import re
import sample20
lines = sample20.f('イギリス').split('\n')
for i in lines:
file_line = re.search('(File|ファイル):(.*?)\|', i)
if file_line is not None:
#print(file_line)
print(file_line.group(2))
import re
import sample20
temp_dict = {}
lines = re.split('\n[\|}]', sample20.f('イギリス'))
for i in lines:
temp_line = re.search('^(.*?)\s=\s(.*)', i, re.S)
if temp_line is not None:
temp_dict[temp_line.group(1)] = re.sub(r"'+", r"", temp_line.group(2))
for k, v in sorted(temp_dict.items(), key=lambda x: x[1]):
print(k, v)
else:
ret_dict[k] = v
return ret_dict
def remove_markup(str):
str = re.sub(r"'{2,5}", r"", str)
str = re.sub(r"\[{2}([^|\]]+?\|)*(.+?)\]{2}", r"\2", str)
str = re.sub(r"\{{2}.+?\|.+?\|(.+?)\}{2}", r"\1 ", str)
str = re.sub(r"<.*?>", r"", str)
str = re.sub(r"\[.*?\]", r"", str)
return str
temp_dict = {}
lines = sample20.f(u"イギリス").split("\n")
for line in lines:
temp_line = re.search("^\|(.*?)\s=\s(.*)", line)
if temp_line is not None:
temp_dict[temp_line.group(1)] = remove_markup(temp_line.group(2))
url = "https://en.wikipedia.org/w/api.php"
payload = {
"action": "query",
"titles": "File:{}".format(temp_dict[u"国旗画像"]),
"prop": "imageinfo",
"format": "json",
"iiprop": "url"
}
import re
import sample20
def remove_markup(str):
str = re.sub(r"'{2,5}", r"", str)
str = re.sub(r"\[{2}([^|\]]+?\|)*(.+?)\]{2}", r"\2", str)
str = re.sub(r"\{{2}.+?\|.+?\|(.+?)\}{2}", r"\1 ", str)
str = re.sub(r"<.*?>", r"", str)
str = re.sub(r"\[.*?\]", r"", str)
return str
temp_dict = {}
lines = sample20.f("日本").split("\n")
for i in lines:
temp_line = re.search("^\|(.*?)\s=\s(.*)", i)
if temp_line is not None:
temp_dict[temp_line.group(1)] = remove_markup(temp_line.group(2))
for k, v in sorted(temp_dict.items(), key=lambda x: x[0]):
print(k, v)
