Skip to content

Instantly share code, notes, and snippets.

@K-Wu
Created February 25, 2017 04:17
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save K-Wu/cd9ca275767bfa30718cad0466f9df25 to your computer and use it in GitHub Desktop.
Save K-Wu/cd9ca275767bfa30718cad0466f9df25 to your computer and use it in GitHub Desktop.
import to quizlet from bing dictionary
#!/usr/bin/python2.7
# -*- coding: UTF-8 -*-
import sys
if len(sys.argv)!=3:
print "Usage:"
print "python bing2quizlet.py BingDictExport.txt QuizletImport.txt"
exit(1)
print sys.argv
infile=sys.argv[1]
outfile=sys.argv[2]
word_anchor=u"单词:"
anchor=u":"
word_dict={}
encoding_string="utf8"
with open(infile) as ifd:
line=ifd.readline()
try:
line = unicode(line, "utf8")
except UnicodeDecodeError:
print "the encoding of input file is not utf8, try gb2312"
encoding_string="gb2312"
with open(infile) as ifd:
lines=ifd.readlines()
for idx in range(len(lines)):
line=unicode(lines[idx],encoding_string)
if line.find(word_anchor)==0:
word_start_index=line.find(anchor)+1
word=line[word_start_index:-1]
idx+=2
line=unicode(lines[idx],encoding_string)
meaning_start_index=line.find(anchor)+1
meaning=line[meaning_start_index:]
word_dict[word]=meaning
with open(outfile,'w') as ofd:
for word,meaning in word_dict.items():
line=word+u"\t"+meaning
line=line.encode("utf8")
ofd.write(line)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment