优化无效词汇过滤

2021-05-07 22:53:15 +08:00 · 2021-05-07 22:53:15 +08:00 · 6f6df9479b
commit 6f6df9479b
parent 33522e4791
1 changed files with 3 additions and 1 deletions
--- a/task.py
+++ b/task.py
@ -50,7 +50,9 @@ def do_task():
            word_amount = {}
            # print(word_amount)
            for word in word_list:
-                if word in ["。", "，", "！", "：", "“", "”", "!", ".", ",", ":", '"', "+", "-", "[", "]", "\\", "/"]:
+                if re.search(
+                        r"[。|，|、|？|！|,|.|!|?|\\|/|+|\-|`|~|·|@|#|￥|$|%|^|&|*|(|)|;|；|‘|’|“|”|'|_|=|\"]",
+                        word) is not None:
                    continue
                # 判断该词是否之前已经出现
                if word_amount.get(word) is not None: