import requests  # 数据请求模块 第三方模块 pip install requests
import pprint  # 格式化输出模块
import csv  # csv保存数据
import time

url = 'https://www.lagou.com/jobs/positionAjax.json?needAddtionalResult=false'
# headers 请求头 用来伪装python代码, 防止被识别出是爬虫程序, 然后被反爬
# user-agent: 浏览器的基本标识
headers = {
    'cookie': 'privacyPolicyPopup=false; user_trace_token=20211016201224-ba4d90f0-3db5-4647-a86e-411ee3d5bfef; __lg_stoken__=08639898fbdd53a7ebf88fa16e895b59a51e47738f45faef6a32b9a88d6537bf9459b2c6d956a636a99ff599c6a260f04514df42cb77f83065d55f48a2549e60381e8da811b8; JSESSIONID=ABAAAECAAEBABIIE72FFC38A79322951663B5C7AF10CD12; WEBTJ-ID=20211016201225-17c89047f4293-0d7a7cd583dc83-b7a1438-2073600-17c89047f43a90; sajssdk_2015_cross_new_user=1; sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%2217c8904800d57b-04f17ed5193984-b7a1438-2073600-17c8904800e765%22%2C%22%24device_id%22%3A%2217c8904800d57b-04f17ed5193984-b7a1438-2073600-17c8904800e765%22%7D; PRE_UTM=; PRE_HOST=; PRE_LAND=https%3A%2F%2Fwww.lagou.com%2Fjobs%2Flist%5Fpython%3FlabelWords%3D%26fromSearch%3Dtrue%26suginput%3D; LGSID=20211016201225-7b8aa578-74ab-4b09-885c-ebbe57a6029a; PRE_SITE=; LGUID=20211016201225-fda15dbb-7823-4a2d-9d80-258caf018f02; _ga=GA1.2.903785807.1634386346; _gat=1; Hm_lvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1634386346; _gid=GA1.2.701447082.1634386346; X_HTTP_TOKEN=ba154973a88f2f64153683436141effc1d544fa2ed; Hm_lpvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1634386352; LGRID=20211016201232-8913a057-d37d-41c3-b094-a04cf36515a7; SEARCH_ID=ff32d1294b464305b4e0907f659ef2a7',
    'referer': 'https://www.lagou.com/jobs/list_python?labelWords=&fromSearch=true&suginput=',
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.81 Safari/537.36',
}
data = {
    'first': 'false',
    'pn': page,
    'kd': 'python',
    'sid': 'bf8ed05047294473875b2c8373df0357'
}
# response 自定义变量 可以自己定义 
response = requests.post(url=url, data=data, headers=headers)

result = response.json()['content']['positionResult']['result']
# 循环遍历  从 result 列表里面 把元素一个一个提取出来
for index in result:
    # pprint.pprint(index)
    # href = index['positionId']
    href = f'https://www.lagou.com/jobs/{index["positionId"]}.html'
    dit = {
        '标题': index['positionName'],
        '地区': index['city'],
        '公司名字': index['companyFullName'],
        '薪资': index['salary'],
        '学历': index['education'],
        '经验': index['workYear'],
        '公司标签': ','.join(index['companyLabelList']),
        '详情页': href,
    }
    # ''.join() 把列表转成字符串 '免费班车',
    csv_writer.writerow(dit)
    print(dit)

for page in range(1, 31):
    print(f'------------------------正在爬取第{page}页-------------------------')
    time.sleep(1)

f = open('招聘数据.csv', mode='a', encoding='utf-8', newline='')
csv_writer = csv.DictWriter(f, fieldnames=[
    '标题',
    '地区',
    '公司名字',
    '薪资',
    '学历',
    '经验',
    '公司标签',
    '详情页',
])

csv_writer.writeheader() # 写入表头