get_zendesk_voice_comment_audits.py

import pandas as pd
from pandas.io.json import json_normalize
import requests
from configparser import ConfigParser

dir_path = '.'

config = ConfigParser()
config_file = dir_path+'/config.ini'
config.read(config_file)

api_key=config['zendesk']['api_key']
email = config['zendesk']['email']
subdomain = config['zendesk']['subdomain']

user = 'USEREMAIL' + '/token'
pwd = api_key

def get_voice_comments(ticket_ids):
  all_voice_comment_dfs = []
  total_tickets = len(ticket_ids)

  for i, ticket_id in enumerate(ticket_ids):
      event_dfs = []
      url = f'https://YOUR-ZENDESK-DOMAIN.com/api/v2/tickets/{ticket_id}/audits.json'
      response = requests.get(url, auth=(user, pwd))
      response_json = response.json()
      event_dfs = []
      for audit in response_json['audits']:
          try:
              audit_events_df = json_normalize(audit['events'],sep='_')
              event_dfs.append(audit_events_df)
          except Exception as ex:
              print(ex)
              continue

      all_audit_events_df = pd.concat(event_dfs,ignore_index=True, sort=False)
      voice_comment_df = all_audit_events_df[all_audit_events_df['type'].str.lower().str.contains('voice')]

      if i % 100 == 0 and i != 0:
          print(i / total_tickets * 100.0, "% of tickets completed")
          print(len(all_voice_comment_dfs), ' dfs extracted with voice comments')

      if voice_comment_df.empty == False:
          voice_comment_df['ticket_id'] = ticket_id
          all_voice_comment_dfs.append(voice_comment_df)
      else:
          continue

  voice_comment_df = pd.concat(all_voice_comment_dfs, ignore_index=True, sort=False)
  #voice_comment_df.to_csv('./voice_comments.csv',index=False)
  return voice_comment_df