def choose_parser(self, path, html):
def open_website(path):
if re.match('(?=http)\w+', path):
f = urllib2.urlopen(path)
else:
f = open(path, 'r')
return f.read()
if path:
self.html = open_website(path)
if 'on AOL Answers' in self.html:
print 'aol'
import aol_answers as p
elif '- Yahoo! Answers\">' in self.html:
print 'yahoo'
import yahoo_answers as p
elif 'Ask.com' in self.html:
print 'ask'
import ask_answers as p
elif 'Search Askville' in self.html:
print 'askville'
import askville_answers as p
else:
raise ParserError('\nError: could not recognize site')
return p.parseQAPage(self.html, self.path, self.verbose)
def runTest(self):
if 'http://aolanswers.com' in self.url:
self.checkQuestionAndAnswer(aol_answers.parseQAPage(urllib2.urlopen(self.url).read(), '', False))
if 'http://answers.yahoo.com' in self.url:
self.checkQuestionAndAnswer(yahoo_answers.parseQAPage(urllib2.urlopen(self.url).read(), '', False))
if 'http://answers.ask.com/' in self.url:
self.checkQuestionAndAnswer(ask_answers.parseQAPage(urllib2.urlopen(self.url).read(), '', False))
if 'http://askville.amazon.com/' in self.url:
self.checkQuestionAndAnswer(askville_answers.parseQAPage(urllib2.urlopen(self.url).read(), '', False))