Forked from tushortz/UNICODE to ASCII python replace
Created
December 22, 2022 01:20
-
-
Save codeslp/7d9b52b59a25f789f2e3e5d5a0fc9df8 to your computer and use it in GitHub Desktop.
Function to replace some annoying characters
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
| def unicodetoascii(text): | |
| TEXT = (text. | |
| replace('\\xe2\\x80\\x99', "'"). | |
| replace('\\xc3\\xa9', 'e'). | |
| replace('\\xe2\\x80\\x90', '-'). | |
| replace('\\xe2\\x80\\x91', '-'). | |
| replace('\\xe2\\x80\\x92', '-'). | |
| replace('\\xe2\\x80\\x93', '-'). | |
| replace('\\xe2\\x80\\x94', '-'). | |
| replace('\\xe2\\x80\\x94', '-'). | |
| replace('\\xe2\\x80\\x98', "'"). | |
| replace('\\xe2\\x80\\x9b', "'"). | |
| replace('\\xe2\\x80\\x9c', '"'). | |
| replace('\\xe2\\x80\\x9c', '"'). | |
| replace('\\xe2\\x80\\x9d', '"'). | |
| replace('\\xe2\\x80\\x9e', '"'). | |
| replace('\\xe2\\x80\\x9f', '"'). | |
| replace('\\xe2\\x80\\xa6', '...').# | |
| replace('\\xe2\\x80\\xb2', "'"). | |
| replace('\\xe2\\x80\\xb3', "'"). | |
| replace('\\xe2\\x80\\xb4', "'"). | |
| replace('\\xe2\\x80\\xb5', "'"). | |
| replace('\\xe2\\x80\\xb6', "'"). | |
| replace('\\xe2\\x80\\xb7', "'"). | |
| replace('\\xe2\\x81\\xba', "+"). | |
| replace('\\xe2\\x81\\xbb', "-"). | |
| replace('\\xe2\\x81\\xbc', "="). | |
| replace('\\xe2\\x81\\xbd', "("). | |
| replace('\\xe2\\x81\\xbe', ")") | |
| ) | |
| return TEXT |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment