You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
23 lines
476 B
23 lines
476 B
import os
|
|
|
|
# scraper/utils.py
|
|
|
|
|
|
def load_replacements(path):
|
|
repl = {}
|
|
if not path or not os.path.exists(path):
|
|
return repl
|
|
|
|
with open(path, encoding="utf-8") as f:
|
|
for line in f:
|
|
if "=>" in line:
|
|
k, v = line.strip().split("=>", 1)
|
|
repl[k.strip()] = v.strip()
|
|
return repl
|
|
|
|
|
|
def clean_text(text, repl_dict):
|
|
for src, tgt in repl_dict.items():
|
|
text = text.replace(src, tgt)
|
|
return text
|