def maru():
text = read20.file_reading()
template_dictionary = {}
basic_information = re.search(r'^\{\{基礎情報\s国\n(.*)\n\}\}$', text,
re.MULTILINE + re.DOTALL)
basic_data = basic_information.group(1)
basic_data = re.split('\n(?=\|)', basic_data)
for line in basic_data:
data = re.match(r'^\|(.+?)\s*\=\s*(.*)', line,
re.DOTALL) #???????????????
if data == None:
continue
else:
key = re.sub('\|', '', data.group(1))
key = re.sub('\s$', '', key)
value = re.sub('(\'{2,4})', '', data.group(2))
if re.search(r'\[\[.+\]\]', value):
value = re.sub('[\[\]#\|]', '', value)
if re.search(r'\{\{.+\}\}', value):
value = re.sub('[{}]', '', value)
pattern = re.compile(r'\[http:([^]]*)\]')
value = pattern.sub(r'', value)
template_dictionary[key] = value
return template_dictionary
#記事のカテゴリ名を（行単位ではなく名前で）抽出せよ．
#カテゴリの名前だけ？とってくるの？
import read20
import re
text = read20.file_reading()
text = text.split('\n') #一行ごとに分けた
"""
def CategoryName(line):
name = re.match(r'\[\[Category:(.*)\]\]', line)
name_group = name.group(1).split('|')
return name_group[0]
"""
def category_name(line):
name = re.search(r'(?<=Category:)\w+', line)
return name.group()
for line in text:
if re.match(r'\[\[Category:.+\]\]', line):
print(category_name(line))
#[ぁ-んァ-ン一-龥0-9０−９a-zA-Z・] = \w