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..388f5da
--- /dev/null
+++ b/app/test/test_bug553_LinShan.py
@@ -0,0 +1,58 @@
+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 selenium.webdriver.common.keys import Keys
+import logging
+import time
+import pytest
+
+@pytest.mark.parametrize("test_input,expected",
+ [("‘test1’", "test1"),
+ ("'test2'", "test2"),
+ ("“test3”", "test3"),
+ ("it's", "it's"),
+ ("hello,I'm linshan", ["hello","i'm","linshan"]),
+ ("Happy New Year！？", ["happy","new","year"]),
+ ("My favorite book is 《Harry Potter》。", ["potter","harry","my","favorite","book","is"])])
+def test_bug553_LinShan(test_input,expected, driver, URL):
+ try:
+ # 打开对应地址的网页
+ driver.get(URL)
+
+ # 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(1)
+
+ # 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(1)
+
+ # 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(0.1)
+
+ except Exception as e:
+ # 输出异常信息
+ logging.error(e)
+ # 关闭浏览器
+ driver.quit()
+ finally:
+ driver.quit()
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'):