diff --git a/app/wordfreqCMD.py b/app/wordfreqCMD.py index e56ba0c..dc231b9 100644 --- a/app/wordfreqCMD.py +++ b/app/wordfreqCMD.py @@ -39,7 +39,8 @@ 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 + 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('--', ' ') @@ -103,6 +104,7 @@ if __name__ == '__main__': for x in sort_in_descending_order(L): 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') @@ -117,6 +119,7 @@ if __name__ == '__main__': # 合并频率 lst_history = pickle_idea.dict2lst(d) d = pickle_idea.merge_frequency(L, lst_history) + pickle_idea.save_frequency_to_pickle(d, 'frequency.p') diff --git a/requirements.txt b/requirements.txt index e2d1e1f..2746a3b 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,4 +1,3 @@ Flask==1.1.2 selenium==3.141.0 PyYAML~=6.0 -pony==0.7.16