gsc.py

#!/usr/bin/python
"""Uso de Google Search Analytics API (part of Search Console API).

Mas info en: https://developers.google.com/webmaster-tools/

To use:
1) Install the Google Python client library, as shown at https://developers.google.com/webmaster-tools/v3/libraries.
2) Sign up for a new project in the Google APIs console at https://code.google.com/apis/console.
3) Register the project to use OAuth2.0 for installed applications.
4) Copy your client ID, client secret, and redirect URL into the client_secrets.json file included in this package.
5) Run the app in the command-line as shown below.

Sample usage:

  $ python search_analytics_api.py 'https://www.example.com/' '2015-05-01' '2015-05-30' --limit 50

"""
from __future__ import print_function
import argparse
import sys
import csv
import json
from datetime import datetime, timedelta
from googleapiclient import sample_tools

# Declare command-line flags.
argparser = argparse.ArgumentParser(add_help=False)
argparser.add_argument('property_uri', type=str, help=('Site or app URI to query data for (including ''trailing slash).'))
argparser.add_argument('start_date', type=str, help=('Start date of the requested date range in ''YYYY-MM-DD format.'))
argparser.add_argument('end_date', type=str, help=('End date of the requested date range in ''YYYY-MM-DD format.'))
argparser.add_argument('--limit', '-n', type=int, default=20, help=('Rows limit.'))

def main(argv):
  service, flags = sample_tools.init(
      argv, 'webmasters', 'v3', __doc__, __file__, parents=[argparser],
      scope='https://www.googleapis.com/auth/webmasters.readonly')

  start_date = datetime.strptime(flags.start_date, "%Y-%m-%d")
  end_date = datetime.strptime(flags.end_date, "%Y-%m-%d")
  
  for day in date_range(start_date, end_date):
    day = day.strftime("%Y-%m-%d")
    # Get top queries for the date range, sorted by click count, descending.
    # List of countries https://en.wikipedia.org/wiki/ISO_3166-1_alpha-3
    request = {
        'startDate': day,
        'endDate': day,
        'searchType': ['web'],
        'dimensions': ["page", "query", "country", "device"],
        'dimensionFilterGroups': [{
          'filters': [{
              'dimension': 'country',
              'expression': 'arg'
            }]
        }],
        'rowLimit': flags.limit
    }
    response = execute_request(service, flags.property_uri, request)
    print_table(response, flags.property_uri, day)

def date_range(start_date, end_date, delta=timedelta(days=1)):
  """
  Yields a stream of datetime objects, for all days within a range.
  The range is inclusive, so both start_date and end_date will be returned,
  as well as all dates in between.
  Args:
      start_date: The datetime object representing the first day in the range.
      end_date: The datetime object representing the second day in the range.
      delta: A datetime.timedelta instance, specifying the step interval. Defaults to one day.
  Yields:
      Each datetime object in the range.
  """
  current_date = start_date
  while current_date <= end_date:
      yield current_date
      current_date += delta

def execute_request(service, property_uri, request):
  """Executes a searchAnalytics.query request.

  Args:
    service: The webmasters service to use when executing the query.
    property_uri: The site or app URI to request data for.
    request: The request to be executed.

  Returns:
    An array of response rows.
  """
  return service.searchanalytics().query(
      siteUrl=property_uri, body=request).execute()


def print_table(response, gsc_property, day):
  """Prints out a response table.

  Each row contains key(s), clicks, impressions, CTR, and average position.

  Args:
    response: The server response to be printed as a table.
    gsc_property: The GSC property we are targeting.
  """
  
  if 'rows' not in response:
    print('Empty response')
    return

  rows = response['rows']
  # print(json.dumps(rows, indent=4, separators=(". ", " = ")))
  # print('Page', 'Keywords', 'Clicks', 'Impressions', 'CTR', 'Position', 'Device', 'Country', 'GSC Property',sep=',')
  filas = 0
  
  f = open("data_gsc_all_vc.csv", 'a')
  for row in rows:    
    page = row['keys'][0].encode('utf-8').lower()
    keywords = row['keys'][1].encode('utf-8').lower()
    device = row['keys'][2].encode('utf-8').lower()
    country = row['keys'][3].encode('utf-8').lower()
    clicks = row['clicks']
    impressions = row['impressions']
    ctr = row['ctr']
    position = row['position']

    filas += 1

    writer = csv.writer(f)
    # with open("data_gsc.csv", "a") as myfile:
      # print(day, keywords, page, clicks, impressions, ctr, position, gsc_property, country, device, negocio, sep=',', file=myfile)
    gsc_property = gsc_property.replace("https://","")
    gsc_property = gsc_property.replace("http://","")
    gsc_property = gsc_property.replace("/","")
    writer.writerow( (day, keywords, page, clicks, impressions, ctr, position, gsc_property, country, device) )
  print(day, ": ", filas, " resultados importados")
  f.close()
  # ['Date','Query','Page','Clicks','Impressions','CTR','AVG_position','Property','Country','Device']

if __name__ == '__main__':
  main(sys.argv)