crawlspider爬虫：定义url规则

spider爬虫，适合meta传参的爬虫（列表页，详情页都有数据要爬取的时候）

 crawlspider爬虫，适合不用meta传参的爬虫

scrapy genspider -t crawl it it.com

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

class DongguanSpider(CrawlSpider):
    name = 'dongguan'
    # 修改允许的域
    allowed_domains = ['sun0769.com']
    # 修改起始的url
    start_urls = ['http://wz.sun0769.com/index.php/question/questionType?type=4']

    rules = (
        # 构建列表url的提取规则
        Rule(LinkExtractor(allow=r'questionType'), follow=True),
        # 构建详情页面url提取规则
        # 'html/question/201711/352271.shtml'
        Rule(LinkExtractor(allow=r'html/question/\d+/\d+.shtml'), callback='parse_item'),
    )

    def parse_item(self, response):
        # print (response.url,'--------')

        # 构建item实例
        item = SunItem()

        # 抽取数据，将数据存放到item中
        item['number'] = response.xpath('/html/body/div[6]/div/div[1]/div[1]/strong/text()').extract()[0].split(':')[-1].strip()
        item['title'] = response.xpath('/html/body/div[6]/div/div[1]/div[1]/strong/text()').extract()[0].split('：')[-1].split(' ')[0]
        item['link'] = response.url
        data = ''.join(response.xpath('//div[@class="c1 text14_2"]/text()|//div[@class="contentext"]/text()').extract())
        item['content'] = data.replace('\xa0','')
        # print(item)
        # 返回数据
        yield item

　　

 

链接提取器的使用

scrapy shell http://hr.tencent.com/position.php

>>> from scrapy.linkextractors import LinkExtractor
>>> le = LinkExtractor(allow=('position_detail.php\?id=\d+&keywords=&tid=0&lid=0'))

或者直接 le = LinkExtractor(allow=('position_detail.php'))   也可以

>>> links=le.extract_links(response)
>>> for link in links:
... print(link)
...

>>> for link in links:
... print(link.url)
...

 

 

转载于:https://www.cnblogs.com/andy9468/p/8299894.html