name_slug) == ('academic', 'kuznetsov'):
if desc.find(u'[с прописной буквы]') != -1:
# todo: бывает и с большой буквы, и с маленькой "Галактика"
print word
word = word.capitalize()
print word
# word = prettify(word, encoding=False).decode('utf8')
# desc = prettify(desc, encoding=False).decode('utf8')
word = remove_end(word, ['1', '2', ' .', ';']).strip()
if not check_word(word, debug): # "-" and " "
continue
bulk.add(word, desc, num)
# todo: also save num to db
# print num
# print desc
# print
i += 1
# if i > 10:
# break
if not i % 10000:
print i
