Python-我可以检测Unicode字符串语言代码吗？

Python-我可以检测Unicode字符串语言代码吗？

如果您需要检测语言以响应用户 *** 作，则可以使用google
ajax语言API
：

#!/usr/bin/env pythonimport jsonimport urllib, urllib2def detect_language(text,    userip=None,    referrer="http://stackoverflow.com/q/4545977/4279",    api_key=None):    query = {'q': text.enpre('utf-8') if isinstance(text, unipre) else text}    if userip: query.update(userip=userip)    if api_key: query.update(key=api_key)    url = 'https://ajax.googleapis.com/ajax/services/language/detect?v=1.0&%s'%(        urllib.urlenpre(query))    request = urllib2.Request(url, None, headers=dict(Referer=referrer))    d = json.load(urllib2.urlopen(request))    if d['responseStatus'] != 200 or u'error' in d['responseData']:        raise IOError(d)    return d['responseData']['language']print detect_language("Python - can I detect unipre string language pre?")

输出量

en

[Google翻译API

v2](http://pre.google.com/apis/language/translate/v2/using_rest.html)

默认限制为每天100000个字符（一次不超过5000个）。

#!/usr/bin/env python# -*- coding: utf-8 -*-import jsonimport urllib, urllib2from operator import itemgetterdef detect_language_v2(chunks, api_key):    """    chunks: either string or sequence of strings    Return list of corresponding language pres    """    if isinstance(chunks, basestring):        chunks = [chunks]    url = 'https://www.googleapis.com/language/translate/v2'    data = urllib.urlenpre(dict(        q=[t.enpre('utf-8') if isinstance(t, unipre) else t for t in chunks],        key=api_key,        target="en"), doseq=1)    # the request length MUST be < 5000    if len(data) > 5000:        raise ValueError("request is too long, see " "http://pre.google.com/apis/language/translate/terms.html")    #NOTE: use POST to allow more than 2K characters    request = urllib2.Request(url, data,        headers={'X-HTTP-Method-Override': 'GET'})    d = json.load(urllib2.urlopen(request))    if u'error' in d:        raise IOError(d)    return map(itemgetter('detectedSourceLanguage'), d['data']['translations'])

现在，您可以请求显式检测语言：

def detect_language_v2(chunks, api_key):    """    chunks: either string or sequence of strings    Return list of corresponding language pres    """    if isinstance(chunks, basestring):        chunks = [chunks]    url = 'https://www.googleapis.com/language/translate/v2/detect'    data = urllib.urlenpre(dict(        q=[t.enpre('utf-8') if isinstance(t, unipre) else tfor t in chunks],        key=api_key), doseq=True)    # the request length MUST be < 5000    if len(data) > 5000:        raise ValueError("request is too long, see " "http://pre.google.com/apis/language/translate/terms.html")    #NOTE: use POST to allow more than 2K characters    request = urllib2.Request(url, data,        headers={'X-HTTP-Method-Override': 'GET'})    d = json.load(urllib2.urlopen(request))    return [sorted(L, key=itemgetter('confidence'))[-1]['language'] for L in d['data']['detections']]

例：

print detect_language_v2(    ["Python - can I detect unipre string language pre?",     u"матрёшка",     u"打水"], api_key=open('api_key.txt').read().strip())

输出量

[u'en', u'ru', u'zh-CN']