scrapy模板爬网易新闻

# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from day12.items import WangyiItem

class WangyiSpider(CrawlSpider):
    name = 'wangyi'
    allowed_domains = ['163.com']
    start_urls = ['http://163.com/']

    rules = (
        #LinkExtractor 获取需要的url的正则表达式
        # callback 用此函数处理页面返回数据
        # fllow true  继续寻找当前页面的url进行处理
        #       False 不在当前页面寻找url处理
        Rule(LinkExtractor(allow=r'https:.*\.163\.com/.*\.html'), callback='parse_item', follow=False),
        Rule(LinkExtractor(allow=r'163\.com'), follow=True),
    )

    def parse_item(self, response):
        # i = {}
        #i['domain_id'] = response.xpath('//input[@id="sid"]/@value').extract()
        #i['name'] = response.xpath('//div[@id="name"]').extract()
        #i['description'] = response.xpath('//div[@id="description"]').extract()
        # return i
        title = response.xpath('//h1/text()').extract_first()
        print(title)
        content = response.xpath('//div[@class="post_text"]//p//text()').extract()
        content = ''.join(content)
        print(content)

        item = WangyiItem()
        item['title'] = title
        content['content'] = content
        return item