Created
February 1, 2023 14:02
-
-
Save FelixWeichselgartner/62e20e0747554109dd05996106217db9 to your computer and use it in GitHub Desktop.
convert broken latin1 to utf8 wordpress sql table backups
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
with open('exp-my-database-utf8.sql', 'r', encoding='utf8') as s: | |
input = s.read() | |
output = '' | |
split_char = 't' | |
split = input.split(split_char) | |
corrected = 0 | |
not_corrected = 0 | |
for i in split: | |
try: | |
wrong = i.encode('windows-1252') | |
right = wrong.decode('utf8') | |
output += right | |
corrected += 1 | |
except (UnicodeEncodeError, UnicodeDecodeError) as e: | |
print(i) | |
output += i | |
not_corrected += 1 | |
output += split_char | |
output = output[:-1] | |
with open('output.sql', 'w', encoding='utf8') as o: | |
o.write(output) | |
print(f'corrected {corrected} segments') | |
print(f'couldnt corrected {not_corrected} segments') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment