from apiclient.discovery import build
import os
import unicodecsv as csv
from googleapiclient.errors import HttpError
import time
SCOPES = ['https://www.googleapis.com/auth/analytics.readonly']
KEY_FILE_LOCATION = 'my_key_file.p12'
SERVICE_ACCOUNT_EMAIL = 'service_account_email@my-google-cloud-project.iam.gserviceaccount.com'

class ApiGA():
    
    def __init__(self, scopes=SCOPES, 
                 key_file_location=KEY_FILE_LOCATION, 
                 service_account_email=SERVICE_ACCOUNT_EMAIL, 
                 version='v4'):
        credentials = ServiceAccountCredentials.from_p12_keyfile(
                service_account_email, key_file_location, scopes=scopes)
        self.handler = build('analytics', version, credentials=credentials)
        
    
    def downloadReport(self, view_id, dim_list, metrics_list, date, page, end_date=None, filters=None):
        if not end_date:
            end_date = date
        body = {
                'reportRequests': [
        {
          'viewId': view_id,
          'dateRanges': [{'startDate': date, 'endDate': end_date}],
          'dimensions': dim_list,
          'metrics': metrics_list,
          'includeEmptyRows': True,
          'pageSize': 10000,
          'samplingLevel': 'LARGE'
        }]}
        if page:
            body['reportRequests'][0]['pageToken'] = page        
        if filters:
            body['reportRequests'][0]['filtersExpression'] = filters
        while True:
            try:
                return self.handler.reports().batchGet(body=body).execute()
            except HttpError:
                time.sleep(0.5)
    
    def getData(self, view_id, dimensions, metrics, date, filename='raw_data.csv', end_date=None, write_mode='wb', filters=None):
        dim_list = map(lambda x: {'name': 'ga:'+x}, dimensions)
        metrics_list = map(lambda x: {'expression': 'ga:'+x}, metrics)
        
        file_data = open(filename, write_mode)
        writer = csv.writer(file_data)
        
        page = None
        while True:
            response = self.downloadReport(view_id, dim_list, metrics_list, date, page, end_date=end_date, filters=filters)
            report = response['reports'][0]
            rows = report.get('data', {}).get('rows', [])
            for row in rows:
                dimensions = row['dimensions']
                metrics = row['metrics'][0]['values']
                writer.writerow(dimensions+metrics)
                
            if 'nextPageToken' in report:
                page = report['nextPageToken']
            else:
                break
        file_data.close()

from google.cloud import bigquery

client = bigquery.Client()


schema = [
    	bigquery.SchemaField('clientId', 'STRING'),
bigquery.SchemaField('sessionId', 'STRING'),
bigquery.SchemaField('source', 'STRING'),
bigquery.SchemaField('medium', 'STRING'),
bigquery.SchemaField('campaign', 'STRING'),
bigquery.SchemaField('keyword', 'STRING'),
bigquery.SchemaField('adContent', 'STRING'),
bigquery.SchemaField('userType', 'STRING'),
bigquery.SchemaField('hits', 'INTEGER'),
bigquery.SchemaField('pageviews', 'INTEGER'),
bigquery.SchemaField('totalEvents', 'INTEGER'),
bigquery.SchemaField('transactions', 'INTEGER'),
bigquery.SchemaField('screenviews', 'INTEGER')
]
table_id = ‘raw.sessions’
table = bigquery.Table(table_id, schema=schema)
table = client.create_table(table)

dataset_ref = client.dataset(dataset_id)
table_ref = dataset_ref.table(table_id)
job_config = bigquery.LoadJobConfig()
job_config.source_format = bigquery.SourceFormat.CSV
job_config.skip_leading_rows = 0
job_config.autodetect = True

with open(filename, "rb") as source_file:
    job = client.load_table_from_file(source_file, table_ref, job_config=job_config)

job.result()