scrapy 中crawlspider 爬虫

 

爬取目标网站：

http://www.chinanews.com/rss/rss_2.html

获取url后进入另一个页面进行数据提取

检查网页：

 

爬虫该页数据的逻辑：

Crawlspider爬虫类：

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

class NwSpider(CrawlSpider):
    name = 'nw'
    # allowed_domains = ['www.new.com']
    start_urls = ['http://www.chinanews.com/rss/rss_2.html']

    rules = (
　　　　　
        Rule(LinkExtractor(allow='http://www.chinanews.com/rss/.*?\.xml'), callback='parse_item'),
    )

    def parse_item(self, response):
        selector = Selector(response)
        items =response.xpath('//item').extract()
        for node in items:
            # print(type(node))
            #
            item = {}
            item['title'] = re.findall(r'<title>(.*?)</title>',node,re.S)[0]
            item['link'] = re.findall(r'<link>(.*?)</link>',node,re.S)[0]
            item['desc'] = re.findall(r'<description>(.*?)</description>',node,re.S)[0]
            item['pub_date'] =re.findall(r'<pubDate>(.*?)</pubDate>',node,re.S)[0]
            print(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()
            # yield item

 

转载于:https://www.cnblogs.com/knighterrant/p/10743532.html