#!/usr/bin/env python # Copyright 2011, Nathan Milford # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # Extracts the URLs from a google reader export with the magic of xpath. import sys from xml.dom.ext.reader import Sax2 from xml import xpath srcFile = sys.argv[1] xml = Sax2.FromXmlFile(srcFile).documentElement for url in xpath.Evaluate('//@htmlUrl', xml): print url.value
def Benchmark(fileName): return Sax2.FromXmlFile(fileName)