}
ACT_TYPE_OTHER = "інше"
print('getting acts list')
acts = rada.list_acts()
for act_number in acts:
for act_type in ACT_TYPES:
#print(act_number)
if acts[act_number][2].startswith(act_type):
acts[act_number].append(ACT_TYPES[act_type])
if len(acts[act_number]) == 3:
acts[act_number].append(ACT_TYPE_OTHER)
print('getting deputies list')
mp_list = rada.list_deputy_links()
fh = open(OUTPUT_FILE, 'w')
csvwriter = writer(fh)
csvwriter.writerow(ROW_HEADERS)
cf = open(EDITS_FILE, "w")
cor_writer = writer(cf)
cor_writer.writerow(COR_HEADERS)
for link in [link.attrib['href'] for link in mp_list]:
sleep(SLEEP_TIME)
deputy_id_matched = DEPUTY_ID_RE.fullmatch(link)
if deputy_id_matched:
template_arguments['deputy_id'] = \
int(deputy_id_matched.group('deputy_id'))
district = ditrict_matched.group('district_number')
print(district)
region_matched = REGION_SELECTOR.search(b_info)
if region_matched:
region = region_matched.group('region')
print(region)
party_matched = PARTY_SELECTOR.search(b_info)
if party_matched:
party = party_matched.group('party')
print(party)
return ([party, number, region, district])
fh = open(OUTPUT_FILE, 'w')
csvwriter = writer(fh)
csvwriter.writerow(HEADERS)
pre_link_list = rada.list_deputy_links()
link_list = [pq(l).attr('href') for l in pre_link_list]
for link in link_list:
page = pq(link)
name = page(NAME_SELECTOR)
name = pq(name).text()
info = get_basic_info(page)
output_row = [name] + info
csvwriter.writerow(output_row)
sleep(SLEEP_TIME)
fh.close()
}
ACT_TYPE_OTHER = "інше"
print('getting acts list')
acts = rada.list_acts()
for act_number in acts:
for act_type in ACT_TYPES:
print(act_number)
if acts[act_number][2].startswith(act_type):
acts[act_number].append(ACT_TYPES[act_type])
if len(acts[act_number]) == 3:
acts[act_number].append(ACT_TYPE_OTHER)
print('getting deputies list')
mp_list = rada.list_deputy_links()
fh = open(OUTPUT_FILE, 'w')
csvwriter = writer(fh)
csvwriter.writerow(ROW_HEADERS)
for link in [link.attrib['href'] for link in mp_list]:
sleep(SLEEP_TIME)
deputy_id_matched = DEPUTY_ID_RE.fullmatch(link)
if deputy_id_matched:
template_arguments['deputy_id'] = \
int(deputy_id_matched.group('deputy_id'))
legislative_link = LINK_TEMPLATE.format(**template_arguments)
legislative_page = pq(legislative_link)
deputy_name = legislative_page(NAME_SELECTOR).text()\
.replace(NAME_STRIP, '')
cells = list(map(lambda x: pq(x).text(), cols))
start_date = change_date_format(cells[1])
if cells[2] != "-":
end_date = change_date_format(cells[2])
else:
end_date = ""
faction_title = cells[0]
output_row = [name, faction_title, start_date, end_date]
output_csv_writer.writerow(output_row)
output_csv = open(OUTPUT_FILE, 'w')
output_csv_writer = writer(output_csv)
output_csv_writer.writerow(HEADERS)
mps = rada.list_deputy_links()
for mp in mps:
name = pq(mp).text()
page_link = pq(mp).attr('href')
print(page_link)
print(MP_PAGE_RE)
page_link_matched = MP_PAGE_RE.fullmatch(page_link)
print(page_link_matched)
mp_id = int(page_link_matched.group('ID'))
faction_changes_link = FACTION_CHANGES_URL.format(**{
'ex_page': EX_PAGE_PARTICLE,
'mp_id': mp_id
})
parse_changes_table(faction_changes_link)
sleep(SLEEP_TIME)
7: 'Генеральному прокурору України',
8: 'Місцевим органам влади і управління'
}
ROW_SELECTOR = 'table:eq(1) tr'
ROW_SUBSELECTORS = (
'td.THEAD3:nth-child(1) a',
'td.THEAD21:nth-child(2)',
'td.THEAD3:nth-child(3)',
'td.THEAD21:nth-child(4)',
)
print("getting deputies list")
mps = rada.list_deputy_links()
names = list(map(lambda x: pq(x).text(), mps))
fh = open(OUTPUT_FILE, 'w')
csvwriter = writer(fh)
csvwriter.writerow(ROW_HEADERS)
mp_number = 0
for link in [link.attrib['href'] for link in mps]:
deputy_id_matched = DEPUTY_ID_RE.fullmatch(link)
if deputy_id_matched:
template_arguments['deputy_id'] = int(
deputy_id_matched.group('deputy_id'))
for type_id in QUERY_TYPES.keys():
sleep(SLEEP_TIME)
template_arguments['type_id'] = type_id
queries_link = LINK_TEMPLATE.format(**template_arguments)
