Merge pull request 'Bug553_LinShan' (#104) from Bug553_LinShan into Alpha-snapshot20230621

Reviewed-on: mrlan/EnglishPal#104
Alpha-snapshot20230621
林杉 2024-04-25 15:12:54 +08:00
commit df34770af0
3 changed files with 63 additions and 3 deletions

View File

@ -2,7 +2,7 @@
<html lang="en">
<head>
<meta charset="UTF-8">
<title>Title</title>
<title>单词词频</title>
{{ yml['header'] | safe }}
{% if yml['css']['item'] %}

View File

@ -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()

View File

@ -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'):