From fa77ff6a2788527ceea750b9331528670c852668 Mon Sep 17 00:00:00 2001 From: Samuel Clay Date: Sat, 2 Jul 2022 13:11:25 -0400 Subject: [PATCH] Also scrub twitter authors for xml invalid chars. --- utils/twitter_fetcher.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/utils/twitter_fetcher.py b/utils/twitter_fetcher.py index 945220507..0354a6e07 100644 --- a/utils/twitter_fetcher.py +++ b/utils/twitter_fetcher.py @@ -471,7 +471,7 @@ class TwitterFetcher: # Remove unserializable control characters content = re.sub(r'[\x00-\x08\x0B-\x0C\x0E-\x1F\x7F-\x84\x86-\x9F\uFDD0-\uFDEF\uFFFE\uFFFF]', '', content) - + author_fullname = re.sub(r'[\x00-\x08\x0B-\x0C\x0E-\x1F\x7F-\x84\x86-\x9F\uFDD0-\uFDEF\uFFFE\uFFFF]', '', author_fullname) story = { 'title': tweet_title, 'link': "https://twitter.com/%s/status/%s" % (original_author_screen_name, user_tweet['id']),