def remove_Mediawiki_markup():
uk_data = extract_json().split('\n')
basic_info = {info_pattern.search(line).group(1):
mediawiki_pattern1.sub(r'',
mediawiki_pattern2.sub(r'\1',
link_pattern.sub(r'\2',
emp_pattern.sub('',info_pattern.search(line).group(2)))))
for line in uk_data if info_pattern.match(line)}
return basic_info
def extract_basic_info():
uk_data = extract_json().split('\n')
basic_info = {info_pattern.search(line).group(1): info_pattern.search(line).group(2) \
for line in uk_data if info_pattern.match(line)}
return basic_info
def remove_emp_markup():
uk_data = extract_json().split('\n')
basic_info = {info_pattern.search(line).group(1): emp_pattern.sub('',info_pattern.search(line).group(2)) \
for line in uk_data if info_pattern.match(line)}
return basic_info
# coding :utf-8
import re
from k20 import extract_json
if __name__ == '__main__':
section_pattern = re.compile(r'^(=+)(.*?)(=+)$')
uk_data = extract_json().split('\n')
print('\n'.join(['{}:{}'.format(section_pattern.search(line).group(2),\
len(section_pattern.search(line).group(1))) for line in uk_data if section_pattern.match(line)]))