def extract_category():
re_category = re.compile(r'\[\[Category:.+\]\]')
res = []
for line in load_wiki_data().split("\n"):
m = re.match(re_category, line)
if m:
res.append(line)
return res
def extract_country_data():
re_curly_brackets = r"(?<rec>\{\{(?:[^{}]+|(?&rec))*\}\})"
country_data = [data for data in regex.findall(re_curly_brackets,load_wiki_data(), regex.VERBOSE) if re.match(r"^\{\{基礎情報 国", data)][0].split("\n")[1:-1]
# dic_country_data = OrderedDict()
dic_country_data = {}
for e in country_data:
m = re.match(r"^\|(.+) \= (.+)", e)
if m:
current_key = m.group(1)
dic_country_data[current_key] = m.group(2)
else:
dic_country_data[current_key] += "\n"+e
return dic_country_data
from Chap03_020 import load_wiki_data
import re
re_media = re.compile(r"(ファイル|File):(.+?)\|", re.I)
for line in load_wiki_data().split("\n"):
m = re.search(re_media, line)
if m:
print(m.group(2))