1 import jieba
 2 import io
 3
 4 #对句子进行分词
 5 def cut():
 6     f=open("E://luntan.txt","r+",encoding="utf-8")
 7     for line in f:
 8         seg_list=jieba.cut(line)
 9         #print(' '.join(seg_list))
10         for i in seg_list:
11             print(i)
12             write(i+" ")
13         #write(' '.join(seg_list))
14
15
16 #分词后写入
17 def write(contents):
18     f=open("E://luntan_cut.txt","a+",encoding="utf-8")
19     f.write(contents)
20     print("写入成功！")
21     f.close()
22
23 #创建停用词
24 def stopwordslist(filepath):
25     stopwords = [line.strip() for line in open(filepath, 'r', encoding='utf-8').readlines()]
26     return stopwords
27
28 # 对句子进行去除停用词
29 def seg_sentence(sentence):
30     sentence_seged = jieba.cut(sentence.strip())
31     stopwords = stopwordslist('E://stop.txt')  # 这里加载停用词的路径
32     outstr = ''
33     for word in sentence_seged:
34         if word not in stopwords:
35             if word != '\t':
36                 outstr += word
37                 outstr += " "
38     return outstr
39
40 #循环去除
41 def cut_all():
42     inputs = open('E://luntan_cut.txt', 'r', encoding='utf-8')
43     outputs = open('E//luntan_stop', 'w')
44     for line in inputs:
45         line_seg = seg_sentence(line)  # 这里的返回值是字符串
46         outputs.write(line_seg + '\n')
47     outputs.close()
48     inputs.close()
49
50 if __name__=="__main__":
51     cut()

 1 import io
 2 import re
 3
 4 patton=re.compile(r'title=".*"')
 5 def read():
 6     f=open("E://mhtml.txt","r+",encoding="utf-8")
 7     for line in f:
 8         line=line.rstrip("\n")
 9         m=patton.findall(line)
10         #print(line)
11         if len(m)!=0:
12             print(m)
13             write(str(m).lstrip("['title=\"").rstrip("\"']")+"\r")
14
15 def write(contents):
16     f=open("E://xinxi.txt","a+",encoding="utf-8")
17     f.write(contents)
18     print("写入成功！")
19     f.close()
20
21 if __name__=="__main__":
22     read()