英语中的定义单词（Defining Vocabulary）

参见：http://rocflytosky.iteye.com/blog/116646

附件是用python从dict.cn查词后，附加了中文和例句的文件（纯文本）

查词程序处理牛津和朗文的区别就是牛津里面带了词性，用split给去掉了，代码如下：

python 代码

#!d:/python25/python.exe
# -*- coding: gbk -*-
'''
用途:读取文本文件中的单词，获取中文意义写入文件
     感谢dict.cn 提供web查词功能
作者:invalid
mail:[email protected]
'''
import urllib
import urlparse
import re
import string
import sys
import pprint
from sgmllib import SGMLParser


class Html2TXT(SGMLParser):
    ''' convert html to txt parser'''

    def __init__ (self):
        ''' init '''
        self.text = ''
        SGMLParser.__init__(self)

    def reset(self):
        ''' reset '''
        self.text = ''
        SGMLParser.reset(self)

    def handle_data(self, text):
        ''' deal '''
        self.text += text

def get_txt(hname):
    ''' Get Txt'''
    html = open(hname,"r").read()
    parser = Html2TXT()
    parser.feed(html)
    parser.close()
    return parser.text

def getpage(url):
    ''' get page '''
    data = [];
    try:
        filehandle = urllib.urlopen(url)
        data = filehandle.readlines()
        filehandle.close()
    except:
        pass

    return data


def main(argv):
    ''' main '''

    if len(argv) < 2:
        print "%s wordsfile" % argv[0]
        sys.exit(0)

    urlbase = 'http://dict.cn/mini.php?q=%s'
    words = open(argv[1],"rt").readlines()
    #print words
    words2 = {}
    for word in words:
        word = word.strip()
        #朗文注释掉下面二行，比提供查询词组功能
        word = word.split(" ")[0].split(",")[0]
        if word.startswith('"'): word = word[1:]
        url = urlbase % word
        for x in range(10):
            print url
            data = getpage(url)
            open('tmp.htm','w').writelines(data)
            data = get_txt('tmp.htm')
            if (len(data)>2):
                break;

        if (len(data)>2):
            start = data.find("'#ffffff')")+11
            end   = data.find("\n\r\n\r\n加入生词本")
            #pprint.pprint(data[start:end])
            words2[word]= data[start:end]

    wk = words2.keys()
    wk.sort()
    outfile = open(argv[1]+".txt","w")
    for w in wk:
        print >>outfile,"-----------------------"
        print >>outfile, w, words2[w]
    outfile.close()

if __name__ == "__main__":

    main(sys.argv)