def published_econ_agri_indic(content):
# Retorna a tabela de indicadores extraída do arquivo txt do site da bovespa
cont_list = content.split('\n')
cont_list.pop(len(cont_list) - 1)
parseStr = lambda x: x.isalpha() and x or x.isdigit() and \
int(x) or x.isalnum() and x or \
len(set(string.punctuation).intersection(x)) == 1 and \
x.count('.') == 1 and float(x) or x
table = [i for i in cont_list]
for i in range(0, len(cont_list)):
table[i] = [
cont_list[i][0:6], cont_list[i][6:9], cont_list[i][9:11],
parsers.dateISOer(cont_list[i][11:19]), cont_list[i][19:21],
cont_list[i][21:46].strip(),
str(
DefaultContext.divide(
Decimal(parseStr(cont_list[i][47:71])),
DefaultContext.power(
Decimal('10'),
Decimal(parseStr(cont_list[i][71:73]))))),
cont_list[i][71:73]
]
#'''
last_biz_day = bd.Calendar('ANBIMA').offset(date.today().isoformat(), -1)
f = open('IndicRelatorio' + last_biz_day + '.txt', 'w+')
for m, i in enumerate(table):
for k, j in enumerate(table[m]):
f.write(table[m][k] + ',')
f.write('\n')
f.close()
#'''
return dict(id='BOLETIM_ECON_AGRO',
date=parsers.dateISOer(cont_list[1][11:19]),
indic=table)
def published_selic(content):
selic = {}
selic['id'] = 'SELIC'
selic['value'] = re.findall('SELIC: (\d*.\d*)% ao ano', content)[0]
selic['value'] = selic['value'].replace(',', '.')
selic['date'] = parsers.dateISOer(
re.findall('SELIC: \d*.\d*% ao ano \*[^\*]*\*Em (\d*.\d*.\d*)',
content)[0])
return selic
def published_options(content):
cont_list = content.split('\n')
cont_list.pop(len(cont_list) - 1) # retira a linha vazia criada no split()
# O Cabeçalho e o Rodapé possuem formatos diferentes
header = []
header = [
cont_list[0][:2], cont_list[0][2:15], cont_list[0][15:23],
cont_list[0][23:31]
]
footer = []
footer = [
cont_list[len(cont_list) - 1][:2], cont_list[len(cont_list) - 1][2:15],
cont_list[len(cont_list) - 1][15:23],
cont_list[len(cont_list) - 1][23:31],
cont_list[len(cont_list) - 1][31:42]
]
# Cria a lista com a mesma qtd de elementos da lista final
table = [i for i in cont_list]
# Cria lista com as linhas cortadas no campo correto segundo o arq de layout da bm&f bovespa
for i in range(0, len(cont_list)):
if i == 0:
table[i] = header
else:
if i == len(cont_list) - 1:
table[i] = footer
else:
table[i] = [
cont_list[i][0:2], cont_list[i][2:10], cont_list[i][10:12],
cont_list[i][12:24], cont_list[i][24:27],
cont_list[i][27:39], cont_list[i][39:49],
cont_list[i][49:52], cont_list[i][52:56],
cont_list[i][56:69], cont_list[i][69:82],
cont_list[i][82:95], cont_list[i][95:108],
cont_list[i][108:121], cont_list[i][121:134],
cont_list[i][134:147], cont_list[i][147:152],
cont_list[i][152:170], cont_list[i][170:188],
cont_list[i][188:201], cont_list[i][201:202],
cont_list[i][202:210], cont_list[i][210:217],
cont_list[i][217:230], cont_list[i][230:242],
cont_list[i][242:245]
]
# Extrai apenas os códigos de opções de compra e venda, exceto do header e do footer.
options = [
i for j, i in enumerate(table)
if j not in [0, len(table) -
1] and (table[j][4] == '070' or table[j][4] == '080')
]
return dict(id='BOLETIM_OPCOES',
date=parsers.dateISOer(header[3]),
opt=options)
def published_ipca_pro_rata(content):
ipca = {}
ipca['id'] = 'IPCA_PRO_RATA'
ipca['date'] = parsers.dateISOer(
re.findall('IPCA.* pro rata em.* (\d*/\d*/\d)*.*= \d*.\d*,\d*',
content)[0])
ipca['value'] = re.findall(
'IPCA.* pro rata em.* \d*/\d*/\d*.*= (\d*.\d*,\d*)', content)[0]
ipca['value'] = ipca['value'].replace('.', '').replace(',', '.')
