# -*- coding:utf-8 -*-
'''
Created on 2015年10月22日
(1.1) 例子来源: http://scrapy-chs.readthedocs.org/zh_CN/latest/intro/tutorial.html
'''
import scrapy
# 去掉 s 在PyDev中不报错, 但是无法运行.如果加上 s 虽然报错,但是程序能正常运行.
# 可以在 PyDev 中使用 " # @UndefinedVariable "来压制错误提示.
class DmozSpider(scrapy.spiders.Spider): # @UndefinedVariable
name = "dmoz"
allowed_domains = ["dmoz.org"]
start_urls = [
"http://www.dmoz.org/Computers/Programming/Languages/Python/Books/",
"http://www.dmoz.org/Computers/Programming/Languages/Python/Resources/"
]
def parse(self, response):
filename = response.url.split("/")[-2]
with open(filename, 'wb') as f:
f.write(response.body)