kwnews_spider.py

from scrapy.spider import BaseSpider
from lxml.html import parse as lxmlparse

class KwnewsSpider(BaseSpider):
    name = 'kwnews'
    allowed_domains = ['www.independent.co.uk']
    start_urls = ['http://www.independent.co.uk/']
    def parse(self, response):
        doc = lxmlparse(response.body)
        print doc