diff --git a/app/templates/mainpage_post.html b/app/templates/mainpage_post.html
index 7357457..5df7dd5 100644
--- a/app/templates/mainpage_post.html
+++ b/app/templates/mainpage_post.html
@@ -2,7 +2,7 @@
- Title
+ 单词词频
{{ yml['header'] | safe }}
{% if yml['css']['item'] %}
diff --git a/app/test/test_bug553_LinShan.py b/app/test/test_bug553_LinShan.py
new file mode 100644
index 0000000..393e82d
--- /dev/null
+++ b/app/test/test_bug553_LinShan.py
@@ -0,0 +1,66 @@
+# -*- coding: utf-8 -*-
+# Run the docker image using the following command:
+# docker run -d -p 4444:4444 selenium/standalone-chrome
+from selenium import webdriver
+from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
+from selenium.webdriver.support import expected_conditions as EC
+from selenium import webdriver
+from selenium.webdriver.support.wait import WebDriverWait
+from selenium.webdriver.common.by import By
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.keys import Keys
+import logging
+import time
+import pytest
+
+# driver = webdriver.Remote('http://localhost:4444/wd/hub', DesiredCapabilities.FIREFOX)
+# HOME_PAGE = 'http://121.4.94.30:91/'
+
+
+# 我使用的是Chrome浏览器，所以我又通过安装webdriver-manager插件来配置浏览器的驱动
+# 我通过 'pip install webdriver-manager==4.00' 命令安装webdriver-manager，并且设置其版本为4.00
+driver = webdriver.Chrome(ChromeDriverManager().install())
+HOME_PAGE = 'http://127.0.0.1:5000/'
+driver.implicitly_wait(10)
+
+
+@pytest.mark.parametrize("test_input",("‘test1’","'test2'","“test3”","it's","hello,I'm linshan","Happy New Year！？","My favorite book is 《Harry Potter》。"))
+@pytest.mark.parametrize("expected",(["test1"],["test2"],["test3"],["it's"],["hello","i'm","linshan"],["happy","new","year"],["potter","harry","my","favorite","book","is"]))
+def test_bug553_LinShan(test_input,expected):
+ try:
+ # 打开对应地址的网页
+ driver.get(HOME_PAGE)
+
+ # 浏览器最大窗口化
+ driver.maximize_window()
+
+ # 判断网页源代码中是否有English Pal -文字
+ assert 'English Pal -' in driver.page_source
+
+ # 将测试的数据输入到主页的textarea里
+ driver.find_element_by_xpath("//textarea[@name='content']").send_keys(Keys.CONTROL, "a")
+ driver.find_element_by_xpath("//textarea[@name='content']").send_keys(test_input)
+ time.sleep(2)
+
+ # 点击按钮获取单词
+ driver.find_element_by_xpath("//input[@value='get文章中的词频']").click()
+ time.sleep(2)
+
+ # 获取筛选后的单词
+ words = driver.find_elements_by_xpath("//p/a")
+
+ # 遍历获取到的单词，并判断单词与预期的相同
+ for word in words:
+ # 判断单词是否在预期结果中
+ assert word.text in expected
+
+ # 返回上一页网页
+ driver.find_element_by_xpath("//input[@value='确定并返回']").click()
+ time.sleep(2)
+
+ except Exception as e:
+ # 输出异常信息
+ logging.error(e)
+ # 关闭浏览器
+ finally:
+ driver.quit()
\ No newline at end of file
diff --git a/app/wordfreqCMD.py b/app/wordfreqCMD.py
index dcee74e..feeafbd 100644
--- a/app/wordfreqCMD.py
+++ b/app/wordfreqCMD.py
@@ -4,6 +4,7 @@
###########################################################################
import collections
+import html
import string
import operator
import os, sys # 引入模块sys，因为我要用里面的sys.argv列表中的信息来读取命令行参数。
@@ -39,7 +40,8 @@ def file2str(fname):#文件转字符
def remove_punctuation(s): # 这里是s是形参 (parameter)。函数被调用时才给s赋值。
- special_characters = '\_©~<=>+/[]*&$%^@.,?!:;#()"“”—‘’{}|' # 把里面的字符都去掉
+ special_characters = '\_©~<=>+/[]*&$%^@.,?!:;#()"“”—‘’{}|，。？！￥……（）、《》：；·' # 把里面的字符都去掉
+ s = html.unescape(s) # 将HTML实体转换为对应的字符，比如<会被识别为小于号
for c in special_characters:
s = s.replace(c, ' ') # 防止出现把 apple,apple 移掉逗号后变成 appleapple 情况
s = s.replace('--', ' ')
@@ -104,7 +106,7 @@ if __name__ == '__main__':
print('%s\t%d\t%s' % (x[0], x[1], youdao_link(x[0])))#函数导出
# 把频率的结果放result.html中
- make_html_page(sort_in_descending_order(L), 'result.html')
+ make_html_page(sort_in_descending_order(L), 'result.html')
print('\nHistory:\n')
if os.path.exists('frequency.p'):