'How to get the google search console data using access_token or refresh token in python?
I'm trying to get the data from google search console in behalf of the user once they login it returns the access_token and refresh_token by using the access_token or refresh_token how to get the Google Search Console data (imperssion,click,pages). Same way i am getting the data from Google Analytics but in google search console it's not possible.
def extract_data(site, creds, num_days, output):
domain_name = get_domain_name(site)
create_project(domain_name)
full_path = domain_name + '/' + output
current_dates = get_dates_from_csv(full_path)
webmasters_service = authorize_creds(creds)
# Set up Dates
end_date = datetime.date.today() - relativedelta.relativedelta(days=3)
start_date = end_date - relativedelta.relativedelta(days=num_days)
delta = datetime.timedelta(days=1) # This will let us loop one day at the time
scDict = defaultdict(list)
while start_date <= end_date:
if current_dates is not None and current_dates.str.contains(
datetime.datetime.strftime(start_date, '%Y-%m-%d')).any():
start_date += delta
else:
# print('Start date at beginning: %s' % start_date)
maxRows = 25000 # Maximum 25K per call
numRows = 0 # Start at Row Zero
status = '' # Initialize status of extraction
# print("status status status status",status)
while (status != 'Finished'): # Test with i < 10 just to see how long the task will take to process.
request = {
'startDate': datetime.datetime.strftime(start_date, '%Y-%m-%d'),
'endDate': datetime.datetime.strftime(start_date, '%Y-%m-%d'),
'dimensions': ['date', 'page', 'query'],
'rowLimit': maxRows,
'startRow': numRows
}
response = execute_request(webmasters_service, site, request)
try:
# Process the response
for row in response['rows']:
scDict['date'].append(row['keys'][0] or 0)
scDict['page'].append(row['keys'][1] or 0)
scDict['query'].append(row['keys'][2] or 0)
scDict['clicks'].append(row['clicks'] or 0)
scDict['ctr'].append(row['ctr'] or 0)
scDict['impressions'].append(row['impressions'] or 0)
scDict['position'].append(row['position'] or 0)
# print('successful at %i' % numRows)
except:
print('error occurred at %i' % numRows)
# Add response to dataframe
df = pd.DataFrame(data=scDict)
df['clicks'] = df['clicks'].astype('int')
df['ctr'] = df['ctr'] * 100
df['impressions'] = df['impressions'].astype('int')
df['position'] = df['position'].round(2)
print('Numrows at the start of loop: %i' % numRows)
try:
numRows = numRows + len(response['rows'])
except:
status = 'Finished'
print('Numrows at the end of loop: %i' % numRows)
if numRows % maxRows != 0:
status = 'Finished'
start_date += delta
print('Start date at end: %s' % start_date)
write_to_csv(df, full_path)
return df
This is code i am getting in google search console this code using the webmasters_service = authorize_creds(creds) method but i want to access using access_token or refresh token.
This is the code used in google analytics.
def google_analytics_reporting_api_data_extraction(viewID, dim, met, start_date,
end_date, refresh_token,
transaction_type, goal_number,
condition):
viewID = viewID;
dim = dim;
met = met;
start_date = start_date;
end_date = end_date;
refresh_token = refresh_token;
transaction_type = transaction_type;
condition = condition
goal_number = goal_number
viewID = "".join(['ga%3A', viewID])
if transaction_type == "Goal":
met1 = "%2C".join([re.sub(":", "%3A", i) for i in met]).replace("XX", str(goal_number))
elif transaction_type == "Transaction":
met1 = "%2C".join([re.sub(":", "%3A", i) for i in met])
dim1 = "%2C".join([re.sub(":", "%3A", i) for i in dim])
credentials = client.OAuth2Credentials(
access_token=None, client_id=client_id, client_secret=client_secret, refresh_token=refresh_token,
token_expiry=3600, token_uri=GOOGLE_TOKEN_URI, user_agent='my-user-agent/1.0', revoke_uri=GOOGLE_REVOKE_URI)
credentials.refresh(httplib2.Http())
rt = (json.loads(credentials.to_json()))['access_token']
api_url = "https://www.googleapis.com/analytics/v3/data/ga?ids="
url = "".join(
[api_url, viewID, '&start-date=', start_date, '&end-date=', end_date, '&metrics=', met1, '&dimensions=',
dim1, '&max-results=1000000', condition, '&access_token=', rt])
data = pd.DataFrame()
dataa = pd.DataFrame()
users = []
final_date = []
# try:
r = requests.get(url)
# print("r values",list((r.json())['rows']))
# print("start_date",start_date)
start = datetime.datetime.strptime(start_date, "%Y-%m-%d")
end = datetime.datetime.strptime(end_date, "%Y-%m-%d")
date_generated = [start + datetime.timedelta(days=x) for x in range(0, (end - start).days)]
for each in date_generated:
date_value = each.date()
url = "".join(
[api_url, viewID, '&start-date=', str(each.date()), '&end-date=', str(each.date()), '&metrics=', met1,
'&dimensions=',
dim1, '&max-results=1000000', condition, '&access_token=', rt])
rr = requests.get(url)
dataa = pd.DataFrame(list((rr.json())['rows']))
users.append(dataa[0][0])
final_date.append(str(date_value))
# print("data and users", users, final_date)
data = pd.DataFrame(list((r.json())['rows']))
try:
data = pd.DataFrame(list((r.json())['rows']), columns=[re.sub("ga:", "", i) for i in met])
# data['date'] = start_date
# dim_data = pd.DataFrame(list((r.json())['rows']), columns=[re.sub("ga:", "", i) for i in dim])
return data, users, final_date
except:
print((r.json()))
In the above code by using refresh_token we access the data from google analytics. Like this way only i want the code in google search console. Please help me out
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|
