我面临一个情况,我正在阅读一串文本,我需要检测语言代码(en、de、fr、es等)。
在Python中有没有简单的方法可以做到这一点?
在Python中有没有简单的方法可以做到这一点?
#!/usr/bin/env python
import json
import urllib, urllib2
def detect_language(text,
userip=None,
referrer="https://dev59.com/ym855IYBdhLWcg3wFAHy",
api_key=None):
query = {'q': text.encode('utf-8') if isinstance(text, unicode) 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.urlencode(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 unicode string language code?")
en
默认限制每天100000个字符(一次不超过5000个字符)。
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import json
import urllib, urllib2
from operator import itemgetter
def detect_language_v2(chunks, api_key):
"""
chunks: either string or sequence of strings
Return list of corresponding language codes
"""
if isinstance(chunks, basestring):
chunks = [chunks]
url = 'https://www.googleapis.com/language/translate/v2'
data = urllib.urlencode(dict(
q=[t.encode('utf-8') if isinstance(t, unicode) 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://code.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'])
def detect_language_v2(chunks, api_key):
"""
chunks: either string or sequence of strings
Return list of corresponding language codes
"""
if isinstance(chunks, basestring):
chunks = [chunks]
url = 'https://www.googleapis.com/language/translate/v2/detect'
data = urllib.urlencode(dict(
q=[t.encode('utf-8') if isinstance(t, unicode) else t
for 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://code.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']]
例子:
print detect_language_v2(
["Python - can I detect unicode string language code?",
u"матрёшка",
u"打水"], api_key=open('api_key.txt').read().strip())
[u'en', u'ru', u'zh-CN']
import unicodedata
def is_greek(term):
return 'GREEK' in unicodedata.name(term.strip()[0])
def is_hebrew(term):
return 'HEBREW' in unicodedata.name(term.strip()[0])
但正如名字所说,它只是猜测语言。您不能期望100%正确的结果。 编辑: guess-language已经停止维护。但有一个支持python3的分支:guess_language-spirit尝试确定Unicode(utf-8)文本的自然语言。
langdetect
上,现在我正在转向CLD
,它比langdetect
快16倍,并且准确率达到了98.8%。试试通用编码检测器
,它是从Firefox的chardet
模块移植到Python的。
如果你只有有限的语言选择,你可以使用每种语言的一组字典(可能仅包括最常见的单词),然后检查输入中的单词是否在这些字典中。