def main():
lines = mywiki.extrac_text_from_title(u'イギリス').split('\n')
for text in lines:
section_in_lines = re.search('^(=+)\s*(.*?)\s*(=+)$', text)
if section_in_lines is not None:
print(section_in_lines.group(2),
len(section_in_lines.group(1)) - 1)
def main():
lines = re.split(r'\n[\|}]', mywiki.extrac_text_from_title(u'イギリス'))
var_dict = {}
for text in lines:
line = re.search("^(.*?)\s=\s(.*)", text, re.S)
if line is not None:
var_dict[line.group(1)] = re.sub(r"'{2,5}", r"", line.group(2))
for k,v in sorted(var_dict.items(), key=lambda x: x[1]):
print(k,v)
def main():
lines = mywiki.extrac_text_from_title(u'イギリス').split('\n')
var_dict = {}
for text in lines:
line = re.search("^\|(.*?)\s=\s(.*)", text)
if line is not None:
var_dict[line.group(1)] = removeInnerLinkMarkup(line.group(2))
for k, v in sorted(var_dict.items(), key=lambda x: x[0]):
print(k, v)
def main():
lines = mywiki.extrac_text_from_title(u'イギリス').split('\n')
var_dict = {}
for text in lines:
line = re.search("^\|(.*?)\s=\s(.*)", text)
if line is not None:
var_dict[line.group(1)] = removeInnerLinkMarkup(line.group(2))
url = "https://en.wikipedia.org/w/api.php"
payload = {
"action": "query",
"titles": "File:{}".format(var_dict[u'国旗画像']),
"prop": "imageinfo",
"format": "json",
"iiprop": "url"
}
json_data = requests.get(url, params=payload).json()
print(json_search(json_data)["url"])
def main():
lines = mywiki.extrac_text_from_title(u'イギリス').split('\n')
for text in lines:
category_in_line = re.search('^\[\[Category:(.*?)(|\|.*)\]\]$', text)
if category_in_line is not None:
print(category_in_line.group(1))
def main():
lines = mywiki.extrac_text_from_title(u'イギリス').split('\n')
for text in lines:
media_file = re.search('(File|ファイル):(.*?)\|', text)
if media_file is not None:
print(media_file.group(2))