dramaVol.py

from urllib.request import urlopen
import bs4
import os.path
import openpyxl

# openpyxl: http://liyangliang.me/posts/2013/02/using-openpyxl-to-read-and-write-xlsx-files/

def yahoo_dict(word):
  html = urlopen("https://tw.dictionary.search.yahoo.com/search?p=%s" % word).read().decode("utf-8")
  bs = bs4.BeautifulSoup(html, "html.parser")

  explainArea = bs.select(".explain.DictionaryResults")[0]
  wordClassList = explainArea.select(".compTitle")
  wordExplainsList = explainArea.select(".compArticleList")

  meaning = ""
  for i in range(len(wordClassList)):
    wordClass = wordClassList[i].getText()
    wordExplains = [h4.getText() for h4 in wordExplainsList[i].select("h4")]

    meaning += "%s\n" % wordClass
    for exp in wordExplains:
      meaning += "  %s\n" % exp
  return meaning

### main

FILE_NAME = '2brokegirls.xlsx'

if os.path.isfile(FILE_NAME):
  wb = openpyxl.load_workbook(FILE_NAME)
else:
  wb = openpyxl.Workbook()
  wb.remove_sheet(wb.active)

season  = input('這是第幾季?: ')
episode = input('這是第幾集?: ')
sheet_name = "S%02dEP%02d" % (int(season), int(episode))

if sheet_name in wb.get_sheet_names():
  sh = wb.get_sheet_by_name(sheet_name)
else:
  sh = wb.create_sheet(sheet_name)

while True:
  word = input("請輸入單字: ")
  nextRow = len(sh.rows) + 1
  sh.cell(row=nextRow, column=1).value = word
  sh.cell(row=nextRow, column=2).value = yahoo_dict(word)

  wb.save(filename=FILE_NAME)