TW_Eta_Rank_Analyzer

TW_down_HK.py

import urllib.request, datetime, os

# This code executes many http get requests in short time
# So don't abuse it

NumPages = 20
startTime = datetime.datetime.now()
if startTime.hour < 11:
  dirName = (startTime - datetime.timedelta(days=1)).strftime('%Y%m%d')
else:
  dirName = startTime.strftime('%Y%m%d')
  
# create saving directory
if not os.path.exists(dirName):
  os.makedirs(dirName)

for k in [x+1 for x in range(NumPages)]:
  url = f'https://tales.nexon.com/Community/Ranking/EtaRank?page={k}&cc=99&sc=7'
  with urllib.request.urlopen(url) as response:
    html = response.read().decode("utf-8")
    fname = f"hk_{k}.html"
    with open(f"{dirName}/{fname}", 'w', encoding="utf-8") as f:
      f.write(html)

TW_down_NP.py

import urllib.request, datetime, os

# This code executes many http get requests in short time
# So don't abuse it

NumPages = 20
startTime = datetime.datetime.now()
if startTime.hour < 11:
  dirName = (startTime - datetime.timedelta(days=1)).strftime('%Y%m%d')
else:
  dirName = startTime.strftime('%Y%m%d')
  
# create saving directory
if not os.path.exists(dirName):
  os.makedirs(dirName)

for k in [x+1 for x in range(NumPages)]:
  url = f'https://tales.nexon.com/Community/Ranking/EtaRank?page={k}&cc=99&sc=16'
  with urllib.request.urlopen(url) as response:
    html = response.read().decode("utf-8")
    fname = f"{k}.html"
    with open(f"{dirName}/{fname}", 'w', encoding="utf-8") as f:
      f.write(html)

TW_down_postprocessor.py

import bs4
import collections
import operator

dirName = "20231009"
NumPages = 20
serverList = ["네냐플", "하이아칸"]
serverFileNamePrefix = ["", "hk_"]

for k2 in range(len(serverList)):
  print(f"{dirName} 기준 {serverList[k2]} 서버 에타랭킹 캐릭별 분포")

  charList = []
  for k in [x+1 for x in range(NumPages)]:
    fname = f"{serverFileNamePrefix[k2]}{k}.html"
    with open(f"{dirName}/{fname}", 'r', encoding="utf-8") as f:
      html = f.read()
      soup = bs4.BeautifulSoup(html,features="html.parser")
      characterAnchorTags = soup.find_all("td", {"class": "col_rank"})
      for anchorTag in characterAnchorTags:
        rootTag = anchorTag.parent
        clsNames = ["number", "charname", "nickname", "col_level", "col_point"]
        tagNames = ["span", "span", "span", "td", "td"]
        characterValues = [rootTag.find(tagNames[k], {"class": clsNames[k]}).text for k in range(len(clsNames))]
        charList.append(characterValues)

  charNames = [elem[1] for elem in charList]

  # for elem in collections.Counter(charNames).most_common():
  #   print(f"{elem[0]:10}\t{elem[1]:>3}")

  EtaLvIndex = 3
  charListLv5 = [elem for elem in charList if int(elem[EtaLvIndex])>=5]
  charNamesLv5 = [elem[1] for elem in charListLv5]

  EtaLv1MostCommon = collections.Counter(charNames).most_common()
  EtaLv5MostCommon = collections.Counter(charNamesLv5).most_common()
  EtaLv5MostCommonCharNames = [elem[0] for elem in EtaLv5MostCommon] 

  EtaLv5dict = dict(EtaLv5MostCommon)
  EtaLv1dict = dict(EtaLv1MostCommon)

  charTable = [[charName, EtaLv5dict[charName], EtaLv1dict[charName]] for charName in EtaLv5MostCommonCharNames]
  sortedCharTable = sorted(charTable, key=operator.itemgetter(1,2),reverse=True)

  print(f"{'캐릭명':10}\t{'5렙↑':>3}\t{'1렙↑':>3}")
  print(f"{'------':10}\t{'---':>3}\t{'---':>3}")
  for elem in sortedCharTable:
    print(f"{elem[0]:10}\t{elem[1]:>3}\t{elem[2]:>3}")

  print(f"{'------':10}\t{'---':>3}\t{'---':>3}")
  print(f"{'계':10}\t{len(charListLv5):>3}\t{len(charList):>3}")

  clsTypes = ["등수", "캐릭터", "캐릭터명", "에타레벨", "정수개수"]
  txtArranged = ",".join(clsTypes) + "\n" + "\n".join([",".join(elem) for elem in charList])
  with open(f"{dirName}_{serverList[k2]}.txt", 'w', encoding="utf-8") as f:
      f.write(txtArranged)