return ipca
def published_igpm_pro_rata(content):
igpm = {}
igpm['id'] = 'IGPM_PRO_RATA'
igpm['date'] = parsers.dateISOer(
re.findall('IGP-M.* pro rata em.* (\d*/\d*/\d)*.*= \d*,\d*',
content)[0])
igpm['value'] = re.findall(
'IGP-M.* pro rata em.* \d*/\d*/\d*.*= (\d*,\d*)', content)[0]
igpm['value'] = igpm['value'].replace(',', '.')
return igpm
def published_ipca_index(content):
ipca = {}
ipca['id'] = 'IPCA_ANBIMA_INDICE'
ipca['date'] = parsers.dateISOer(
re.findall('\*Expectativa IPCA.*para[^\d]*(\d*.\d*.\d*)', content)[0])
ipca['value'] = re.findall(
'tabelaTitulo.*Tarifa.*Valores de Refer.*[^I]*IGP-M.*\d*,\d*.*[^I]*IPCA.* (\d*.\d*,\d*)',
content)[0]
ipca['value'] = ipca['value'].replace('.', '').replace(',', '.')
return ipca
def published_igpm_index(content):
igpm = {}
igpm['id'] = 'IGPM_ANBIMA_INDICE'
igpm['date'] = parsers.dateISOer(
re.findall('\*Expectativa IGP-M.*para[^\d]*(\d*.\d*.\d*)', content)[0])
igpm['value'] = re.findall(
'tabelaTitulo.*Tarifa.*Valores de Refer.*[^I]*IGP-M.* (\d*,\d*)',
content)[0]
igpm['value'] = igpm['value'].replace(',', '.')
return igpm
def published_ipca(content):
ipca = {}
ipca['id'] = 'IPCA_ANBIMA'
ipca['date'] = parsers.dateISOer(
re.findall('\*Expectativa IPCA.*para[^\d]*(\d*.\d*.\d*)', content)[0])
ipca['value'] = re.findall(
'\*Expectativa IPCA.*para[^\d]*\d*.\d*.\d*.*[^\d]* (\d*,\d*)%',
content)[0]
ipca['value'] = ipca['value'].replace(',', '.')
return ipca
def published_igpm(content):
igpm = {}
igpm['id'] = 'IGPM_ANBIMA'
igpm['date'] = parsers.dateISOer(
re.findall('\*Expectativa IGP-M.*para[^\d]*(\d*.\d*.\d*)', content)[0])
igpm['value'] = re.findall(
'\*Expectativa IGP-M.*para[^\d]*\d*.\d*.\d*.*[^\d]* (\d*.\d*)%',
content)[0]
igpm['value'] = igpm['value'].replace(',', '.')
return igpm
def published_euro_bce(content):
euro_bce = {}
euro_bce['id'] = 'EURO_BCE'
euro_bce['value'] = re.findall(
'Taxa de .* US\$.*[^*]*>Em \d*.\d*.\d* = (\d*.\d*).*[^*]*\*.* Banco Central Europeu',
content)[0]
euro_bce['value'] = euro_bce['value'].replace(',', '.')
euro_bce['date'] = parsers.dateISOer(
re.findall(
'Taxa de .* US\$.*[^*]*>Em (\d*.\d*.\d*) = \d*.\d*.*[^*]*\*.* Banco Central Europeu',
content)[0])
return euro_bce
def published_cdi_cetip(content):
cdi_cetip = {}
cdi_cetip['id'] = 'CDICETIP'
cdi_cetip['value'] = re.findall(
'Taxa Referencial de DI / Cetip[^(DI)]*.*: (\d*.\d*)%[^(Em)]*Em \d*.\d*.\d*',
content)[0]
cdi_cetip['value'] = cdi_cetip['value'].replace(',', '.')
cdi_cetip['date'] = parsers.dateISOer(
re.findall(
'Taxa Referencial de DI / Cetip[^(DI)]*.*: \d*.\d*%[^(Em)]*Em (\d*.\d*.\d*)',
content)[0])
return cdi_cetip
