python阿里巴巴招聘网站爬虫

写了个阿里巴巴招聘网站爬虫，这次是存在csv文件里，小伙伴们可以对比一下～

            
              import requests,json,csv

#写入csv文件中
list=[]
csv_file=open('阿里巴巴招聘.csv','w+',newline='',encoding='utf=8')
writer=csv.writer(csv_file)
list_head=['职位名称','部门','是否招聘','学历','大类','小类','工作地','工作经历','要求','职责']
writer.writerow(list_head)

#爬虫
keyword=str(input('请输入职位关键字：'))

url='https://job.alibaba.com/zhaopin/socialPositionList/doList.json'
headers={
    'Referer': 'https://job.alibaba.com/zhaopin/positionList.htm?spm=a2obv.11875463.0.0.2ac23a5dSb7Wbw',

}

for p in range(10):
    p=p+1
    data={
        'MIME 类型': 'application/x-www-form-urlencoded; charset=UTF-8',
        'pageSize': '10',
        't': '0.9218667109769481',
        'keyWord': keyword,
        'location'
        'second'
        'first'
        'pageIndex': str(p)
    }
    cookies={
        'Cookie': ' isg=BM7OlPeDH1cyaKt12PikCz_-HaKQT5JJOm4ATvgXOlGNW2y1at3VWbNdkwc32Iph; l=cBLBoTMuqFP2KvuXBOCanurza77OSId4YuPzaNbMi_5BG6L1xV_Okk5T4Fp6csWFGhLk4nXUfzeT6FibJPDjtQPl2eGJXZ5..; CNZZDATA1000004769=1840857478-1567157075-%7C1567549123; tmp0=6vzoNBZKbkA%2BBLyFAxc%2F%2B5%2FiZdeVqJ%2BQe1wqEFgcolw%2Bv%2BNF%2BSOMmjyEAbaxmDieCW6DN%2FW1NgF3ABlBHs%2BQVVV2hLJ2KNwMGtDuyycdGSJ6QuN6svOgAsp7j9AZ0WOupUzUlbSrvipNMHgwXXNByNszrL0xUXa2GZogaVwPGKi7SGNCFAAV69vqvj6X2DlVaPMaTpJ3iqH20Tnd%2FLw7QVdbcEn3PhXzGaBl3yQmiW9LYRA8MDOBcbOWVZJ1lrwS8QCt4%2FQhkY70vFtrIvKAQhtb4iXr6OkIZI793Ao1syY%3D; _hvn_login=0; csg=87ae08c0; _tb_token_=eeed45e87e5e7; cookie2=14659eb4996e47c896f304074d300557; JSESSIONID=JFYJXFOV-FDC82NZA4NVS98Y8CX7N3-KRA0E30K-9MTB2; t=81b209fbe498754d386d92ccdaa8ff67; UM_distinctid=16ce1eb6c4342c-05f3012e7a8dcb8-3f616f4a-13c680-16ce1eb6c443e1; cna=ft7vFfKyZQACAbeW36y9ZReA'
    }

    res_post=requests.post(url,headers=headers,data=data,cookies=cookies)

    res_text=res_post.text
    res_dict=json.loads(res_text)

    positions=res_dict['returnValue']['datas']

    for position in positions:
        requirement=position['requirement']
        departmentName=position['departmentName'][5:]
        workExperience=position['workExperience']
        description=position['description']
        name=position['name']
        degree=position['degree']
        firstCategory=position['firstCategory']
        secondCategory=position['secondCategory']
        workLocation=position['workLocation']
        status=position['status']
        list_content=[name,departmentName,status,degree,firstCategory,secondCategory,workLocation,workExperience,requirement,description]
        list.append(list_content)
        writer.writerow(list_content)

csv_file.close()
print('爬取成功！')