A filter to extract elements from an html file/stream

elements.py

#!/usr/bin/python

import sys
from optparse import OptionParser
from lxml import html
from lxml.cssselect import CSSSelector
from lxml.etree import XPath

def main():
    parser = OptionParser(description="Select elements from an html file with css selectors",
                          version="0.1",
                          prog="elements")

    parser.add_option("-s", "--selector", dest="selector", default=False,
                      help="a css selector", metavar="select")

    parser.add_option("-x", "--xpath", dest="xpath_exp", default=False,
                      help="an xpath selector", metavar="xpath")

    parser.add_option("-o", "--outfile", dest="out_file", default=False,
                        metavar="OUT", help="defaults to stdout")

    parser.add_option("-i", "--infile", dest="in_file", default=False, metavar="IN",
                      help="defaults to stdin")

    (options, args) = parser.parse_args()

    if options.out_file:
        out_file = open(options.out_file, "w")
    else:
        out_file = sys.stdout

    if options.in_file:
        in_file = open(options.in_file, "r")
    else:
        in_file = sys.stdin

    if options.selector or options.xpath_exp:
        if options.selector:
            sel = CSSSelector(options.selector)
        else:
            sel = XPath(options.xpath_exp) 

        tree = html.parse(in_file)
        for item in sel(tree):
            try:
                out_file.write(html.tostring(item).strip().encode('utf-8'))
            except TypeError:
                out_file.write(item.encode('utf-8'))

            out_file.write('\n')
    else:
        parser.print_help()

if __name__ == "__main__":
    main()