crawlspider

scrapy genspider --t crawl baidu baidu.com

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


class CfSpider(CrawlSpider):
    name = ‘cf‘
    allowed_domains = [‘circ.gov.cn‘]
    start_urls = [‘http://circ.gov.cn/‘]
    # 提取规则 follow=True 继续提取（提取下一页地址 需要True）
    rules = (
        Rule(LinkExtractor(allow=r‘Items/‘), callback=‘parse_item‘, follow=True),
    )

    def parse_item(self, response):
        item = {}
        #item[‘domain_id‘] = response.xpath(‘//input[@id="sid"]/@value‘).get()
        #item[‘name‘] = response.xpath(‘//div[@id="name"]‘).get()
        #item[‘description‘] = response.xpath(‘//div[@id="description"]‘).get()
        return item