Scrapy制作爬虫

import scrapy
from tutorial.items import DmozItem
class DmozSpider(scrapy.Spider):
    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):
        sel = Selector(response)
        sites = sel.xpath('//ul[@class="directory-url"]/li')
        for sel in sites:
            item = DmozItem() # 实例化一个 DmozItem 类
            item['title'] = sel.xpath('a/text()').extract()
            item['link'] = sel.xpath('a/@href').extract()
            item['desc'] = sel.xpath('text()').extract()
            yield item

#! -*- encoding:utf-8 -*-
        import base64            
        import sys
        import random

        PY3 = sys.version_info[0] >= 3

        def base64ify(bytes_or_str):
            if PY3 and isinstance(bytes_or_str, str):
                input_bytes = bytes_or_str.encode('utf8')
            else:
                input_bytes = bytes_or_str

            output_bytes = base64.urlsafe_b64encode(input_bytes)
            if PY3:
                return output_bytes.decode('ascii')
            else:
                return output_bytes

        class ProxyMiddleware(object):                
            def process_request(self, request, spider):
                # 代理服务器(产品官网 www.16yun.cn)
                proxyHost = "t.16yun.cn"
                proxyPort = "31111"

                # 代理验证信息
                proxyUser = "username"
                proxyPass = "password"

scrapy crawl itcast -o teachers.json

scrapy crawl itcast -o teachers.jsonl

scrapy crawl itcast -o teachers.csv

scrapy crawl itcast -o teachers.xml