Я новичок в Google Analytics API.
Я пытаюсь загрузить данные в течение 3 месяцев, поэтому мне нужно несколько раз вызывать API и добавлять данные каждый раз.
Вот мой код:
def initialize_analyticsreporting():
'''Initializes an Analytics Reporting API V4 service object.
Returns:
An authorized Analytics Reporting API V4 service object.
'''
credentials = ServiceAccountCredentials.from_json_keyfile_name(
KEY_FILE_LOCATION, SCOPES)
# Build the service object.
analytics = build('analyticsreporting', 'v4', credentials=credentials)
return analytics
list = []
def get_report(analytics, pageTokenVariable):
return analytics.reports().batchGet(
body={
'reportRequests': [
{
'viewId': VIEW_ID,
'pageSize': 100000,
'dateRanges': [{'startDate': '1daysAgo', 'endDate': 'yesterday'}],
'metrics': [{'expression': 'ga:adClicks'}, {'expression': 'ga:impressions'}, {'expression': 'ga:adCost'}, {'expression': 'ga:CTR'}, {'expression': 'ga:CPC'}, {'expression': 'ga:costPerTransaction'}, {'expression': 'ga:transactions'}, {'expression': 'ga:transactionsPerSession'}, {'expression': 'ga:pageviews'}, {'expression': 'ga:timeOnPage'}],
"pageToken": pageTokenVariable,
'dimensions': [{'name': 'ga:adMatchedQuery'}, {'name': 'ga:campaign'}, {'name': 'ga:adGroup'}, {'name': 'ga:adwordsCustomerID'}, {'name': 'ga:date'}],
'orderBys': [{'fieldName': 'ga:impressions', 'sortOrder': 'DESCENDING'}],
'dimensionFilterClauses': [{
'filters': [{
'dimension_name': 'ga:adwordsCustomerID',
'operator': 'EXACT',
'expressions': 'abc',
'not': 'True'
}]
}],
'dimensionFilterClauses': [{
'filters': [{
'dimension_name': 'ga:adMatchedQuery',
'operator': 'EXACT',
'expressions': '(not set)',
'not': 'True'
}]
}]
}]
}
).execute()
analytics = initialize_analyticsreporting()
response = get_report(analytics, "0")
for report in response.get('reports', []):
pagetoken = report.get('nextPageToken', None)
print(pagetoken)
columnHeader = report.get('columnHeader', {})
dimensionHeaders = columnHeader.get('dimensions', [])
metricHeaders = columnHeader.get(
'metricHeader', {}).get('metricHeaderEntries', [])
rows = report.get('data', {}).get('rows', [])
for row in rows:
# create dict for each row
dict = {}
dimensions = row.get('dimensions', [])
dateRangeValues = row.get('metrics', [])
# fill dict with dimension header (key) and dimension value (value)
for header, dimension in zip(dimensionHeaders, dimensions):
dict[header] = dimension
# fill dict with metric header (key) and metric value (value)
for i, values in enumerate(dateRangeValues):
for metric, value in zip(metricHeaders, values.get('values')):
# set int as int, float a float
if ',' in value or ',' in value:
dict[metric.get('name')] = float(value)
else:
dict[metric.get('name')] = float(value)
list.append(dict)
# Append that data to a list as a dictionary
while pagetoken: # This says while there is info in the nextPageToken get the data, process it and add to the list
response = get_report(analytics, pagetoken)
pagetoken = response['reports'][0]['nextPageToken']
print(pagetoken)
for row in rows:
# create dict for each row
dict = {}
dimensions = row.get('dimensions', [])
dateRangeValues = row.get('metrics', [])
# fill dict with dimension header (key) and dimension value (value)
for header, dimension in zip(dimensionHeaders, dimensions):
dict[header] = dimension
# fill dict with metric header (key) and metric value (value)
for i, values in enumerate(dateRangeValues):
for metric, value in zip(metricHeaders, values.get('values')):
# set int as int, float a float
if ',' in value or ',' in value:
dict[metric.get('name')] = float(value)
else:
dict[metric.get('name')] = float(value)
list.append(dict)
df = pd.DataFrame
df.to_csv('Second Dataset.csv', encoding="utf-8", index=False)
В терминале я вижу, что pagetoken
увеличивается на 100,000
каждый раз, как и ожидалось, но результаты, которые я получаю от API, совпадают. Таким образом, в итоге я получаю те же 100,000
строки, умноженные на время, которое он выполнял в while
l oop.
У вас есть предложения, где может быть моя ошибка?