招聘网站职位信息爬取

需求

1.用户输入想要爬取的职位，起始条目，结束条目

2.将爬取结果保存为csv文件

实现

    from  urllib import request,parse  
    import csv  
    import json  

    class zhilianSpider(object):  
        def __init__(self,job,start,end):  
            self.job=parse.quote(job)#链接中的字符串需要转换，否则报错  
            self.start=int(start)  
            self.end=int(end)  
            self.data=[]  
        def run(self):  
            #创建请求、发送请求，解析  
            url = 'https://fe-api.zhaopin.com/c/i/sou?start=%d&pageSize=%d&cityId=538&workExperience=-1&education=-1&companyType=-1&employmentType=-1&jobWelfareTag=-1&kw=%s&kt=3&_v=0.48405690&x-zp-page-request-id=22e67c28152f47a1a424b6f5bf58e535-1558511284814-104138'%(self.start,self.start+self.end,self.job)  
            req = self.make_req(url)  
            res = request.urlopen(req)  
            print('开始爬取……')  
            self.parse(res)  
            #写入数据到csv中  
            headers = ['工作名', '收入', '公司名', '规模', '最近更新时间','工作经验','职位链接']  
            with open('job.csv','w',encoding='utf-8') as f:  
                f_csv = csv.writer(f)  
                f_csv.writerow(headers)  
                f_csv.writerows(self.data)  
            print('爬取结束')  

        def make_req(self,url):  
            headers={  
                'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3676.400 QQBrowser/10.4.3505.400'  
            }  
            req=request.Request(headers=headers,url=url)  
            return req  
        def parse(self,res):  
            res=json.loads(res.read().decode())  
            results=res['data']['results']  
            for item in results:  
                lt=[]  
                lt.append(item['jobName'])  
                lt.append(item['salary'])  
                lt.append(item['company']['name'])  
                lt.append(item['company']['size']['name'])  
                lt.append(item['updateDate'])  
                lt.append(item['workingExp']['name'])  
                lt.append(item['positionURL'])  
                lt=tuple(lt)  
                self.data.append(lt)  
    def main():  
        job=input('请输入要爬取的职位:')  
        start=input('请输入起始条:')  
        end = input('请输入末尾条:')  
        zhilian=zhilianSpider(job,start,end)  
        zhilian.run()  

    if __name__=='__main__':  
        main()

结果：

    请输入要爬取的职位:python开发  
    请输入起始条:0  
    请输入末尾条:180  
    开始爬取……  
    爬取结束  

    Process finished with exit code 0

csv文件内容：