getpage

#!/usr/bin/env python2
# -*- mode:python -*-

import sys     # for handling arguments (argv)
import libxml2
import urllib2


def namespaceDefs(node):
    n = node.nsDefs()
    while n:
        yield n
        n = n.next

def checkNamespaceDefs(node, count):
    nsList = list(namespaceDefs(node))
    #print nsList
    if len(nsList) != count :
        raise Exception("Error: saw %d namespace declarations.  Expected %d" % (len(nsList), count))

def printNamespaceDefs(node):
    nsList = list(namespaceDefs(node))
    print nsList
    

def read_url(f_use):
    if len(sys.argv) > 1:
        xmlpath = sys.argv[1]
        try:
            response = urllib2.urlopen(xmlpath)
            f_use(response)
        except urllib2.URLError as e:
            sys.stderr.write("Failed to open URL \"%s\"\n\"%s\"\n"
                             % (xmlpath, e.reason))

def write_xmldoc(rfile):
    readopts = (libxml2.HTML_PARSE_RECOVER |
                libxml2.HTML_PARSE_NODEFDTD |
                libxml2.HTML_PARSE_NOERROR |
                libxml2.HTML_PARSE_NOWARNING |
                libxml2.HTML_PARSE_NONET)

    xmldoc = libxml2.htmlReadDoc(rfile.read(),None,None,readopts)
    if xmldoc:
        dumpopts = (libxml2.XML_SAVE_FORMAT   +
                    libxml2.XML_SAVE_NO_DECL  +
                    libxml2.XML_SAVE_XHTML    +
                    libxml2.XML_SAVE_AS_XML
)

        root = xmldoc.getRootElement()
        root.saveTo(sys.stdout, None, dumpopts)
        # xmldoc.formatDump(sys.stdout,dumpopts)
        xmldoc.freeDoc()
    else:
        sys.stderr.write("failed to parse html document")

def main():
    read_url(write_xmldoc)


if __name__ == "__main__":
   main()