使用Python实现利用google翻译英文文章中的单词

4k jdi0O1{!K0#-*-coding:gb2312-*-51Testing软件测试网&k:s:]Ceu+W
import urllib,urllib251Testing软件测试网:|3],}g|
from sgmllib import SGMLParser51Testing软件测试网YZ6i:W2VB)`Xw
import re

"h!?+@0Z,z9W0class URLLister(SGMLParser):51Testing软件测试网1C"F3v/K9K

}6OL4hqr
FX(L0    def __init__(self):

@PO1p,aM1b3~vK0        SGMLParser.__init__(self)

        self.result = []51Testing软件测试网"\[$nhap U

I)f(Y7o
V%f#H0        self.open = False51Testing软件测试网G m+` [G0^A

ur3Q4yw+Gl0    def start_div(self, attrs):

        id = [v for k, v in attrs if k=='id']

C
Y(W9m^;u cpI0        if 'result_box' in id:

            self.open = True

Bm]rXR3s6L8r0    def handle_data(self, text):

+Jo@uQd0K(S+D0        if self.open:51Testing软件测试网.[q]U3{5i
            self.result.append(text)51Testing软件测试网zQa5qM{
            self.open = False

#读取Txt文件中的英文文章并利用正则表达式解析单词51Testing软件测试网K'eT7Si,g

f = open("D:\\result.txt","w")
+O x)nX#oB-MO0r = open("D:\\input.txt","r")
4Bb8c @#@0R0strs =r.read()
w8\"QA V5D&~:l$q0s = re.findall("\w+",strs)51Testing软件测试网+omp[Z[
for i in s:
l6[7Q+Ud4m~N3j0    m = re.search("\d+",i)51Testing软件测试网s.z5s+Y S'U'J
    n = re.search("\W+",i)
P~|&HIn0    if not m and  not n:51Testing软件测试网 o.D5VE2p/yTj5v
        values={'hl':'zh-CN','ie':'UTF-8','text':i,'langpair':"en|zh-CN" }
U)ij6SNW0        url='http://translate.google.cn/translate_t'
4J
Z w%\9I;B~AJD @0        data = urllib.urlencode(values)
I u@~$nXc0        req = urllib2.Request(url, data)
5l!q&vR*Xkim1}9i0        req.add_header('User-Agent', "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 2.0.50727)")
1pl#g^L,S1V0        response = urllib2.urlopen(req)51Testing软件测试网;sa6O:rOE yQ
        ul = URLLister()
DA*I)~5~\0        ul.feed(response.read())
asS!k5hQcJ0        f.write(ul.result[0]+"\n")51Testing软件测试网5h#~*eqnt.CVI(}
r.close()51Testing软件测试网gd/t[h1m
f.close()

y/hH:fE[
M0 51Testing软件测试网1S&EM ~"ZN