Python | 正则表达式Re

Re模块

import re

str1 = ''asdf2020b_dev12dasdfasdf' #待匹配2020b_dev12d

result = re.search(r'\d{4}\w_(dev)\d{2}\w',str1)

#待匹配字符串
result.group() 
#待匹配字符串组1，即dev
result.group(1) 

Web

https://regexr.com/

速查表

贪婪模式

贪婪模式	尽可能多的匹配字符
非贪婪模式	尽可能少的匹配字符

非贪婪模式常用组合(.*?)

正则常用函数

1、re.findall(): 将匹配的全部内容放入到一个列表中

2、re.search():全局匹配，可根据group

3、re.match：从头开始匹配，只匹配字符串的开始

4、re.sub(pattern, ‘待替换字符串’, ‘原字符串’)

str1 = 'Spark-SQL'

pattern = r'-\w*'
result = re.sub(pattern, '-asdf', str1)
#Out: 'Spark-asdf'

组合使用flag

re.compile(‘foo’, re.IGNORECASE | re.DOTALL)

多行匹配实例

import re
import pandas as pd
inputfile_path = r'./cbk_output.c'
txt_ouput_path = r'./output.txt'
csv_output_path = r'./FUNC.csv'

'''
读取原文件
'''
with open(inputfile_path, 'r') as f:
    content = f.read()

'''
正则表达式编译
非贪婪模式开启
多行匹配开启

FUNC(void, COM_APPL_CODE) ComNotification_ESP_VLC_CDDCtrlActive_oESP_DriverAssistantStatus_oCH_CAN_4ea8c5b2_Rx(void)
{
   Com_ReceiveSignal(ComConf_ComSignal_ESP_VLC_CDDCtrlActive_oESP_DriverAssistantStatus_oCH_CAN_4ea8c5b2_Rx , (void*)&Com_Rawvalue_ESP_VLC_CDDCtrlActive_ESP_DriverAssistantStatus);

   Com_Phyvalue_ESP_VLC_CDDCtrlActive_ESP_DriverAssistantStatus = (float)(Com_Rawvalue_ESP_VLC_CDDCtrlActive_ESP_DriverAssistantStatus*(1.0f)+(0));
}

volatile uint32 Com_Rawvalue_ESP_VLC_CDDVehiHoldStatus_ESP_DriverAssistantStatus;
volatile float Com_Phyvalue_ESP_VLC_CDDVehiHoldStatus_ESP_DriverAssistantStatus;
FUNC(void, COM_APPL_CODE) ComNotification_ESP_VLC_CDDVehiHoldStatus_oESP_DriverAssistantStatus_oCH_CAN_558ca0e6_Rx(void)
{
   Com_ReceiveSignal(ComConf_ComSignal_ESP_VLC_CDDVehiHoldStatus_oESP_DriverAssistantStatus_oCH_CAN_558ca0e6_Rx , (void*)&Com_Rawvalue_ESP_VLC_CDDVehiHoldStatus_ESP_DriverAssistantStatus);

   Com_Phyvalue_ESP_VLC_CDDVehiHoldStatus_ESP_DriverAssistantStatus = (float)(Com_Rawvalue_ESP_VLC_CDDVehiHoldStatus_ESP_DriverAssistantStatus*(1.0f)+(0));
}
'''
raw = r'FUNC\(void, COM_APPL_CODE\).*?}'
pattern = re.compile(raw, re.DOTALL)


'''
正则表达式匹配
匹配所有满足条件的文本
返回类型：list
'''
result = re.findall(pattern, content)


'''
输出到文本
'''

f = open(txt_ouput_path, 'w')
for item in result:
    f.write(item)
    f.write('\n')
    f.write('\n')
f.close()