65 lines
2.7 KiB
Python
65 lines
2.7 KiB
Python
|
import boto3
|
||
|
|
import pandas as pd
|
||
|
|
from concurrent.futures import ThreadPoolExecutor, as_completed
|
||
|
|
|
||
|
|
|
||
|
|
"""
|
||
|
|
This script is used to copy complex contract text files to a different folder in the same S3 bucket.
|
||
|
|
The script reads a CSV file that contains the filenames and their table counts. It filters the rows where the table count is greater than or equal to 1.
|
||
|
|
|
||
|
|
This script is NOT CLIENT SPECIFIC. It is a generic script that can be used for any client.
|
||
|
|
|
||
|
|
"""
|
||
|
|
|
||
|
|
|
||
|
|
# Function to copy a single file
|
||
|
|
def copy_file(bucket_name, source_prefix, dest_prefix, file_name, profile_name):
|
||
|
|
try:
|
||
|
|
# Initialize S3 client
|
||
|
|
session = boto3.Session(profile_name=profile_name)
|
||
|
|
s3 = session.client('s3')
|
||
|
|
copy_source = {'Bucket': bucket_name, 'Key': f'{source_prefix}/{file_name}'}
|
||
|
|
dest_key = f'{dest_prefix}/{file_name}'
|
||
|
|
s3.copy_object(CopySource=copy_source, Bucket=bucket_name, Key=dest_key)
|
||
|
|
print(f'Successfully copied from {copy_source} to {dest_key}')
|
||
|
|
except Exception as e:
|
||
|
|
# print(f'Failed to copy {file_name}: {e}')
|
||
|
|
print('File not in bucket. Skipping')
|
||
|
|
pass
|
||
|
|
|
||
|
|
# Function to process copying in parallel
|
||
|
|
def copy_files_in_parallel(bucket_name, source_prefix, dest_prefix, file_list,profile_name ,max_workers=10):
|
||
|
|
with ThreadPoolExecutor(max_workers=max_workers) as executor:
|
||
|
|
futures = [
|
||
|
|
executor.submit(copy_file, bucket_name, source_prefix, dest_prefix, file_name, profile_name=profile_name)
|
||
|
|
for file_name in file_list
|
||
|
|
]
|
||
|
|
for future in as_completed(futures):
|
||
|
|
future.result() # This will raise any exceptions that occurred during execution
|
||
|
|
|
||
|
|
# Main function
|
||
|
|
def main():
|
||
|
|
# Client bucket where the text files are stored
|
||
|
|
bucket_name = 'centene-national-contracting-files'
|
||
|
|
|
||
|
|
# This is used to copy complex contract text files to a different folder
|
||
|
|
source_prefix = 'batch6_16_file/txt_files'
|
||
|
|
dest_prefix_3a = 'batch6_16_file/complex_contract_files/txt_files'
|
||
|
|
max_workers = 50
|
||
|
|
profile_name = 'default' # Set this as per your AWS profile
|
||
|
|
|
||
|
|
# Read the table analysis file (from DS code) and read the filenames and their table counts
|
||
|
|
csv_file = 'C:\\Doczy\\National contracting\\Somefolder\\CNC-6to16-Table-Analysis.csv' # Replace with your CSV file path
|
||
|
|
file_df = pd.read_csv(csv_file)
|
||
|
|
|
||
|
|
# Filter rows where 'tables' value is greater than or equal to 1
|
||
|
|
complex_table_files = file_df[file_df['Table Count'] >= 1]
|
||
|
|
|
||
|
|
# Assuming the CSV has a column 'file_name' with the list of file names
|
||
|
|
file_list = complex_table_files['Filename_pdf'].tolist()
|
||
|
|
|
||
|
|
copy_files_in_parallel(bucket_name, source_prefix, dest_prefix_3a, file_list, profile_name = profile_name, max_workers=max_workers)
|
||
|
|
|
||
|
|
if __name__ == '__main__':
|
||
|
|
main()
|