def submit(self):
self.trace()
self.response = self.browser.submit()
self.text = self.Decode(self.response.read())
self.parsed = htmldom(self.Encode(self.text))
self.handleHtmlErrors()
def submit( self ): self.trace() self.response = self.browser.submit() self.text = self.Decode(self.response.read()) self.parsed = htmldom(self.Encode(self.text)) self.handleHtmlErrors()
def load(self,
url=None,
title=None,
parameters=None,
GET=False,
visit=False,
parse_as=None,
unicodify=True,
censor_url=False,
catch_errors=True):
(self.trace() if not censor_url else self.trace(
overrides={'parameters': '<<hidden>>'}))
# get URL & query string
if not url:
if not title:
raise self.Error, 'Browser::load called with no URL or page title to load'
url = self.url_base + self.path_article + title
if parameters:
parameters = self.UrlEncode(parameters)
# force GET mode?
if GET and parameters:
if url.find('?') != -1:
url = '%s%s' % (url, '&%s' % parameters)
else:
url = '%s%s' % (url, '?%s' % parameters)
parameters = None
self.last_url = url
else:
self.last_url = u'%s << %s' % (url, parameters)
if censor_url:
self.last_url = '<<hidden>>'
self.traceMessage(self.last_url)
# load page
if visit:
self.response = self.browser.open(url, parameters)
# bugfix -- mechanize confused by <br/>
self.response.set_data(self.response.get_data().replace(
"<br/>", "<br />"))
self.browser.set_response(self.response)
else:
self.response = self.browser.open_novisit(url, parameters)
# fetch page text
self.text = self.response.read()
if unicodify:
self.text = self.Decode(self.text)
# parse page text
if not parse_as:
self.parsed = None
return
parse_as = parse_as.lower()
if parse_as == 'xml':
self.parsed = xmldom.parseString(self.Encode(self.text))
if catch_errors:
self.handleApiErrors()
elif parse_as == 'html':
self.parsed = htmldom(self.Encode(self.text))
if catch_errors:
self.handleHtmlErrors()
elif parse_as == 'json':
self.parsed = simplejson.loads(self.Encode(self.text))
else:
raise self.Error, 'Browser::load cannot parse text as "%s", unrecognized format' % parse_as
def load( self, url = None, title = None, parameters = None, GET = False, visit = False, parse_as = None, unicodify = True, censor_url = False, catch_errors = True ):
(self.trace() if not censor_url else self.trace(overrides = {'parameters':'<<hidden>>'}))
# get URL & query string
if not url:
if not title:
raise self.Error, 'Browser::load called with no URL or page title to load'
url = self.url_base + self.path_article + title
if parameters:
parameters = self.UrlEncode( parameters )
# force GET mode?
if GET and parameters:
if url.find( '?' ) != -1:
url = '%s%s' % (url, '&%s' % parameters)
else:
url = '%s%s' % (url, '?%s' % parameters)
parameters = None
self.last_url = url
else:
self.last_url = u'%s << %s' % (url, parameters)
if censor_url:
self.last_url = '<<hidden>>'
self.traceMessage(self.last_url)
# load page
if visit:
self.response = self.browser.open( url, parameters )
# bugfix -- mechanize confused by <br/>
self.response.set_data(self.response.get_data().replace("<br/>", "<br />"))
self.browser.set_response(self.response)
else:
self.response = self.browser.open_novisit( url, parameters )
# fetch page text
self.text = self.response.read()
if unicodify:
self.text = self.Decode(self.text)
# parse page text
if not parse_as:
self.parsed = None
return
parse_as = parse_as.lower()
if parse_as == 'xml':
self.parsed = xmldom.parseString(self.Encode(self.text))
if catch_errors:
self.handleApiErrors()
elif parse_as == 'html':
self.parsed = htmldom(self.Encode(self.text))
if catch_errors:
self.handleHtmlErrors()
elif parse_as == 'json':
self.parsed = simplejson.loads(self.Encode(self.text))
else:
raise self.Error, 'Browser::load cannot parse text as "%s", unrecognized format' % parse_as
