Created
December 5, 2023 17:30
-
-
Save Dylancyclone/4a5a241e8f0e097e47db8ea9a0a3bae5 to your computer and use it in GitHub Desktop.
Exports every KB article from zendesk into text documents
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 os | |
import datetime | |
import csv | |
import requests | |
from bs4 import BeautifulSoup | |
zendesk = "https://[endpoint].zendesk.com" | |
language = "en-us" | |
date = datetime.date.today() | |
backup_path = os.path.join(str(date), language) | |
if not os.path.exists(backup_path): | |
os.makedirs(backup_path) | |
log = [] | |
endpoint = zendesk + "/api/v2/help_center/{locale}/articles.json".format( | |
locale=language.lower() | |
) | |
while endpoint: | |
response = requests.request( | |
"GET", | |
endpoint, | |
# auth=("", ""), | |
headers={ | |
"Content-Type": "application/json", | |
"Cookie": "", | |
}, | |
) | |
if response.status_code != 200: | |
print("Failed to retrieve articles with error {}".format(response.status_code)) | |
exit() | |
data = response.json() | |
for article in data["articles"]: | |
if article["body"] is None: | |
continue | |
filename = "{title}.txt".format(title=article["title"].replace("[/<>:\"/|?*]", "")) | |
with open(os.path.join(backup_path, filename), mode="w", encoding="utf-8") as f: | |
f.write(article["title"] + "\n" + BeautifulSoup(article["body"]).get_text()) | |
print("{title} copied!".format(title=article["title"])) | |
log.append((filename, article["title"], article["author_id"])) | |
endpoint = data["next_page"] | |
with open(os.path.join(backup_path, "_log.csv"), mode="wt", encoding="utf-8") as f: | |
writer = csv.writer(f) | |
writer.writerow(("File", "Title", "Author ID")) | |
for article in log: | |
writer.writerow(article) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment