Twisted Python getPage

Question

I tried to get support on this, but I was completely confused.

Here is my code:

from twisted.internet import reactor
from twisted.web.client import getPage
from twisted.web.error import Error
from twisted.internet.defer import DeferredList
from sys import argv

class GrabPage:
 def __init__(self, page):
  self.page = page

 def start(self, *args):
  if args == ():
   # We apparently don't need authentication for this
   d1 = getPage(self.page)
  else:
   if len(args) == 2:
    # We have our login information
    d1 = getPage(self.page, headers={"Authorization": " ".join(args)})
   else:
    raise Exception('Missing parameters')

  d1.addCallback(self.pageCallback)
  dl = DeferredList([d1])
  d1.addErrback(self.errorHandler)
  dl.addCallback(self.listCallback)

 def errorHandler(self,result):
  # Bad thingy!
  pass

 def pageCallback(self, result):
  return result

 def listCallback(self, result):
  print result

a = GrabPage('http://www.google.com')
data = a.start() # Not the HTML

I want to get the HTML code that is called for pageCallback when the start () function is called. It was lavash for me. Ty! And sorry for my sucky coding.

Answer 1

You are missing the basics of Twisted. Everything revolves around reactorthat you never even run. Think of a reactor like this:

_{(source: krondo.com )}

Until you start the reactor, when setting up deferrals, all you do is chain them without events from which you can shoot.

Twisted Intro Dave Peticolas. , Twisted.

, getPage:

from twisted.web.client import getPage
from twisted.internet import reactor

url = 'http://aol.com'

def print_and_stop(output):
    print output
    if reactor.running:
       reactor.stop()

if __name__ == '__main__':
    print 'fetching', url
    d = getPage(url)
    d.addCallback(print_and_stop)
    reactor.run()

getPage , print_and_stop . reactor. getPage, print_and_stop aol.com, .

, OP:

class GrabPage:
    def __init__(self, page):
        self.page = page
        ########### I added this:
        self.data = None

    def start(self, *args):
        if args == ():
            # We apparently don't need authentication for this
            d1 = getPage(self.page)
        else:
            if len(args) == 2:
                # We have our login information
                d1 = getPage(self.page, headers={"Authorization": " ".join(args)})
            else:
                raise Exception('Missing parameters')

        d1.addCallback(self.pageCallback)
        dl = DeferredList([d1])
        d1.addErrback(self.errorHandler)
        dl.addCallback(self.listCallback)

    def errorHandler(self,result):
        # Bad thingy!
        pass

    def pageCallback(self, result):
        ########### I added this, to hold the data:
        self.data = result
        return result

    def listCallback(self, result):
        print result
        # Added for effect:
        if reactor.running:
            reactor.stop()

a = GrabPage('http://google.com')
########### Just call it without assigning to data
#data = a.start() # Not the HTML
a.start()

########### I added this:
if not reactor.running:
    reactor.run()

########### Reference the data attribute from the class
data = a.data
print '------REACTOR STOPPED------'
print
########### First 100 characters of a.data:
print '------a.data[:100]------'
print data[:100]