黄舟2017-04-17 11:24:371楼

我忘记这代码是从哪儿来的了，大概是从这个改的吧：http://yongsun.me/2010/07/%E5%AF%BC%E5%85%A5sogou%E8%BE%93%E5%85%A5%E6%B3%95%E7%9A%84%E7%BB%86%E8%83%9E%E8%AF%8D%E5%BA%93/

importer.py

#!/usr/bin/python2

import struct

import os, sys

def read_utf16_str (f, offset=-1, len=2):

if offset >= 0:

f.seek(offset)

str = f.read(len)

return str.decode('UTF-16LE')

def read_uint16 (f):

return struct.unpack ('

def get_word_from_sogou_cell_dict (fname):

f = open (fname, 'rb')

file_size = os.path.getsize (fname)

hz_offset = 0

mask = struct.unpack ('B', f.read(128)[4])[0]

if mask == 0x44:

hz_offset = 0x2628

elif mask == 0x45:

hz_offset = 0x26c4

else:

sys.exit(1)

title = read_utf16_str (f, 0x130, 0x338 - 0x130)

type = read_utf16_str (f, 0x338, 0x540 - 0x338)

desc = read_utf16_str (f, 0x540, 0xd40 - 0x540)

samples = read_utf16_str (f, 0xd40, 0x1540 - 0xd40)

py_map = {}

f.seek(0x1540+4)

while 1:

py_code = read_uint16 (f)

py_len = read_uint16 (f)

py_str = read_utf16_str (f, -1, py_len)

if py_code not in py_map:

py_map[py_code] = py_str

if py_str == 'zuo':

break

f.seek(hz_offset)

while f.tell() != file_size:

word_count = read_uint16 (f)

pinyin_count = read_uint16 (f) / 2

py_set = []

for i in range(pinyin_count):

py_id = read_uint16(f)

py_set.append(py_map[py_id])

py_str = "'".join (py_set)

for i in range(word_count):

word_len = read_uint16(f)

word_str = read_utf16_str (f, -1, word_len)

f.read(12)

yield py_str, word_str

f.close()

def showtxt (records):

for (pystr, utf8str) in records:

#print len(utf8str), utf8str

print utf8str.encode('utf8')

def main ():

if len (sys.argv) != 2:

print "Please specify the Sogou PinYin Cell dict file!"

exit (1)

generator = get_word_from_sogou_cell_dict (sys.argv[1])

showtxt(generator)

if __name__ == "__main__":

main()

然后到 http://pinyin.sogou.com/dict/ 下载搜狗细胞词库。运行 ./importer.py 文件名

运行后会向标准输出输出 *.scel 文件里的所有词，每行一个。