def parse_wiki():
dic = {}
shouldParse = False
check = []
for line in k20.read_jwc_json()['イギリス'].split('\n'):
check.append('')
if '基礎情報' in line:
shouldParse = True
continue
if shouldParse:
r = parse('|{} = {}', line)
if r is None:
if line == '}}':
break
continue
dic[r[0]] = re.sub('<.*>', '', re.sub('\'|\"|\[|\]', '', r[1]))
return dic
def extract_template(page_source=k20.read_jwc_json()['イギリス']):
dic = {}
should_parse = False
check = []
for line in page_source.split('\n'):
check.append('')
if '基礎情報' in line:
should_parse = True
continue
if should_parse:
r = parse('|{} = {}', line)
if r is None:
if line == '}}':
break
continue
dic[r[0]] = r[1]
return dic
import k20
import re
from pprint import pprint
# Windowsのファイル名禁止文字「\ / : * < > |」以外 が 1個以上 .(ピリオド）が1個 英字4個まで」の文字列を取ってくる。
sections = re.findall(':[^\\\/:\*\?\"\<\>\|]+\.[a-zA-Z]{,4}\|',
k20.read_jwc_json()['イギリス'])
pprint(sections)
import k20
import re
from pprint import pprint
categories = re.findall('\[\[Category:.+\]\]', k20.read_jwc_json()['イギリス'])
cateWords = [re.sub('\]\]', '', word).split(':')[1] for word in categories]
pprint(cateWords)
# for cateWord in cateWords:
# print(cateWord)
import k20
from pprint import pprint
from parse import parse
import re
dic = {}
shouldParse = False
check = []
for line in k20.read_jwc_json()['イギリス'].split('\n'):
check.append('')
if '基礎情報' in line:
shouldParse = True
continue
if shouldParse:
r = parse('|{} = {}', line)
if r is None:
if line == '}}':
break
continue
dic[r[0]] = re.sub('\'|\"', '', r[1])
pprint(dic)
# 強調マークアップは1行だけ存在した
import k20
import re
from pprint import pprint
# 「=が2個以上 .(なんか文字）が1個以上 =が2個以上」の文字列を取ってくる。
sections = re.findall('={2,}.+={2,}', k20.read_jwc_json()['イギリス'])
pprint(sections)
section_and_level = {
''.join(re.findall('[^=]+', section)).strip():
int(len(re.findall('=', section)) / 2 - 1)
for section in sections
}
pprint(section_and_level)
# for sec, level in section_and_level.items():
# print('N : {0:<10}, L : {1}'.format(sec, level))