forked from xxg1413/python-cookbook
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathChapter2.py
More file actions
172 lines (124 loc) · 3.87 KB
/
Chapter2.py
File metadata and controls
172 lines (124 loc) · 3.87 KB
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
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
#!/usr/bin/python3
#encoding=utf8
def ch2_1():
'''
2.1 使用多个界定符分割字符串
一个字符串中的分隔符不固定需要使用re.split开灵活切割字符串
'''
print("\nch2_1:")
import re
line = '我 是中国;人,你是-哪国人'
result = re.split(r'[ ;,-]\s*', line)
print(result)
def ch2_2():
'''
2.2 在字符串的开头或者结尾处做文本匹配
startswith和endswith
'''
print("\nch2_2:")
import os
filenames = os.listdir(".")
md_file = [file for file in filenames if file.endswith((".md",".MD"))]
print(md_file)
https = ["https:","HTTPS:"]
urls =["http://baidu.com","www.qq.com:80","https://github.com","ftp://mirror.aliyun.com"]
https_url = [url for url in urls if url.startswith(tuple(https))]
print(https_url)
#使用正则
import re
result=re.match(r"^(https:)","https://github.com")
if result:
print(result.groups())
else:
print("no result")
def ch2_3():
'''
2.3利用Shell通配符做字符串匹配
使用fnmatch模块中的fnmatch和fnmatchcase
'''
print("\nch2_3:")
from fnmatch import fnmatch,fnmatchcase
#fnmatch按照平台是否区分大小写，window不区分
files = ["config.ini","data1.csv","data2.csv","ata_train.csv","README.md","CONTINUE.MD"]
print(files)
data_file = [file for file in files if fnmatch(file,"data*.csv")]
print(data_file)
#fnmatchcase 可以区分大小写
print(files)
data_file = [file for file in files if fnmatchcase(file, "*.MD")]
print(data_file)
def ch2_4():
'''
2.4 文本模式的匹配和查找
使用正则
'''
print("\nch2_4:")
text1 = "02/11/2017"
text2 = "02/11/2017 tomorrow is 02/12/2017"
import re
if re.match(r"\d+/\d+/\d+", text1):
print("yes")
else:
print("no")
date_p = re.compile(r"\d+/\d+/\d+")
if date_p.match(text1):
print("yes")
else:
print("no")
result = date_p.findall(text2)
print(result)
#增加捕获组 多次匹配或者查找，建议先编译
date_p = re.compile(r"(\d+)/(\d+)/(\d+)")
result = date_p.findall(text2)
for month,day, year in result:
print("{}-{}-{}".format(year,month,day))
def ch2_5():
'''
2.5 对字符串中的文本做查找和替换
'''
print("\nch2_5:")
text1 ="Today is 02/11/2017, 春节是02/26/2017"
import re
#先匹配，后替换
result = re.sub(r"(\d+)/(\d+)/(\d+)",r"\3-\1-\2", text1)
print(result)
data_p = re.compile(r"(\d+)/(\d+)/(\d+)")
from calendar import month_abbr
def change_date(m):
mon_name = month_abbr[int(m.group(1))]
return '{} {} {}'.format(m.group(2),mon_name,m.group(3))
result,count = data_p.subn(change_date, text1)
print("结果:",result, "\n总共替换:", count)
def ch2_6():
'''
2.6 以不区分大小写的方式对文本做检查和替换
使用re.IGNORECASE
'''
print("\nch2_6:")
text = "UPPER PYTHON, lower python, Mixed Python"
import re
result = re.findall(r"python", text, flags=re.IGNORECASE)
print(result)
#替换成相同的格式
result = re.sub("python", "snake", text, flags=re.IGNORECASE)
print(result) #注意snake是全部小写
def matchcase(word):
def replace(m):
text = m.group()
if text.isupper():
return word.upper()
elif text.islower():
return word.lower()
elif text[0].isupper():
return word.capitalize()
else:
return word
return replace
result = re.sub("python", matchcase("snake"), text, flags=re.IGNORECASE)
print(result)
def main():
for i in range(1,7):
func='ch2_%d()'%(i)
exec(func)
if __name__ == "__main__":
main()