getaddrinfo returns always 11001 (host not found)

Question

Although the searched FQDN appears in etc\hosts file.

Any idea? Thanks a lot!

Answer 1

Take a look at this http://stackoverflow.com/questions/490235/hostname-not-translated-into-an-ip-address-using-winsock

getaddrinfo may be giving you an IPv6 address, or perhaps the machine has more than one IP address and you're trying to connect to the wrong one.

Answer 2

The following code contains a recursion function which is giving an error: I think the problem is the len(childLinks)==0 which cant be true bcoz web page will definately contain link so len of childLinks will never be zero and this recursive function will go into infinite loop.What should i do in order to come out of the infinite loop.

import sgmllib

import urllib, sgmllib

import sys

sys.setrecursionlimit(1000)

class Parser(sgmllib.SGMLParser):

def parse(self, s):
    "Parse the given string 's'."
    self.feed(s)
    self.close()

def __init__(self, verbose=0):
    "Initialise an object, passing 'verbose' to the superclass."
    sgmllib.SGMLParser.__init__(self, verbose)
    self.hyperlinks = []
    self.inside_a_element = 0

def start_a(self, attributes):
    "Process a hyperlink and its 'attributes'."

    for name, value in attributes:
        if name == "href":
            self.hyperlinks.append(value)
            self.inside_a_element = 1

def end_a(self):
    "Record the end of a hyperlink."
    self.inside_a_element = 0

def get_hyperlinks(self):
    "Return the list of hyperlinks."
    return self.hyperlinks

def process_page(self, parentNode):

    print "parent :: ", parentNode.nodeName

    file= urllib.urlopen(parentNode.nodeName)
    data = file.read()
    parser = Parser()
    parser.parse(data)
    childLinks = parser.get_hyperlinks()
    if len(childLinks) == 0:
        print "Leaf Node :: ", parentNode.nodeName
        return

    for childLink in childLinks:
        childNode = Node(childLink)
        parentNode.addChild(childNode)
        print "   Child :: ", childNode.nodeName
        self.process_page(childNode)

class Node(object):

def __init__(self, nodeName=None, children=[]):
    self.nodeName = nodeName
    self.children = children


def print_info(self):
    print "RootNode", "<" + self.rootNode + ">"

def getNodeName(self):
    return nodeName

def setNodeName(self,value):
    self.nodeName=value

def getParentNode(self):
    return parentNode

def setChildren(children):
    self.children=children

def addChild(self, child):
    self.children.append(child)

def getChildren(self):
    return children

def setRootNode(self,rootNode):
     self.rootNode="d://PythonSample/Page.html"

def getRootNode(self):
    return self.rootNode

def getFirstChild():
    firstChild=Node("d://PythonSample/Page.html")
    return firstChild

class TreeCreator:

def __init__(self, startURL):
    self.startURL = startURL

def createTree(self):
    parser=Parser()
    node = Node(startURL)
    parser.process_page(node)
    return node

def printTree(self, node):
    print node.nodeName
    children = node.children

    if len(children) == 0 :
        return

    for childNode in children:
        print "   ->" ,childNode.nodeName
        #self.printTree(childNode)

if name == 'main':

startURL="http://ocado.com"  
treeCreator =TreeCreator(startURL)
nodeTree = treeCreator.createTree()
treeCreator.printTree(nodeTree);

Kindly suggest something.

Answer 3

Since I don't have code, here's a guess:

getaddrinfo("http://www.example.com");

Doesn't work; getaddrinfo takes a hostname not a URL.