Created
April 1, 2020 23:22
-
-
Save hughlilly/660738c4e80ceaaa373b2fbefb40a232 to your computer and use it in GitHub Desktop.
Check AM API IDs to see if they exist
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import csv | |
import requests | |
import pandas | |
import time | |
from collections import namedtuple | |
from tqdm import tqdm | |
# Takes a .csv of API IDs, which are manipulated to URLs below | |
# Outputs a .csv | |
infile = "IDs.csv" | |
outfile = "results.csv" | |
# This header is for the output file | |
headers = ["url"] | |
with open(infile, mode='r') as f: | |
reader = csv.reader(f) | |
all_records = namedtuple('rec', next(reader)) | |
records = [all_records._make(row) for row in reader] | |
with open(outfile, mode='w+') as o: | |
w = csv.writer(o) | |
# Write header row | |
w.writerow(headers) | |
num = len(records) | |
print("Checking {} records...\n".format(num)) | |
with tqdm(total=num, bar_format="{percentage:3.0f}% {bar} [{n_fmt}/{total_fmt}] ", ncols=64) as pbar: | |
for r in records: | |
pbar.update(1) | |
# update the ".id" here according to the header of that column (or just rename the column to 'id') | |
identifier = r.id | |
# construct URL; update this according to the content type you're checking | |
url = "https://api.aucklandmuseum.com/id/humanhistory/object/" + identifier | |
# url = "https://api.aucklandmuseum.com/id/naturalsciences/object/" + identifier | |
# url = "https://api.aucklandmuseum.com/id/library/manuscriptsandarchives/" + identifier | |
req = requests.get(url, allow_redirects=False) | |
code = req.status_code | |
# only write URLs of 200 OK statuses | |
if code == 200: | |
w.writerow([url]) | |
time.sleep(.25) | |
else: | |
time.sleep(.25) | |
# Construct a Pandas dataframe from the output, and report the number of entries (= number of 200 OKs). | |
df = pandas.read_csv(outfile) | |
print("Found {} 200 OK statuses".format(len(df))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment