[Python] Python Typeerror list indices must be integers or slices, not str

I'm relatively new to Python and I'm trying to setup a script that will read a json file that I'm importing from an api and then write that file to a parquet file.

In that JSON file I have fields with lists such as email addresses:

{
"cc_emails": [
"Jimmy@somewhere.com",
"Homer@Nutella.com"
],
"fwd_emails": [],
"reply_cc_emails": [
"Jimmy@somewhere.com",
"Homer@Nutella.com"
],
"ticket_cc_emails": [
"JimBeam@Bourbon.com",
"Homer@Nutella.com"
],
"ticket_bcc_emails": [],
"fr_escalated": false,
"spam": false,
"email_config_id": 1234455,


When I use the below code to try and turn these into a string ie:
cc_emails Jimmy@Somewhere.com, Homer@Nutella.com

I get the error list indices must be integers or slices, not str

I've attempted to do this with this code:

import requests
import json
import pandas as pd
from pyspark.sql import SparkSession
from datetime import datetime, timedelta
from requests.auth import HTTPBasicAuth

# Function to get tickets incrementally with pagination
def get_incremental_tickets(updated_since):
url = f'https://{FRESHDESK_DOMAIN}.freshdesk.com/api/v2/tickets'
headers = {
'Content-Type': 'application/json'
}
params = {
'updated_since': updated_since,
'per_page': 100 # Set the number of tickets per page to 100 (maximum allowed by Freshdesk)
}
all_tickets = []
page = 1

while True:
params['page'] = page
response = requests.get(url, headers=headers, params=params, auth=(API_KEY, 'X'))

if response.status_code == 200:
tickets = response.json()
if not tickets:
break
all_tickets.extend(tickets)
page += 1
if page > 300:
break
else:
print(f'Error: {response.status_code}, Response: {response.text}')
break

return all_tickets

if __name__ == '__main__':
# Fetch tickets updated since 2023 in smaller increments
start_date = datetime(2025, 1, 1)
all_tickets = []

while start_date < datetime.now():
end_date = start_date + timedelta(days=30)
tickets = get_incremental_tickets(start_date.isoformat())
if tickets:
all_tickets.extend(tickets)
print(f'Found {len(tickets)} tickets from {start_date} to {end_date}')
start_date = end_date

if all_tickets:
print('Found Tickets')

# Normalize the JSON data to include custom fields as columns
df = pd.json_normalize(all_tickets, sep='_')

# Flatten nested custom fields
custom_fields_df = pd.json_normalize([ticket['custom_fields'] for ticket in all_tickets], sep='_')
custom_fields_df['id'] = [ticket['id'] for ticket in all_tickets]
df = df.merge(custom_fields_df, on='id', how='left')

combined_cc_emails = [", ".join(sublist) for sublist in all_tickets["ticket_cc_emails"].tolist()]

# Create a DataFrame with all fields
df_combined = pd.DataFrame({'id': all_tickets['id'], 'combined_cc_emails': combined_cc_emails})


df['responder_id'] = df['responder_id'].fillna(0).astype('int64')

# Save DataFrame to a Parquet file
parquet_table_name = f"{table_name}.parquet"
parquet_file_path = parquet_file_path_base + parquet_table_name
df.to_parquet(parquet_file_path, engine='pyarrow', index=False)
print(f'Tickets saved to {parquet_file_path}')
delta_table_name = f"{schema.lower()}.{table_name}"
print(delta_table_name)

# Load parquet file to data lake table
spark = SparkSession.builder.appName("FabricNotebook").getOrCreate()
df_spark = spark.read.parquet(parquet_file_path)

# Write the Spark DataFrame to the Delta table
df_spark.write.mode("overwrite").option("overwriteSchema", "true").format("delta").saveAsTable(delta_table_name)
print(f'Tickets saved to Delta table {delta_table_name}')

else:
print('No tickets found or an error occurred.')



Let me know if you need more code samples. Wasn't sure how much to include.

My ultimate goal is to place these into a table. Hence the need to concatenate them together.

error:

---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
Cell In[23], line 69
61 df = df.merge(custom_fields_df, on='id', how='left')
63 # Ensure list fields are kept as arrays of strings
64 # list_fields = ['cc_emails', 'fwd_emails', 'reply_cc_emails', 'ticket_cc_emails', 'ticket_bcc_emails', 'to_emails']
65 # for field in list_fields:
66 # df[field] = df[field].apply(lambda x: x if isinstance(x, list) else [])
67 # Flatten the list of lists
68 # Assuming all_tickets is a DataFrame
---> 69 combined_cc_emails = [", ".join(sublist) for sublist in all_tickets["ticket_cc_emails"].tolist()]
71 # Create a DataFrame with all fields
72 df_combined = pd.DataFrame({'id': all_tickets['id'], 'combined_cc_emails': combined_cc_emails})

TypeError: list indices must be integers or slices, not str

Continue reading...