解决Python从Jira获取链接时遇到的问题

1 import jieba
 2 all_mode=jieba.cut('南京市长江大桥',cut_all=True)
 3 alls=" ".join(all_mode)
 4 print('【全模式】：',alls)
 5 jingque=jieba.cut('南京市长江大桥',cut_all=False)
 6 jings=" ".join(jingque)
 7 print('【精确模式】：',jings)
 8 search=jieba.cut_for_search('南京市长江大桥')
 9 searchs=" ".join(search)
10 print('【搜索引擎模式】：',searchs)
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.

1 import jieba
 2 # 创建停用词列表
 3 def stopwordslist():
 4     stopwords = [line.strip() for line in open('中文停用词库.txt',encoding='gbk').readlines()]
 5     return stopwords
 6 # 对句子进行中文分词
 7 def seg_depart(sentence):
 8     # 对文档中的每一行进行中文分词
 9     print("正在分词")
10     sentence_depart = jieba.cut(sentence.strip())
11     # 创建一个停用词列表
12     stopwords = stopwordslist()
13     # 输出结果为outstr
14     outstr = ''
15     # 去停用词
16     for word in sentence_depart:
17         if word not in stopwords:
18             if word != '\t':
19                 outstr += word
20                 outstr += " "
21     return outstr
22 if __name__ == '__main__':
23     # 给出文档路径
24     filename = "斗破苍穹.txt"
25     outfilename = "out.txt"
26     inputs = open(filename, 'r', encoding='UTF-8')
27     outputs = open(outfilename, 'w', encoding='UTF-8')
28     
29     # 将输出结果写入ou.txt中
30     for line in inputs:
31         line_seg = seg_depart(line)
32         outputs.write(line_seg + '\n')
33         print("-------------------正在分词和去停用词-----------")
34     outputs.close()
35     inputs.close()
36     print("删除停用词和分词成功！！！")
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
21.
22.
23.
24.
25.
26.
27.
28.
29.
30.
31.
32.
33.
34.
35.
36.

1 import jieba.analyse
2 #读取文件,返回一个字符串，使用utf-8编码方式读取，该文档位于此python同以及目录下
3 path='斗破苍穹.txt'
4 with open(path,'r',encoding='utf-8')as ff:
5     data=ff.read()
6 #返回词频最高的20个词
7 word=jieba.analyse.extract_tags(data,topK=20)
8 print(' '.join(word))
1.
2.
3.
4.
5.
6.
7.
8.