Scrapy框架的应用———爬取Boss招聘网站关于爬虫工程师的名称和薪资

项目主代码

import scrapy
from boss.items import BossItem

class BossproSpider(scrapy.Spider):
    name = 'bossPro'
    # allowed_domains = ['www.baidu.com']
    url = 'https://www.zhipin.com/c101010100/?query=python%E7%88%AC%E8%99%AB&page='
    start_urls = ['https://www.zhipin.com/c101010100/?query=python%E7%88%AC%E8%99%AB&page=1']
    pageNum=1

    def parse(self, response):
        li_list=response.xpath('//div[@class="job-list"]/ul/li')
        for li in  li_list:
            job_name=li.xpath('./div/div[1]/h3/a/div[1]/text()').extract_first()
            salary=li.xpath('./div/div[1]/h3/a/span/text()').extract_first()
            item=BossItem()
            item['job_name']=job_name
            item['salary']=salary

            yield  item

        #通过循环的形式请求其他页码数据
        if self.pageNum <=3:
            self.pageNum+=1#因为第一页的数据已经请求，所有从第二页请求

            # 参数2：回调函数，作用就是对请求到的页面数据进行解析操作
            new_url=self.url+str(self.pageNum)

            # yield的使用场景：1.向管道提交item  2.手动请求发送
            yield scrapy.Request(url=new_url,callback=self.parse)

items代码：

import scrapy


class BossItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    job_name=scrapy.Field()
    salary=scrapy.Field()

pipelines代码：

class BossPipeline(object):

    fp=None
    def open_spider(self,spider):
        self.fp=open('./job.txt','w',encoding='utf-8')
    def process_item(self, item, spider):
        self.fp.write(item['job_name']+":"+item['salary']+'
')
        return item
    def close_spider(self,spider):
        self.fp.close()

setting配置代码

USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36'


ROBOTSTXT_OBEY = False


ITEM_PIPELINES = {
   'boss.pipelines.BossPipeline': 300,
}