1、Create a PRoject

win+R-->cmd-->cd desktop-->scrapy startproject tutorial #this step will create a folder in the desktop.

2、Define an item

open the items.py file,the code:

# -*- coding: utf-8 -*-# Define here the models for your scraped items## See documentation in:# http://doc.scrapy.org/en/latest/topics/items.htmlimport scrapyclass DmozItem(scrapy.Item):    # define the fields for your item here like:    # name = scrapy.Field()    title = scrapy.Field()    link = scrapy.Field()    desc = scrapy.Field()3、Start a Scrapy
create a new file named dmoz_spider.py then start coding:
import scrapyclass 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(slef,response):        filename = response.url.split("/")[-2]        with open(filename,'wb')
import scrapyclass 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(slef,response):        '''filename = response.url.split("/")[-2]        with open(filename,'wb') as f:            f.write(response.body)'''        sel = scrapy.selector.Selector(response)        sites = sel.xpath('//div[@class="title-and-desc"]')        for site in sites:            title = site.xpath('a/div[@class="site-title"]/text()').extract()            link = site.xpath('a/@href').extract()            desc = site.xpath('div[@class="site-descr "]/text()').extract()            print(title,link,desc)                import scrapyclass 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(slef,response):        '''filename = response.url.split("/")[-2]        with open(filename,'wb') as f:            f.write(response.body)'''        sel = scrapy.selector.Selector(response)        sites = sel.xpath('//div[@class="title-and-desc"]')        for site in sites:            title = site.xpath('a/div[@class="site-title"]/text()').extract()            link = site.xpath('a/@href').extract()            desc = site.xpath('div[@class="site-descr "]/text()').extract()            print(title,link,desc)f.write(response.body)
4、cmd：
-->cd desktop
-->cd tutorial
-->scrapy crawl dmoz
when the running ends,you will find two new files named Books and Resources are created  in desktop/tutorial folder
5、cmd：（not necessary）
-->Desktop/tutorial>scrapy shell "http://www.dmoz.org/Computers/Programming/Languages/Python/Books"    #this step get the response(must )
-->respose.body
>>> response.headers{'Cteonnt-Length': ['46147'], 'Content-Language': ['en'], 'Set-Cookie': ['JsessionID=CDE6228CA4B21EA2DE64C22A5578133C; Path=/; HttpOnly'], 'Server': ['Apache'],'Date': ['Sun, 19 Feb 2017 12:50:19 GMT'], 'Content-Type': ['text/html;charset=UTF-8']}>>> response.xpath('//title')[<Selector xpath='//title' data=u'<title>DMOZ - Computers: Programming: La'>]>>> response.xpath('//title').extract()[u'<title>DMOZ - Computers: Programming: Languages: Python: Books</title>']>>>
6、dmoz_spider.py code:
import scrapyfrom tutorial.items import DmozItemclass 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(slef,response):        '''filename = response.url.split("/")[-2]        with open(filename,'wb') as f:            f.write(response.body)'''        sel = scrapy.selector.Selector(response)        sites = sel.xpath('//div[@class="title-and-desc"]')        items = []        for site in sites:            item = DmozItem()                        item['title'] = site.xpath('a/div[@class="site-title"]/text()').extract()            item['link'] = site.xpath('a/@href').extract()            item['desc'] = site.xpath('div[@class="site-descr "]/text()').extract()            #print(title,link,desc)            items.append(item)        return items7、cmd
-->cd tutorial
-->scrapy crawl dmoz -o items.json -t json
"items.json" file will be created