scrapy01-scrapy的项目的创建和启动

pip install pipywin32
pip install wheel #不用也可以
pip install Twisted
pip install scrapy

scrapy startproject [项目名]

scrapy genspider [爬虫名] [域名]

import scrapy
# from scrapy.selector.unified import  SelectorList
from scrapy1_test.items import Scrapy1TestItem

class DuanziSpider(scrapy.Spider):
    name = ‘duanzi‘
    allowed_domains = [‘ishuo.cn‘]
    start_urls = [‘http://ishuo.cn/‘]

    def parse(self, response):
        contents = []
        content_lis = response.xpath("//div[@id=‘list‘]/ul/li")
        for li in content_lis:
            content = li.xpath(‘./div[1]/text()‘).get()#与etree的text()方法不同，这里拿到的是一个对象，需要get()才可以取出里面的内容
            info = li.xpath(‘./div[2]/a/text()‘).get()
            item = Scrapy1TestItem(content=content,info=info)
            yield item #这种方式是单个item返回，也可以用一个列表集中返回
            # contents.append(item)
        # return contents
        yield scrapy.Request