Analytics Reporting API V4

Question

here is the code,

import pandas as pd
from apiclient.discovery import build
from oauth2client.service_account import ServiceAccountCredentials

SCOPES = ['https://www.googleapis.com/auth/analytics.readonly']
KEY_FILE_LOCATION = './c-******-*******.json'
VIEW_ID = '*********'

def initialize_analyticsreporting():
  credentials = ServiceAccountCredentials.from_json_keyfile_name(
      KEY_FILE_LOCATION, SCOPES)
  analytics = build('analyticsreporting', 'v4', credentials=credentials)
  return analytics

#Get one report page
def get_report(analytics, pageTokenVar):
  return analytics.reports().batchGet(
      body={
        'reportRequests': [
        {
          'viewId': VIEW_ID,
          'dateRanges': [{'startDate': '3daysAgo', 'endDate': 'yesterday'}],
          'metrics': [{'expression': 'ga:uniqueevents'}],
          'dimensions': [{'name': 'ga:eventcategory' and 'ga:eventlabel'}],
          'pageSize': 10000,
          'pageToken': pageTokenVar,
          'samplingLevel': 'LARGE'
        }]  
      }
  ).execute()
    
def handle_report(analytics,pagetoken,rows):  
    response = get_report(analytics, pagetoken)

    #Header, Dimentions Headers, Metric Headers 
    columnHeader = response.get("reports")[0].get('columnHeader', {})
    dimensionHeaders = columnHeader.get('dimensions', [])
    metricHeaders = columnHeader.get('metricHeader', {}).get('metricHeaderEntries', [])

    #Pagination
    pagetoken = response.get("reports")[0].get('nextPageToken', None)
    
    #Rows
    rowsNew = response.get("reports")[0].get('data', {}).get('rows', [])
    rows = rows + rowsNew
    print("len(rows): " + str(len(rows)))

    #Recursivly query next page
    if pagetoken != None:
        return handle_report(analytics,pagetoken,rows)
    else:
        #nicer results
        nicerows=[]
        for row in rows:
            dic={}
            dimensions = row.get('dimensions', [])
            dateRangeValues = row.get('metrics', [])

            for header, dimension in zip(dimensionHeaders, dimensions):
                dic[header] = dimension

            for i, values in enumerate(dateRangeValues):
                for metric, value in zip(metricHeaders, values.get('values')):
                    if ',' in value or ',' in value:
                        dic[metric.get('name')] = float(value)
                    else:
                        dic[metric.get('name')] = int(value)
            nicerows.append(dic)
        return nicerows

#Start
def main():    
    analytics = initialize_analyticsreporting()
    
    global dfanalytics
    dfanalytics = []

    rows = []
    rows = handle_report(analytics,'0',rows)

    dfanalytics = pd.DataFrame(list(rows))

if __name__ == '__main__':
  main()

my goal is to add filters to the dimension, I want to exclude "(not set)" results and include only "Search" type events.

I add the lines in #Get one report page,

I looked at the google documentation, try several different lines and option, I can't really understand why it doesn't work.

If I remove the lines, the code works perfectly.

As soon as I add these lines of code:

'dimensionFilterClauses': [
                            {"filters": [{"dimensionName": "ga:eventlabel",
                                          "operator": "EQUAL",
                                          "expressions": [Recherche]}]
                            }
                                        ],

I get an error on the ' of 'pageViews'.

Do you have an idea?

Answer 1

Try simplified syntax for filters, something like this:

"filtersExpression":"ga:eventLabel!=(not set)"