Here is my code.
import urllib2
import urllib
import json
from BeautifulSoup import BeautifulSoup
class parser:
"""
This class uses the Beautiful Soup library to scrape the information from
the HTML source code from Google Translate.
It also offers a way to consume the AJAX result of the translation, however
encoding on Windows won't work well right now so it's recommended to use
the scraping method.
"""
def fromHtml(self, text, languageFrom, languageTo):
"""
Returns translated text that is scraped from Google Translate's HTML
source code.
"""
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":"n开发者_如何学运维o", "polish":"pl", "portugese":"pt",
"romanian":"ro", "russian":"ru", "spanish":"es", "swedish":"sv" }
urllib.FancyURLopener.version = "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[languageFrom.lower()],langCode[languageTo.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()
def fromAjaxService(self, text, languageFrom, languageTo):
"""
Returns a simple string translating the text from "languageFrom" to
"LanguageTo" using Google Translate AJAX Service.
"""
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" }
base_url='http://ajax.googleapis.com/ajax/services/language/translate?'
langpair='%s|%s'%(LANG.get(languageFrom.lower(),languageFrom),
LANG.get(languageTo.lower(),languageTo))
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']
Now in another class called TestingGrounds.py I want to try out both methods, but I get the following error:
from Parser import parser
print parser.fromHtml("Hello my lady!", "English", "Italian")
Traceback (most recent call last): File "C:\Users\Sergio.Tapia\Documents\NetBeansProjects\BabylonPython\src\TestingGrounds.py", line 3, in print parser.fromHtml("Hello my lady!", "English", "Italian") TypeError: unbound method fromHtml() must be called with parser instance as first argument (got str instance instead)
You have to have an instance of the parser
class, not call the method on the class itself.
from Parser import parser
print parser().fromHTML("Hello my lady!", "English", "Italian")
or
from Parser import parser
p = parser()
p.fromHTML(...)
Alternatively, you could make fromHTML
a staticmethod:
class parser(object): # you should probably use new-style classes
...
@staticmethod
def fromHTML(...):
...
which you could then use like:
from Parser import parser
print parser.fromHTML(...)
If you want to use fromHtml() as a static method, useful if you don't really need to access any datamembers in parser, you'll need to do this (cut for brevity)
class parser:
@staticmethod
def fromHtml(text, languageFrom, languageTo):
# etc.
Or, if you want it to be both a static method and have the ability to be an instance method...
class parser:
@classmethod
def fromHtml(self, text, languageFrom, languageTo):
# etc.
You can now use it as parser.fromHtml()
or parser().fromHtml()
Looking at your code, I should think you'd only need a static method.
精彩评论