amywieliczka

PAD-Infrastructure-Repo:
    config                                      # this is the sceptre config directory, each directory
                                                # represents a (sceptre-ism) stack group, and each file 
                                                # represents a (sceptre and cloudformation-ism) stack
                                                # within that group
                    
        config.yml                              # this is the root config file, enforcing pad-wide
                                                # defaults like: 
                                                # project_name: pad
                                                # region: us-west-2

amywieliczka

import json
import urllib.request
import urllib.parse
import boto3

# This lambda function is configured in the AWS console to have a "function URL" 
# a dedicated https endpoint for this function. In this configuration, the 
# event parameter is a dict describing the request made to the function URL
def lambda_handler(event, context):
    

amywieliczka

Cloudfront Distributions in DSC AWS Account

Distro ID	Description	Alternate Domain Names	Last Modified Date
E1RSO6N0RTXH8X	calisphere.org	calisphere.org	July 3, 2023 at 8:19:58 PM UTC
EA4P9EMQ9TNK0	calisphere-test.cdlib.org	calisphere-test.cdlib.org	May 24, 2023 at 5:24:22 PM UTC
E215A3D7QO74OG	this may not be needed	thumbnails.calisphere.org	May 16, 2023 at 11:45:55 PM UTC
E2U9T45UP3ZOJ8	real IIIF		June 1, 2022 at 4:29:03 PM UTC
E2BKF7XHHT31S3	legacy OAC video	av-cdn.calisphere.org	December 8, 2021 at 7:46:23 PM UTC
E1HBH81MROL4M5	legacy redirect	www.calisphere.cdlib.org, calisphere.cdlib.org	December 8, 2021 at 7:45:03 PM UTC

amywieliczka

import csv

def read_csv_file_into_array(filename):
  csv_file = open(filename)
  lines = csv.reader(csv_file, delimiter=',')

  data = []
  for row_num, row in enumerate(lines):
    if row_num == 0:
      continue

amywieliczka

import asyncio
import aiohttp
import aioboto3
import boto3
import xmltodict
import json
import time

async def build_fetchRequest(oai, resumptionToken):
    try:

amywieliczka

import boto3
import uuid
from urllib.parse import unquote_plus
import csv
import socket
import re
import gzip

s3_client = boto3.client('s3')
googlebot_whitelist_ip = []

amywieliczka

from pyspark.sql import SparkSession

def grade_collection(id):
    untitledItemsDF = spark.sql(f"SELECT COUNT(*) FROM calisphere \
       WHERE array_contains(collection_url, 'https://registry.cdlib.org/api/v1/collection/{id}/') \
       AND array_contains(title, 'Untitled')")
    totalItemsDF = spark.sql(f"SELECT COUNT(*) FROM calisphere \
       WHERE array_contains(collection_url, 'https://registry.cdlib.org/api/v1/collection/{id}/')")
    untitledItemsDF.show() / totalItemsDF.show()

amywieliczka