mirror of
https://github.com/LibraHp/GetQzonehistory.git
synced 2024-12-28 15:09:10 +00:00
32 lines
988 B
Python
32 lines
988 B
Python
|
import re
|
||
|
|
|
||
|
|
|
||
|
|
# 提取两个字符串之间的内容
|
||
|
|
def extract_string_between(source_string, start_string, end_string):
|
||
|
|
start_index = source_string.find(start_string) + len(start_string)
|
||
|
|
end_index = source_string.find(end_string)
|
||
|
|
extracted_string = source_string[start_index:-37]
|
||
|
|
return extracted_string
|
||
|
|
|
||
|
|
|
||
|
|
# 去除多余的空格
|
||
|
|
def replace_multiple_spaces(string):
|
||
|
|
pattern = r'\s+'
|
||
|
|
replaced_string = re.sub(pattern, ' ', string)
|
||
|
|
return replaced_string
|
||
|
|
|
||
|
|
|
||
|
|
# 替换十六进制编码
|
||
|
|
def process_old_html(message):
|
||
|
|
def replace_hex(match):
|
||
|
|
hex_value = match.group(0)
|
||
|
|
byte_value = bytes(hex_value, 'utf-8').decode('unicode_escape')
|
||
|
|
return byte_value
|
||
|
|
|
||
|
|
new_text = re.sub(r'\\x[0-9a-fA-F]{2}', replace_hex, message)
|
||
|
|
start_string = "html:'"
|
||
|
|
end_string = "\'\,opuin"
|
||
|
|
new_text = extract_string_between(new_text, start_string, end_string)
|
||
|
|
new_text = replace_multiple_spaces(new_text).replace('\\', '')
|
||
|
|
return new_text
|