import re
from path import project_path
from q21 import load_uk
from q25 import read_info
from q25 import info_to_dict
from q26 import rm_emph
from q27 import rm_link
def rm_tags(text):
text = re.sub(r"<br />", r"", text)
text = re.sub(r"<([^>\s]+)(\s[^>]+)*(>[^<]*</\1>|\s*/>)", r"", text)
return text
if __name__ == "__main__":
print("\rSolving Q28 ... ", end="")
x = info_to_dict(rm_tags(rm_link(rm_emph(read_info(load_uk())))))
with open(project_path / "output/wiki/28.txt", "w") as f:
f.write("\n".join("{} {}".format(k, v) for k, v in x.items()))
print("Done.")
import re
from path import project_path
from q21 import load_uk
if __name__ == "__main__":
print("\rSolving Q24 ... ", end="")
r = re.findall(r"\[\[ファイル:(.+?)\|", load_uk())
with open(project_path / "output/wiki/24.txt", "w") as f:
f.write("\n".join(r))
print("Done.")
return re.findall(r"{{基礎情報 国\|((?:[^{{}}]*{{[^{{}}]*}})*[^{{}}]*)}}", text)[0]
def info_to_dict(info):
x = info
r0 = r"({{[^}\|]+)\|([^}]+}})"
r1 = r"\1<PIPE>\2"
while x != re.sub(r0, r1, x):
x = re.sub(r0, r1, x)
r0 = r"(\[\[[^\]\|]+)\|([^\]]+\]\])"
r1 = r"\1<PIPE>\2"
while x != re.sub(r0, r1, x):
x = re.sub(r0, r1, x)
items = [i.replace("<PIPE>", "|") for i in re.split(r"\|", x)]
return dict([re.findall(r"(\S+)\s*=\s*(.+)", item)[0] for item in items])
if __name__ == "__main__":
print("\rSolving Q25 ... ", end="")
r = info_to_dict(read_info(load_uk()))
with open(project_path / "output/wiki/25.txt", "w") as f:
f.write("\n".join("{} {}".format(k, v) for k, v in r.items()))
print("Done.")
import requests
from path import project_path
from q21 import load_uk
from q25 import read_info
from q25 import info_to_dict
if __name__ == "__main__":
print("\rSolving Q29 ... ", end="")
url = "https://en.wikipedia.org/w/api.php"
params = {
"action": "query",
"prop": "imageinfo",
"iiprop": ["url"],
"format": "json",
"titles": "File:{}".format(info_to_dict(read_info(load_uk()))["国旗画像"]),
}
r = requests.get(url=url, params=params).json()
r = r["query"]["pages"]["23473560"]["imageinfo"][0]["url"]
with open(project_path / "output/wiki/29.txt", "w") as f:
f.write(r)
print("Done.")
import re
from path import project_path
from q21 import load_uk
from q25 import read_info
from q25 import info_to_dict
def rm_emph(text):
return re.sub(r"('{2,})([^']+)\1", r"\2", text)
if __name__ == "__main__":
print("\rSolving Q26 ... ", end="")
r = info_to_dict(rm_emph(read_info(load_uk())))
with open(project_path / "output/wiki/26.txt", "w") as f:
f.write("\n".join("{} {}".format(k, v) for k, v in r.items()))
print("Done.")
import re
from path import project_path
from q21 import load_uk
if __name__ == "__main__":
print("\rSolving Q22 ... ", end="")
r = re.findall(r"\[\[Category:([^\|]+?)(?:|\|.+)\]\]", load_uk())
with open(project_path / "output/wiki/22.txt", "w") as f:
f.write("\n".join(r))
print("Done.")
import re
from path import project_path
from q21 import load_uk
if __name__ == "__main__":
print("\rSolving Q23 ... ", end="")
r = re.findall(r"(={2,})\s?([^=]+)\s?\1", load_uk())
with open(project_path / "output/wiki/23.txt", "w") as f:
f.write("\n".join("{} {}".format(len(s[0]), s[1]) for s in r))
print("Done.")