requests 获取百度推广信息

2019年的第一篇博客，恩，好久没写过博客了，恩，忘了，哈哈，实在是太懒了

今天写一个爬取百度推广数据的爬虫，当然我写的肯定不是那么的完美，但是能用，大哭

注意：有的时候，get或post方法获取数据是会报ssl等错误，网站要验证啥的，没搞懂，网上搜索，都是设置 verify=False，我也懒得去详细分析，你们要是有兴趣可以去了解一下，然后这么设置了，在GET或者post是会有warning提示，编写代码：

# 禁用ssl发出的警告
requests.packages.urllib3.disable_warnings()

下面代码：

def main():
　　#开启一个session对话
   main_session = requests.session()
   return main_session

def get_cost_info(main_session, endtime, flag1, flag2):
　　#获取省或市在日期或者月份下的消费信息
   if flag1 == 'province':
      splitDimension = "provinceName"
   else:
      splitDimension = "provinceCityName"
   if flag2 == 'month':
      unitOfTime = 3
   else:
      unitOfTime = 5
   headers = {
      'Accept':'application/json',
      'Accept-Encoding':'gzip, deflate',
      'Accept-Language':'zh-CN,zh;q=0.8',
      'Connection':'keep-alive',
      'Content-Length':'763',
      'Content-Type':'application/x-www-form-urlencoded',
      'Cookie':setting.Cookie,
      'DNT':'1',
      'Host':'fengchao.baidu.com',
      'Origin':'https://fengchao.baidu.com',
      'Referer':'https://fengchao.baidu.com/fc/report/dashboard/user/%s/account'%setting.userid,
      'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.106 BIDUBrowser/8.7 Safari/537.36',
      'X-DevTools-Emulate-Network-Conditions-Client-Id':'87F3C66D-3166-46F6-8B46-141057354EBC'
   }
   params = {
      "userId":setting.userid,
      "ids":[setting.userid],
      "idType":2,
      "splitDimension":splitDimension,
      "limit":[0,1000],
      "sortRules":[],
      "levelOfDetails":211,
      "startDate":"2019-01-01",
      "endDate":endtime,
      "predicateConditions":[],
      "unitOfTime":unitOfTime,
      "columns":["userId","date","accountName","impression","click","cost","cpc","ctr","conversion","phoneConversion","bridgeConversion"]
   }
   formdata = {
      'reqid': setting.reqid,
      'eventId': setting.eventId,
      'userid': setting.userid,
      'token': setting.token,
      'path': 'mars/GET/AccountReportDataService/getAccountDataCenterReportData',
      'params': json.dumps(params)
   }
　　#url是去F12---network获取的
   url_1 = 'https://fengchao.baidu.com/hairuo/request.ajax?path=mars/GET/AccountReportDataService/getAccountDataCenterReportData&reqid=%s' % formdata['reqid']
   cont_1 = main_session.post(url_1, headers=headers, data=formdata, verify=False)
   datas = cont_1.json()
   cont_list_1 = datas['data']['ACCOUNT']['rows']
   for i in cont_list_1:
      cont_list_2 = i['subRows']
      cont_list = []
      for j in cont_list_2:
         if flag2 == 'month':
            time_1 = j['date'][0:7]
            time_list1 = time_1.split('-')
            date = '%s年%s月份' % (time_list1[0], str(int(time_list1[1])))
         else:
            date = j['date']
         zhanghu = j['accountName']
         province, city = '', ''
         if flag1 == 'province':
            province = j['provinceName']
         else:
            city_list = j['provinceCityName'].split('-')
            province, city = city_list[0], city_list[1]
         zhanxian = str(j['impression'])
         dianji = str(j['click'])
         xiaofei = str(j['cost'])
         pinjunjiage = str('%.2f' % (j['cpc']))
         dianjilv = str('{:.2%}'.format(j['ctr']))
         wangyezhuanhua = str(j['conversion'])
         dianhuazhuanhua = str(j['phoneConversion'])
         shangqiaozhuanhua = str(j['bridgeConversion'])
cont_list.append([date, zhanghu, province, zhanxian, dianji, xiaofei, pinjunjiage, dianjilv, wangyezhuanhua, dianhuazhuanhua, shangqiaozhuanhua])

经过测试，cookie一般能保持7天不过期，七天之后就要重新登录浏览器F12获取