python之如何处理重音字母、德语字母和其他字符

我的 python 脚本现在可以运行了，但是我遇到了一些小问题:

这是输出:

from BeautifulSoup import BeautifulSoup 
import urllib 
 
langCode={ 
    "arabic":"ar", "bulgarian":"bg", "chinese":"zh-CN", 
    "croatian":"hr", "czech":"cs", "danish":"da", "dutch":"nl", 
    "english":"en", "finnish":"fi", "french":"fr", "german":"de", 
    "greek":"el", "hindi":"hi", "italian":"it", "japanese":"ja", 
    "korean":"ko", "norwegian":"no", "polish":"pl", "portugese":"pt", 
    "romanian":"ro", "russian":"ru", "spanish":"es", "swedish":"sv" } 
 
def setUserAgent(userAgent): 
    urllib.FancyURLopener.version = userAgent 
    pass 
 
def translate(text, fromLang, toLang): 
    setUserAgent("Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.1) Gecko/2008070400 SUSE/3.0.1-0.1 Firefox/3.0.1") 
    try: 
        postParameters = urllib.urlencode({"langpair":"%s|%s" %(langCode[fromLang.lower()],langCode[toLang.lower()]), "text":text,"ie":"UTF8", "oe":"UTF8"}) 
    except KeyError, error: 
        print "Currently we do not support %s" %(error.args[0]) 
        return 
 
    page = urllib.urlopen("http://translate.google.com/translate_t", postParameters) 
    content = page.read() 
    page.close() 
 
    htmlSource = BeautifulSoup(content) 
    translation = htmlSource.find('span', title=text ) 
    return translation.renderContents() 
 
 
print translate("Good morning to you friend!", "English", "German") 
print translate("Good morning to you friend!", "English", "Italian") 
print translate("Good morning to you friend!", "English", "Spanish") 
 
Guten Morgen, du Freund! 
Buongiorno a te amico! 
Buenos días a ti amigo! 

如何管理非基本英文字母？你会如何建议我解决这个问题？我在想一本字典来用另一个字符替换某些链，但我确信 Python 已经有了这样的东西。包括电池等等。 :P

谢谢。

请您参考如下方法:

不要解析 http://translate.google.com/translate_t，因为 Google 为此目的提供了 AJAX 服务。 ajax.googleapis.com返回的json数据中的translatedText已经是unicode字符串。

import urllib2 
import urllib 
import sys 
import json 
 
LANG={ 
    "arabic":"ar", "bulgarian":"bg", "chinese":"zh-CN", 
    "croatian":"hr", "czech":"cs", "danish":"da", "dutch":"nl", 
    "english":"en", "finnish":"fi", "french":"fr", "german":"de", 
    "greek":"el", "hindi":"hi", "italian":"it", "japanese":"ja", 
    "korean":"ko", "norwegian":"no", "polish":"pl", "portugese":"pt", 
    "romanian":"ro", "russian":"ru", "spanish":"es", "swedish":"sv" } 
 
def translate(text,lang1,lang2): 
    base_url='http://ajax.googleapis.com/ajax/services/language/translate?'     
    langpair='%s|%s'%(LANG.get(lang1.lower(),lang1), 
                      LANG.get(lang2.lower(),lang2)) 
    params=urllib.urlencode( (('v',1.0), 
                       ('q',text.encode('utf-8')), 
                       ('langpair',langpair),) ) 
    url=base_url+params 
    content=urllib2.urlopen(url).read() 
    try: trans_dict=json.loads(content) 
    except AttributeError: 
        try: trans_dict=json.load(content)     
        except AttributeError: trans_dict=json.read(content) 
    return trans_dict['responseData']['translatedText'] 
 
print translate("Good morning to you friend!", "English", "German") 
print translate("Good morning to you friend!", "English", "Italian") 
print translate("Good morning to you friend!", "English", "Spanish") 

产量

Guten Morgen, du Freund! 
Buongiorno a te amico! 
Buenos días a ti amigo!