Python3 获取百度统计数据

利用Python3 获取百度统计数据，如果有数据异常则发邮件

如何获取站点id

查看报告的链接

Python

# -*- coding: utf-8 -*- """ @Time: 2018/6/11 @Author: songhao @微信公众号: zeropython @File: crawl_baidu_tongji.py """ import csv import json import time import datetime import urllib.parse import urllib.request from pprint import pprint from pandas import DataFrame from pprint import pprint from openpyxl import Workbook base_url = "https://api.baidu.com/json/tongji/v1/ReportService/getData" import datetime # 当前系统时间 nowTime=datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S') class Baidu(object): def __init__(self, siteId, username, password, token): self.siteId = siteId self.username = username self.password = password self.token = token def getresult(self, start_date, end_date, method, metrics, **kw): base_url = "https://api.baidu.com/json/tongji/v1/ReportService/getData" body = {"header": {"account_type": 1, "password": self.password, "token": self.token, "username": self.username}, "body": {"siteId": self.siteId, "method": method, "start_date": start_date, "end_date": end_date, "metrics": metrics}} for key in kw: body['body'][key] = kw[key] data = bytes(json.dumps(body), 'utf8') req = urllib.request.Request(base_url, data) response = urllib.request.urlopen(req) the_page = response.read() return the_page.decode("utf-8") # if __name__ == '__main__': # 初始花 csv def get_new_data(): wf = open('uvdata.csv','w',encoding='utf-8') writer = csv.writer(wf) writer.writerow(['时间', '栏目', '变化','uv1','uv2']) # ws.append(['时间', '栏目', '变化','uv1','uv2']) # 日期开始 today = datetime.date.today() yesterday = today - datetime.timedelta(days=1) fifteenago = today - datetime.timedelta(days=2) end, start = str(yesterday).replace("-", ""), str(fifteenago).replace("-", "") word_idc = [] weblist = {'新闻':648382,} for k,v in weblist.items(): # print(k,v) bd = Baidu(v, "用户名", "密码", "token") result = bd.getresult(start, end, "overview/getTimeTrendRpt", "visitor_count",max_results=100) data = json.loads(result).get('body').get('data')[0].get('result').get('items') data_time = [start,end] data_start_uv = data[1][0][0] data_end_uv = data[1][1][0] get_range_value = abs((data_start_uv-data_end_uv)/data_start_uv) if get_range_value >= 0.05: pre_data = '%.2f%%' % (get_range_value * 100) new_data =[data_time,k,pre_data,data_start_uv,data_end_uv] word_idc.append(new_data) return word_idc if __name__ == '__main__': get_new_data()

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83

# -*- coding: utf-8 -*- """ @Time: 2018/6/11 @Author: songhao @微信公众号: zeropython @File: crawl_baidu_tongji.py """ import csv import json import time import datetime import urllib . parse import urllib . request from pprint import pprint from pandas import DataFrame from pprint import pprint from openpyxl import Workbook   base_url = "https://api.baidu.com/json/tongji/v1/ReportService/getData" import datetime   # 当前系统时间 nowTime = datetime . datetime . now ( ) . strftime ( '%Y-%m-%d %H:%M:%S' )   class Baidu ( object ) :      def __init__ ( self , siteId , username , password , token ) :          self . siteId = siteId          self . username = username          self . password = password          self . token = token        def getresult ( self , start_date , end_date , method , metrics , * * kw ) :          base_url = "https://api.baidu.com/json/tongji/v1/ReportService/getData"          body = { "header" : { "account_type" : 1 , "password" : self . password , "token" : self . token ,                            "username" : self . username } ,                  "body" : { "siteId" : self . siteId , "method" : method , "start_date" : start_date ,                          "end_date" : end_date , "metrics" : metrics } }          for key in kw :              body [ 'body' ] [ key ] = kw [ key ]          data = bytes ( json . dumps ( body ) , 'utf8' )          req = urllib . request . Request ( base_url , data )          response = urllib . request . urlopen ( req )          the_page = response . read ( )          return the_page . decode ( "utf-8" )     # if __name__ == '__main__':      # 初始花 csv def get_new_data ( ) :      wf = open ( 'uvdata.csv' , 'w' , encoding = 'utf-8' )      writer = csv . writer ( wf )      writer . writerow ( [ '时间' , '栏目' , '变化' , 'uv1' , 'uv2' ] )        # ws.append(['时间', '栏目', '变化','uv1','uv2'])        # 日期开始      today = datetime . date . today ( )      yesterday = today - datetime . timedelta ( days = 1 )      fifteenago = today - datetime . timedelta ( days = 2 )      end , start = str ( yesterday ) . replace ( "-" , "" ) , str ( fifteenago ) . replace ( "-" , "" )      word_idc = [ ]      weblist = { '新闻' : 648382 , }      for k , v in weblist . items ( ) :          # print(k,v)          bd = Baidu ( v , "用户名" , "密码" , "token" )          result = bd . getresult ( start , end , "overview/getTimeTrendRpt" ,                                "visitor_count" , max_results = 100 )          data = json . loads ( result ) . get ( 'body' ) . get ( 'data' ) [ 0 ] . get ( 'result' ) . get ( 'items' )            data_time = [ start , end ]          data_start_uv = data [ 1 ] [ 0 ] [ 0 ]          data_end_uv = data [ 1 ] [ 1 ] [ 0 ]          get_range_value = abs ( ( data_start_uv - data_end_uv ) / data_start_uv )          if get_range_value >= 0.05 :              pre_data = '%.2f%%' % ( get_range_value * 100 )              new_data = [ data_time , k , pre_data , data_start_uv , data_end_uv ]              word_idc . append ( new_data )      return word_idc   if __name__ == '__main__' :      get_new_data ( )

---

这段代码是 获取uv 数据，如果环比大于百分之5则发邮件通知站长，流量出现异常

如何发送邮件请移步
https://www.168seo.cn/python/24359.html

• zeropython 微信公众号 5868037 QQ号 5868037@qq.com QQ邮箱