NIJISANJI to vdb~

add_nijisanji.py

#coding: utf8
import sys
reload(sys)
sys.setdefaultencoding("UTF8")

import requests, re, json
sess = requests.Session()
r = sess.get("https://nijisanji.ichikara.co.jp/member/")
urls = re.findall(r"href=(https://nijisanji\.ichikara\.co\.jp/member/.*?)>", r.text)

ret = []
for u in urls:
    r = sess.get(u)
    name = re.findall(r'class="elementor-heading-title elementor-size-default">(.*?)</h2>', r.text)[0]
    u2b = re.findall(r"https://www\.youtube\.com/channel/(.*?)\?sub_confirmation=1", r.text)[0]
    twi = re.findall(r'href="https://twitter\.com/(.*?)"', r.text)[0]
    ret.append((name, u2b, twi))

json.dump(ret, open("nijisanji.json", 'w'), ensure_ascii=False, indent=2)

r = requests.get("https://vdb.vtbs.moe/json/list.json")
missing = [c for c in ret if c[1] not in r.text and c[2] not in r.text]
json.dump(missing, open("nijisanji-missing.json", 'w'), ensure_ascii=False, indent=2)

template = """{
  "name": {
    "jp": "{NAME}"
  },
  "accounts": {
    "youtube": "{U2B}",
    "twitter": "{TWI}"
  },
  "group": "NIJISANJI"
}"""

commands = [["name", "NyaMisty"]]

for c in missing:
    content = template.replace("{NAME}", c[0]).replace("{U2B}", c[1]).replace("{TWI}", c[2])
    commands.append(["put", "%s.json" % c[0], content])

print json.dumps(commands)