气轻Python100 re.findall查找所有匹配

本程序添加了一个处理，就是把英文中的中文符号转换成英文符号。

import re

def qipy100:

txtdata = [‘@#%1、That‘s the first row。！第一行。’,

‘-=+20.That‘s second row．！第二行。’,

‘&……203.That‘s third row．?第三行。’]

p0 = ‘^.*\d{1,3}[、.]’

p1 = ‘[。！．?]{2}’

p2 = ‘(.?)([\u4e00-\u9fa5]+.?)’

pattern = re.compile(p2,re.S)

cmark =

emark =

mdict = dict(zip(cmark, emark))

p3 = “[” + “”.join(cmark) + “]”

for s in txtdata:

s1 = re.sub(p0, “”, s)

print(‘s1:’, s1)

m1 = re.search(p1, s1)

s2 = s1.replace(m1.group, m1.group[0])

s3 = list(pattern.findall(s2)[0])

s4 = s3[0]

m3 = re.findall(p3, s4)

for punctuation in m3:

print(‘punctuation:’, punctuation)

s4 = s4.replace(punctuation, mdict[punctuation])

s3[0] = s4

print(‘s3:’, s3)

return

if name == “main”:

执行结果

s1: That‘s the first row。！第一行。

s3: [“That’s the first row.”, ‘第一行’]

s1: That‘s second row．！第二行。

s3: [“That’s second row.”, ‘第二行’]

s1: That‘s third row．?第三行。

s3: [“That’s third row.”, ‘第三行’]