0
영어를 중국어로 번역 할 수 있도록 python babelizer를 수정했습니다.파이썬으로 babelfish로 번역을 자동화하려고 시도했습니다.
## {{{ http://code.activestate.com/recipes/64937/ (r4)
# babelizer.py - API for simple access to babelfish.altavista.com.
# Requires python 2.0 or better.
#
# See it in use at http://babel.MrFeinberg.com/
"""API for simple access to babelfish.altavista.com.
Summary:
import babelizer
print ' '.join(babelizer.available_languages)
print babelizer.translate('How much is that doggie in the window?',
'English', 'French')
def babel_callback(phrase):
print phrase
sys.stdout.flush()
babelizer.babelize('I love a reigning knight.',
'English', 'German',
callback = babel_callback)
available_languages
A list of languages available for use with babelfish.
translate(phrase, from_lang, to_lang)
Uses babelfish to translate phrase from from_lang to to_lang.
babelize(phrase, from_lang, through_lang, limit = 12, callback = None)
Uses babelfish to translate back and forth between from_lang and
through_lang until either no more changes occur in translation or
limit iterations have been reached, whichever comes first. Takes
an optional callback function which should receive a single
parameter, being the next translation. Without the callback
returns a list of successive translations.
It's only guaranteed to work if 'english' is one of the two languages
given to either of the translation methods.
Both translation methods throw exceptions which are all subclasses of
BabelizerError. They include
LanguageNotAvailableError
Thrown on an attempt to use an unknown language.
BabelfishChangedError
Thrown when babelfish.altavista.com changes some detail of their
layout, and babelizer can no longer parse the results or submit
the correct form (a not infrequent occurance).
BabelizerIOError
Thrown for various networking and IO errors.
Version: $Id: babelizer.py,v 1.4 2001/06/04 21:25:09 Administrator Exp $
Author: Jonathan Feinberg <[email protected]>
"""
import re, string, urllib
import httplib, urllib
import sys
"""
Various patterns I have encountered in looking for the babelfish result.
We try each of them in turn, based on the relative number of times I've
seen each of these patterns. $1.00 to anyone who can provide a heuristic
for knowing which one to use. This includes AltaVista employees.
"""
__where = [ re.compile(r'name=\"q\">([^<]*)'),
re.compile(r'td bgcolor=white>([^<]*)'),
re.compile(r'<\/strong><br>([^<]*)')
]
# <div id="result"><div style="padding:0.6em;">??</div></div>
__where = [ re.compile(r'<div id=\"result\"><div style=\"padding\:0\.6em\;\">(.*)<\/div><\/div>', re.U) ]
__languages = { 'english' : 'en',
'french' : 'fr',
'spanish' : 'es',
'german' : 'de',
'italian' : 'it',
'portugese' : 'pt',
'chinese' : 'zh'
}
"""
All of the available language names.
"""
available_languages = [ x.title() for x in __languages.keys() ]
"""
Calling translate() or babelize() can raise a BabelizerError
"""
class BabelizerError(Exception):
pass
class LanguageNotAvailableError(BabelizerError):
pass
class BabelfishChangedError(BabelizerError):
pass
class BabelizerIOError(BabelizerError):
pass
def saveHTML(txt):
f = open('page.html', 'wb')
f.write(txt)
f.close()
def clean(text):
return ' '.join(string.replace(text.strip(), "\n", ' ').split())
def translate(phrase, from_lang, to_lang):
phrase = clean(phrase)
try:
from_code = __languages[from_lang.lower()]
to_code = __languages[to_lang.lower()]
except KeyError, lang:
raise LanguageNotAvailableError(lang)
html = ""
try:
params = urllib.urlencode({'ei':'UTF-8', 'doit':'done', 'fr':'bf-res', 'intl':'1' , 'tt':'urltext', 'trtext':phrase, 'lp' : from_code + '_' + to_code , 'btnTrTxt':'Translate'})
headers = {"Content-type": "application/x-www-form-urlencoded","Accept": "text/plain"}
conn = httplib.HTTPConnection("babelfish.yahoo.com")
conn.request("POST", "http://babelfish.yahoo.com/translate_txt", params, headers)
response = conn.getresponse()
html = response.read()
saveHTML(html)
conn.close()
#response = urllib.urlopen('http://babelfish.yahoo.com/translate_txt', params)
except IOError, what:
raise BabelizerIOError("Couldn't talk to server: %s" % what)
#print html
for regex in __where:
match = regex.search(html)
if match:
break
if not match:
raise BabelfishChangedError("Can't recognize translated string.")
return match.group(1)
#return clean(match.group(1))
def babelize(phrase, from_language, through_language, limit = 12, callback = None):
phrase = clean(phrase)
seen = { phrase: 1 }
if callback:
callback(phrase)
else:
results = [ phrase ]
flip = { from_language: through_language, through_language: from_language }
next = from_language
for i in range(limit):
phrase = translate(phrase, next, flip[next])
if seen.has_key(phrase): break
seen[phrase] = 1
if callback:
callback(phrase)
else:
results.append(phrase)
next = flip[next]
if not callback: return results
if __name__ == '__main__':
import sys
def printer(x):
print x
sys.stdout.flush();
babelize("I won't take that sort of treatment from you, or from your doggie!",
'english', 'french', callback = printer)
## end of http://code.activestate.com/recipes/64937/ }}}
와 테스트 코드
import babelizer
print ' '.join(babelizer.available_languages)
result = babelizer.translate('How much is that dog in the window?', 'English', 'chinese')
f = open('result.txt', 'wb')
f.write(result)
f.close()
print result
결과가 DIV 블록 내부 예상 할 수있다. html 응답을 저장하기 위해 스크립트를 수정했습니다. 내가 찾은 것은 모든 utf8 문자가 nul로 바뀌 었습니다. utf8 대응에 특별한주의를 기울여야합니까?